Patent Application 17275430 - SYSTEMS AND METHODS FOR MANAGING ENERGY STORAGE - Rejection

Patent Application 17275430 - SYSTEMS AND METHODS FOR MANAGING ENERGY STORAGE

Title: SYSTEMS AND METHODS FOR MANAGING ENERGY STORAGE SYSTEMS

Application Information

• Invention Title: SYSTEMS AND METHODS FOR MANAGING ENERGY STORAGE SYSTEMS
• Application Number: 17275430
• Submission Date: 2025-05-15T00:00:00.000Z
• Effective Filing Date: 2021-03-11T00:00:00.000Z
• Filing Date: 2021-03-11T00:00:00.000Z
• National Class: 705
• National Sub-Class: 007250
• Examiner Employee Number: 94100
• Art Unit: 3625
• Tech Center: 3600

Rejection Summary

• 102 Rejections: 0
• 103 Rejections: 4

Cited Patents

The following patents were cited in the rejection:

• US 0081563🔗
• US 0282193🔗
• US 0650825🔗
• US 0023307🔗
• US 9315190🔗

Office Action Text

    DETAILED ACTION
Status of Claims
The following is a Final Office Action in response to amendments received on 01/21/2025.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action.  
Claims 1, 2, 4, 5, 8, 10, 14, 23, and 32-36 are amended. Claims 12-13, 15-22, 18-22, 24-29, and 31 are cancelled. Claims 1-11, 14, 23, 30, and 32-36 are considered in this Office Action. Claims 1-11, 14, 23, 30, and 32-36 are currently pending. 

Claim Objections
Claims 1-11, 14, 17, 23, 30, 32, and 34 are objected to under 37 CFR 1.75(c) as being in improper form because a claim should not refer to a preceding claim. See MPEP § 608.01(n).  Accordingly, the claims have not been further treated on the merits.

Response to Arguments
In regard to the 35 USC §103 rejection, applicant’s arguments and amendments, which are primarily raised in light of applicant’s amendments, an updated 35 USC §103 rejection will address applicant’s arguments and amendments. 
In regard to the 35 USC §103 rejection, applicant’s arguments and amendments, an updated 35 USC §103 rejection will address applicant’s arguments and amendments. 
 
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.

Claims 1-11, 14, 23, 30, and 32-36 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-patentable subject matter.  The claims are directed to an abstract idea without significantly more.
Claims 1-11, 14, 23, 30, and 32-36 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.  The judicial exception is not integrated into a practical application.  The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.  The eligibility analysis in support of these findings is provided below, in accordance with the “Patent Subject Matter Eligibility Guidance” (as explained MPEP 2106).
With respect to Step 1 of the eligibility inquiry (as explained in MPEP 2106), it is first noted that the system (claims 1-11, 14, 23, and 36), the method (claims 30, 32, and 33), and the one non-transitory computer-readable medium (claim 34 and 35) are directed to an eligible category of subject matter (i.e., process, machine, and article of manufacture respectively).  Thus, Step 1 is satisfied.
With respect to Step 2, and in particular Step 2A Prong One, it is next noted that the claims recite an abstract idea by reciting concepts of concepts performed in the human mind including an observation, evaluation, judgment, opinion or by a human using a pen and paper, which falls into the “mental processes” group within the enumerated groupings of abstract ideas.  The claims further fall into “Mathematical concept” group. The use of computer/computer components to perform the abstract idea does not negate the abstractness of the claims. See MPEP 2106.04(a)(2)(III). The limitations reciting the abstract idea are highlighted in italics and the limitation directed to additional elements highlighted in bold, as set forth in exemplary claim 36, are: A system, comprising: at least one computer processor; and at least one computer-readable storage medium having encoded thereon instructions that, when executed, program the at least one computer processor to: receive sensor data from one or more sensors associated with an electric vehicle; for each candidate model of a plurality of candidate models: determine a reward for using the candidate model in a context, wherein the context comprises a value of a feature selected from a group consisting of: a feature relating to an environment in which the electric vehicle is operating, wherein the feature relating to the environment is determined based at least in part on the sensor data; a feature relating to the electric vehicle; and a feature relating to one or more energy storage devices associated with the electric vehicle, wherein the feature relating to the one or more energy storage devices is determined based at least in part on the sensor data; select a model from the plurality of candidate models, based at least in part on the respective rewards for using the candidate models in the context, wherein each of the plurality of candidate models is a model for estimating a value of a parameter for the electric vehicle; and determine an energy management strategy used to control operation of the electric vehicle based, at least in part, on the selected model. Claims 33 and 35 recite substantially the same limitation as claim 36 and therefore subject to the same rationale.  
With respect to Step 2A Prong Two, the judicial exception is not integrated into a practical application.  The additional elements are directed a system comprising and at least one non-transitory computer-readable medium having encoded thereon instructions which, when executed, cause at least one computer processor, and receive sensor data from one or more sensors associated with an electric vehicle (recited at high level of generality and amounts to data gathering means) to implement the abstract idea.  However, these elements fail to integrate the abstract idea into a practical application because they fail to provide an improvement to the functioning of a computer or to any other technology or technical field, fail to apply the exception with a particular machine, fail to effect a transformation of a particular article to a different state or thing, and fail to apply/use the abstract idea in a meaningful way beyond generally linking the use of the judicial exception to a particular technological environment. Furthermore, these elements have been fully considered, however they are directed to the use of generic computing elements (Applicant’s Specification figure 8 describes high level general purpose computer) to perform the abstract idea, which is not sufficient to amount to a practical application and is tantamount to simply saying “apply it” using a general purpose computer, which merely serves to tie the abstract idea to a particular technological environment (computer based operating environment) by using the computer as a tool to perform the abstract idea, which is not sufficient to amount to particular application.  
Accordingly, because the Step 2A Prong One and Prong Two analysis resulted in the conclusion that the claims are directed to an abstract idea, additional analysis under Step 2B of the eligibility inquiry must be conducted in order to determine whether any claim element or combination of elements amount to significantly more than the judicial exception.
With respect to Step 2B of the eligibility inquiry, it has been determined that the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.  The additional limitations are directed to: a system comprising: at least one computer processor; and at least one computer-readable storage medium having encoded thereon instructions that, when executed, program the at least one computer processor and at least one non-transitory computer-readable medium having encoded thereon instructions which, when executed, cause at least one computer processor, and receive sensor data from one or more sensors associated with an electric vehicle (recited at high level of generality and amounts to data gathering means).  These elements have been considered, but merely serve to tie the invention to a particular operating environment (i.e., computer-based implementation), though at a very high level of generality and without imposing meaningful limitation on the scope of the claim.  In addition, Applicant’s Specification (figure 8) describes generic off-the-shelf computer-based elements for implementing the claimed invention, and which does not amount to significantly more than the abstract idea, which is not enough to transform an abstract idea into eligible subject matter.  Such generic, high-level, and nominal involvement of a computer or computer-based elements for carrying out the invention merely serves to tie the abstract idea to a particular technological environment, which is not enough to render the claims patent-eligible, as noted at pg. 74624 of Federal Register/Vol. 79, No. 241, citing Alice, which in turn cites Mayo.  
In addition, when taken as an ordered combination, the ordered combination adds nothing that is not already present as when the elements are taken individually.  There is no indication that the combination of elements integrate the abstract idea into a practical application.  Their collective functions merely provide conventional computer implementation. Therefore, when viewed as a whole, these additional claim elements do not provide meaningful limitations to transform the abstract idea into a practical application of the abstract idea or that the ordered combination amounts to significantly more than the abstract idea itself.
The dependent claims have been fully considered as well (i.e., claims 1, 2, 7, 8, 9, 11, and 14 recite a plurality a computer processor, local processor, and remote processor. These elements fail to integrate the abstract idea into a practical application because they fail to provide an improvement to the functioning of a computer or to any other technology or technical field, fail to apply the exception with a particular machine, fail to effect a transformation of a particular article to a different state or thing, and fail to apply/use the abstract idea in a meaningful way beyond generally linking the use of the judicial exception to a particular technological environment. Furthermore, these elements have been fully considered, however they are directed to the use of generic computing elements (Applicant’s Specification figure 8 describes high level general purpose computer) to perform the abstract idea, which is not sufficient to amount to a practical application and is tantamount to simply saying “apply it” using a general purpose computer, which merely serves to tie the abstract idea to a particular technological environment (computer based operating environment) by using the computer as a tool to perform the abstract idea, which is not sufficient to amount to particular application. These elements have been considered, but merely serve to tie the invention to a particular operating environment (i.e., computer-based implementation), though at a very high level of generality and without imposing meaningful limitation on the scope of the claim.  In addition, Applicant’s Specification (figure 8) describes generic off-the-shelf computer-based elements for implementing the claimed invention, and which does not amount to significantly more than the abstract idea, which is not enough to transform an abstract idea into eligible subject matter.  Such generic, high-level, and nominal involvement of a computer or computer-based elements for carrying out the invention merely serves to tie the abstract idea to a particular technological environment, which is not enough to render the claims patent-eligible, as noted at pg. 74624 of Federal Register/Vol. 79, No. 241, citing Alice, which in turn cites Mayo.  The additional elements have been considered however recited at high level and fail to apply/use the abstract idea in a meaningful way beyond generally linking the use of the judicial exception to a particular technological environment), however, similar to the finding for claims above, these claims are similarly directed to the abstract idea of mental processes and mathematical concept without integrating it into a practical application and with, at most, a general purpose computer that serves to tie the idea to a particular technological environment, which does not add significantly more to the claims.  The ordered combination of elements in the dependent claims (including the limitations inherited from the parent claim(s)) add nothing that is not already present as when the elements are taken individually.  There is no indication that the combination of elements improves the functioning of a computer or improves any other technology.  Their collective functions merely provide conventional computer implementation.  Accordingly, the subject matter encompassed by the dependent claims fails to amount to significantly more than the abstract idea.

Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA  35 U.S.C. 102 and 103 (or as subject to pre-AIA  35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.  
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.

The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary.  Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 11, 23, 30, 32, and 34 are rejected under 35 U.S.C. 103 as being unpatentable over Millstein (US 10, 417565 B1, hereinafter “Millstein”) in view of Rajesh Tyagi (US 2013/0282193 A1, hereinafter “Tyagi”) in view of Prasanta Panda (US 2016/0650825 A1, hereinafter “Panda”), as applied in claims 33, 35, and 36, and further in view of Yi Lu Murphey (NPL “Intelligent Hybrid Vehicle Power Control—Part I: Machine Learning of Optimal Vehicle Power” published October 2012, hereinafter “Murphey”).
Claim 1/30/34
Millstein teaches:
The system of claim 36, wherein the at least one computer processor is programmed to: estimate the value of the parameter for the electric vehicle (the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations and the factors that affect such variables are primarily measurable by a sensor or other device);
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous art Murphey teaches:
 estimate a value of a parameter for the electric vehicle using a plurality of machine learning models including a first machine learning model and a second machine learning model(fig. 3 and fig. 11 illustrates P-at and ωeng which represent values of parameter of an energy application which is Hybrid Electrical Vehicle as disclosed in abstract. Page 3527 describes two sets of neural networks (NNi Pbatt , NNi ωeng ) have been developed to learn the optimal power split generated by the DP for each of the 11 roadway types and traffic congestion levels Ri, i = 1,..., 11. The neural network NNi Pbatt predicts Pbatt, which is the optimal battery power, and the neural network NNi ωeng predicts the optimal engine speed ωeng for the roadway type and traffic congestion level Ri.), 
wherein the second machine learning model is configured to receive as input, at least one output of the first machine learning model, and the value of the parameter is estimated, at least in part, based on an output of the second machine learning model (Fig. 7 and fig. 3 illustrates the right neural network which presents the driving trend NN while the neural network NNi Pbatt predicts Pbatt, which is the optimal battery power. Fig .7 illustrates the output of the driving trend neural network, “Driving trend prediction” is used as input in DT(t)/Driving trends to NNi Pbatt as disclosed in page 3527 and fig. 11a).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein and Tyagi with Murphey to include machine learning models in the determination and analyzing vehicle context information, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Claim 11
Millstein teaches:
The system of claim 10, wherein: the plurality of candidate models comprises a first plurality of candidate models (fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250));
and the at least one computer processor is further programmed to: for each candidate model of a second plurality of candidate models, determine a reward for using the candidate model in a second context, wherein the second context comprises a value of a second feature different from the first feature (col. 10 lines 21-32 A prediction is then generated for each unique building energy-consumption model/variable behavior model combination. The Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250). Col. 10 lines 54-57 The Analyzer outputs an energy-savings proposal that lists the possible energy-savings measures that satisfy feasibility and return-on-investment constraints (step 320)); select a model from the second plurality of candidate models, based at least in part on the respective rewards for using the candidate models in the second context((col. 10 lines 21-32 A prediction is then generated for each unique building energy-consumption model/variable behavior model combination. The Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250). Col. 10 lines 54-57 The Analyzer outputs an energy-savings proposal that lists the possible energy-savings measures that satisfy feasibility and return-on-investment constraints (step 320)); 
for each candidate model of the second plurality of candidate models: the candidate model comprises an estimation model that maps one or more inputs to an estimated value of the parameter(col. 10 lines 21-32 A prediction is then generated for each unique building energy-consumption model/variable behavior model combination. The Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250). Col. 10 lines 54-57 The Analyzer outputs an energy-savings proposal that lists the possible energy-savings measures that satisfy feasibility and return-on-investment constraints (step 320));
 and the reward for using the candidate model in the second context is based, at least in part, on accuracy of the estimation model when deployed in the second context((col. 10 lines 21-32 A prediction is then generated for each unique building energy-consumption model/variable behavior model combination. The Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250). Col. 10 lines 54-57 The Analyzer outputs an energy-savings proposal that lists the possible energy-savings measures that satisfy feasibility and return-on-investment constraints (step 320)); 
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous art Tyagi teaches:
the context comprises a first context; the feature comprises a first feature ([0020] Processor 112 may execute programs for monitoring and controlling operation of various customer devices, such as electric loads 118, sensors 120, renewable 122, energy storage resources 124, and plug in electric vehicles (PEV) or plug in hybrid electric vehicles (PHEV) 126. Sensors 120 may include electric meters, thermostats, occupancy sensors, humidity gauges, and other such devices. Renewable resources 122 may include solar and/or wind power devices, for example. Fig. 2 and [0025] step 12 allows obtaining a grid system load. For example, the grid system load may be forecasted, estimated, or otherwise obtained); 
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein with Tyagi to include the context comprises a first context; the feature comprises a first feature in the determination and analyzing context information, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous art Murphey teaches:
 the selected model comprises a first machine learning model; the model selected from the second plurality of candidate models comprises the second machine learning model (fig. 3 and fig. 11 illustrates P-at and ωeng which represent values of parameter of an energy application which is Hybrid Electrical Vehicle as disclosed in abstract. Page 3527 describes two sets of neural networks (NNi Pbatt , NNi ωeng ) have been developed to learn the optimal power split generated by the DP for each of the 11 roadway types and traffic congestion levels Ri, i = 1,..., 11. The neural network NNi Pbatt predicts Pbatt, which is the optimal battery power, and the neural network NNi ωeng predicts the optimal engine speed ωeng for the roadway type and traffic congestion level Ri. Fig. 7 and fig. 3 illustrates the right neural network which presents the driving trend NN while the neural network NNi Pbatt predicts Pbatt, which is the optimal battery power. Fig .7 illustrates the output of the driving trend neural network, “Driving trend prediction” is used as input in DT(t)/Driving trends to NNi Pbatt as disclosed in page 3527 and fig. 11a).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein and Tyagi with Murphey to include the selection of models the first machine learning model and the second plurality of candidate models comprises the second machine learning model in the determination and analyzing vehicle context information, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Claim 23/32
Millstein teaches:
an estimated climate control power demand associated with the electric vehicle (col. 6 lines 14-23 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations and the factors that affect such variables are primarily measurable by a sensor or other device. Col. 6 lines 66- col. 7 lines 1-15 Each of the energy-consumption equations in the model includes one or more variables. In order to predict how much energy will be consumed by the non-plug-load systems in the building during a period of time, the Analyzer needs to understand what factors influence the behavior of the variables and how they do so. Accordingly, the Analyzer builds behavior models for the variables based on input data related to the mechanical/electrical systems and input data related to weather conditions. Such input data is received by the Analyzer during a training period (step 160). All or substantially all (e.g., 95%) the inputs to the Analyzer that are used to create behavior models can be classified as “measurement data.” Measurement data is data resulting from a measurement by a sensor, an automated system, or a conventional measuring device (e.g., a ruler, thermometer, a barometer, etc.)).
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous art Murphey teaches:
The system of claim 1, wherein the plurality of machine learning models further includes a third machine learning model and a fourth machine learning model; the second machine learning model is further configured to receive as input, at least one output of the third machine learning model and at least one output of the fourth machine learning model ( Pages 3524 and 3525 describe “We developed a multilayered and multiclass neural network, NN_RT&TC, for the prediction of roadway types and traffic congestion levels, as shown in Fig. 5”. The examiner notes the multiclass machine neural network contains at least 4 machine learning subclass models. Fig. 7 and fig. 3 illustrates the right neural network which presents the driving trend NN while the neural network NNi Pbatt predicts Pbatt, which is the optimal battery power. Fig .7 illustrates the output of the driving trend neural network, “Driving trend prediction” is used as input in DT(t)/Driving trends to NNi Pbatt as disclosed in page 3527 and fig. 11a);
the first machine learning model is trained to output an estimated state of charge of an energy storage device associated with the energy application (Figure 11 illustrates SOC associated with hybrid vehicle. Fig. 7 and fig. 3 illustrates the right neural network which presents the driving trend NN while the neural network NNi Pbatt predicts Pbatt, which is the optimal battery power. Fig .7 illustrates the output of the driving trend neural network, “Driving trend prediction” is used as input in DT(t)/Driving trends to NNi Pbatt as disclosed in page 3527 and fig. 11a); the third machine learning model is trained to output an estimated velocity profile associated with the electric vehicle (Figure 11 illustrates vehicle speed associated with hybrid vehicle. Fig. 7 and fig. 3 illustrates the right neural network which presents the driving trend NN while the neural network NNi Pbatt predicts Pbatt, which is the optimal battery power. Fig .7 illustrates the output of the driving trend neural network, “Driving trend prediction” is used as input in DT(t)/Driving trends to NNi Pbatt as disclosed in page 3527 and fig. 11a); the fourth machine learning model is trained to output an estimated [parameter] associated with the electric vehicle (Figure 11 illustrates plurality of parameters associated with hybrid vehicle. Fig. 7 and fig. 3 illustrates the right neural network which presents the driving trend NN while the neural network NNi Pbatt predicts Pbatt, which is the optimal battery power. Fig .7 illustrates the output of the driving trend neural network, “Driving trend prediction” is used as input in DT(t)/Driving trends to NNi Pbatt as disclosed in page 3527 and fig. 11a); and the second machine learning model is trained to output a total power demand for the electric vehicle based, at least in part, on the estimated state of charge, the estimated velocity profile, and the … provided as input to the second machine learning model fig. 3 and fig. 11 illustrates P-at and ωeng which represent values of parameter of an energy application which is Hybrid Electrical Vehicle as disclosed in abstract. Page 3527 describes two sets of neural networks (NNi Pbatt , NNi ωeng ) have been developed to learn the optimal power split generated by the DP for each of the 11 roadway types and traffic congestion levels Ri, i = 1,..., 11. The neural network NNi Pbatt predicts Pbatt, which is the optimal battery power, and the neural network NNi ωeng predicts the optimal engine speed ωeng for the roadway type and traffic congestion level Ri. Fig. 7 and fig. 3 illustrates the right neural network which presents the driving trend NN while the neural network NNi Pbatt predicts Pbatt, which is the optimal battery power. Fig .7 illustrates the output of the driving trend neural network, “Driving trend prediction” is used as input in DT(t)/Driving trends to NNi Pbatt as disclosed in page 3527 and fig. 11a).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein and Tyagi with Murphey to include machine learning models in the determination and analyzing vehicle context information, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Millstein (US 10, 417565 B1, hereinafter “Millstein”) in view of Rajesh Tyagi (US 2013/0282193 A1, hereinafter “Tyagi”) in view of Prasanta Panda (US 2016/0650825 A1, hereinafter “Panda”), as applied in claim 36, and further in view of Jay Lee (US 2010/0023307 A1, hereinafter “Lee”).
Claim 3
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Lee teaches:
The system of claim 36, wherein: selecting a model from the plurality of candidate models comprises: with a selected probability E: select a model from the plurality of candidate models uniformly at random; and with probability 1 - E. select a model from the plurality of candidate models that has a highest reward with respect to the context ([0055] The environment of the disclosed reinforcement learning network is defined through historical data. The values of the historical data are utilized to calculate the reward of each prediction model that is incorporated in the framework. [0099] The probability of a random action selection was set to be 0.1 in order to obtain more "exploration" of all the actions in the action set for better choice.  The most appropriate prediction model can be selected according to the highest Q-value for the state-action pair (highest reward)).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein and Tyagi with Lee to include in selecting a model from the plurality of candidate models comprises: with a selected probability E: select a model from the plurality of candidate models uniformly at random; and with probability 1 - E. select a model from the plurality of candidate models that has a highest reward with respect to the context, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Claims 2, 4, 5, 8-10, 14, 33, 35, and 36 are rejected under 35 U.S.C. 103 as being unpatentable over Millstein (US 10, 417565 B1, hereinafter “Millstein”) in view of Rajesh Tyagi (US 2013/0282193 A1, hereinafter “Tyagi”) in view of Prasanta Panda (US 2016/0650825 A1, hereinafter “Panda”).
Claim 2
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Tyagi teaches:
The system of claim 36, wherein: the context comprises a current context((0020]  Processor 112 may execute programs for monitoring and controlling operation of various customer devices, such as electric loads 118, sensors 120, renewable 122, energy storage resources 124, and plug in electric vehicles (PEV) or plug in hybrid electric vehicles (PHEV) 126. Sensors 120 may include electric meters, thermostats, occupancy sensors, humidity gauges, and other such devices. Renewable resources 122 may include solar and/or wind power devices, for example. Fig. 2 and [0025] step 12 allows obtaining a grid system load. For example, the grid system load may be forecasted, estimated, or otherwise obtained); the at least one computer processor is programmed to select a model from the plurality of candidate models in response to detecting a change from a prior context to the current context during operation of the energy application([0021]A demand response (DR) module 128 may be used to evaluate a marginal savings relative to the dispatch cost, if a demand response event is performed. A controller 129, as may include appropriate circuitry, may be configured to determine a control strategy to perform a dispatch made up of a demand response event, an energy storage event, or both. That is, a demand response event and/or an energy storage event, which may be selected to co-optimize an integrated utilization of demand response resources 111 and energy storage resources 109, 124 to meet a given objective based at least in part on the respective marginal savings of the demand response event and/or the energy storage event.); and the at least one computer processor is further programmed to deploy the selected model for the electric vehicle in the current context([0032]step 30 allows estimating at least one aggregate demand response profile for each potential group of demand response participants. Step 32 and remainder steps shown in FIG. 3, indicate that the evaluating of marginal savings regarding a demand response event for each potential group of demand response participants includes the following: Based on a respective aggregate profile of a respective demand response group being evaluated, step 34 allows adjusting an original load forecast. Step 36 allows revising a dispatch cost based on the adjusted load forecast. Step 38 allows calculating a savings in the dispatch cost relative to the original load forecast. Step 40 allows subtracting a cost (e.g., an option or threshold cost) of the demand response event from the calculated savings to determine a net savings, and, prior to stop step 44, step 42 allows selecting a demand response group with a highest normalized savings.).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein with Tyagi to include the context comprises a current context; the at least one computer processor is programed to select a model from the plurality of candidate models in response to detecting a change from a prior context to the current context during operation of the energy application; and the at least one computer processor is further programmed to deploy the selected model for the energy application in the current context in the determination and analyzing context information, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Claim 4
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Tyagi teaches:
The system of claim 36, wherein: the reward for using a candidate model in the context is based on data collected from previously deploying the candidate model for the electric vehicle in that context([0023] An events database 134 may be used to store historical data of events, such as demand response events and energy storage events, which may have been performed in accordance with the control strategy. The historical data can include information on customer utility usage including load type, time of use (TOU), duration of use, shed or demand response events, and energy storage charge/discharge, for example. In addition, the database 134 stores event data for each customer site. More specifically, the database 134 stores historical information on whether a customer site participated in a demand response event, the start time and end time, day of week, season, etc. In addition, the amount of load reduction and rebound may be stored in database 134. Data related to response forecasting and expected future benefit calculations may also be stored in database 134.).  
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein with Tyagi to include the reward for using a candidate model in the context is based on data collected from previously deploying the candidate model for the energy application in that context.in the determination and analyzing context information to determine reward, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.
Claim 5
Millstein teaches
The system of claim 36, wherein: the reward for using a candidate model in the context is based on data collected from deploying the candidate model for a plurality of electric vehicle in that context( Col. 6 lines 10-25 In response to receiving, via the user interface, information that enables the Analyzer to identify the components in and the configuration of a plurality of non-plug-load mechanical/electrical systems in a building (“the mechanical/electrical systems”), the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations and the factors that affect such variables are primarily measurable by a sensor or other device.  Col. 4 lines 21-33 he Analyzer is able to identify potential energy-saving measures by modeling the energy consumption of alternate physical configurations of the mechanical/electrical systems. The models for the alternate configurations are used to predict the energy consumption of the building if the alternate configurations were implemented. If an alternate configuration results in a lower energy-consumption prediction, the Analyzer identifies that configuration as a potential energy-savings measure).  

Claim 8
Millstein teaches:
The system of claim 36, wherein: the plurality of candidate models comprises a first plurality of candidate models(fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250)); the […] processor is programmed to: 
determine a reward for each candidate model of the first plurality of candidate models(col. 10 lines 21-32 A prediction is then generated for each unique building energy-consumption model/variable behavior model combination. The Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250). Col. 10 lines 54-57 The Analyzer outputs an energy-savings proposal that lists the possible energy-savings measures that satisfy feasibility and return-on-investment constraints (step 320)); and select a model from the first plurality of candidate models, based at least in part on the respective rewards(col. 10 lines 29-39 The Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250). In response to one of the alternate energy-consumption predictions being the lowest energy consumption prediction, the Analyzer identifies potential energy-savings measures by identifying one or more differences between the physical configurations and component settings associated with the lowest energy-consumption prediction and the current configurations and component settings of the mechanical/electrical system(s) (step 260).); 
the […] processor is programmed to: determine a reward for each candidate model of a second plurality of candidate models (col. 10 lines 21-32 A prediction is then generated for each unique building energy-consumption model/variable behavior model combination. The Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250). Col. 10 lines 54-57 The Analyzer outputs an energy-savings proposal that lists the possible energy-savings measures that satisfy feasibility and return-on-investment constraints (step 320))); 
select a model from the second plurality of candidate models, based at least in part on the respective rewards; and transmit, to the local processor, an indication of the model selected by the […] processor (col. 10 lines 21-32 The Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250). In response to one of the alternate energy-consumption predictions being the lowest energy consumption prediction, the Analyzer identifies potential energy-savings measures by identifying one or more differences between the physical configurations and component settings associated with the lowest energy-consumption prediction and the current configurations and component settings of the mechanical/electrical system(s) (step 260));
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Tyagi:
the at least computer one processor comprises a local processor associated with the electric vehicle ([0020]  Processor 112 may execute programs for monitoring and controlling operation of various customer devices, such as electric loads 118, sensors 120, renewable 122, energy storage resources 124, and plug in electric vehicles (PEV) or plug in hybrid electric vehicles (PHEV) 126. Sensors 120 may include electric meters, thermostats, occupancy sensors, humidity gauges, and other such devices. Renewable resources 122 may include solar and/or wind power devices, for example. Fig. 2 and [0025] step 12 allows obtaining a grid system load. For example, the grid system load may be forecasted, estimated, or otherwise obtained); 
the at least one computer processor further comprises a remote processor associated with a plurality of electric vehicle ([0044]-[0045] Fig. 1 illustrates a local processor and [0044] the system may be implemented by way of software and hardware (e.g., processor, sensors, etc), which may include but is not limited to firmware, resident software, microcode, etc. Furthermore, parts of the processor system can take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system);
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein with Tyagi to include the at least computer one processor comprises a local processor associated with the electric vehicle and the at least one computer processor further comprises a remote processor associated with a plurality of electric vehicle, because it will provide efficient use of system resources by implementing both local and remote processing units.

Claim 9 
Millstein teaches:
The system of claim 8, wherein the first plurality of candidate models is a subset of the second plurality of candidate models(col. 9 lines 62-67- col 10 lines 1-13   the Analyzer creates a system energy-consumption model for the alternative configuration (step 220). This is done by first creating component energy-consumption models for components in each alternative configuration and then aggregating the component energy consumption models to create the alternate system-level model (i.e., using the same process described with respect to 130-140 in FIG. 1.) The Analyzer then creates one or more alternate energy-consumption models (non-plug-load) for the building based on one or more alternative configurations of the mechanical/electrical systems (step 230). Like step 150 in FIG. 1, this is done by aggregating system-level models, factoring in any interactions between systems. the Analyzer creates an alternate building-level model of energy consumption for each possible combination of existing and alternate system-level models).
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Tyagi teaches:
 […] the local processor and […] the remote processor (([0020]  Processor 112 may execute programs for monitoring and controlling operation of various customer devices, such as electric loads 118, sensors 120, renewable 122, energy storage resources 124, and plug in electric vehicles (PEV) or plug in hybrid electric vehicles (PHEV) 126. Sensors 120 may include electric meters, thermostats, occupancy sensors, humidity gauges, and other such devices. Renewable resources 122 may include solar and/or wind power devices, for example. Fig. 2 and [0025] step 12 allows obtaining a grid system load. For example, the grid system load may be forecasted, estimated, or otherwise obtained and [0044]-[0045] Fig. 1 illustrates a local processor and [0044] the system may be implemented by way of software and hardware (e.g., processor, sensors, etc), which may include but is not limited to firmware, resident software, microcode, etc. Furthermore, parts of the processor system can take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system).  
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein with Tyagi to include a local processor and a remote processor, because it will provide efficient use of system resources by implementing both local and remote processing units.

Claim 10
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Tyagi teaches:
The system of claim 36, wherein: each candidate model of the plurality of candidate models comprises an energy management strategy that maps one or more inputs to a power distribution among the one or more energy storage devices associated with the electric vehicle ([0021]A controller 129, as may include appropriate circuitry, may be configured to determine a control strategy to perform a dispatch made up of a demand response event, an energy storage event, or both. That is, a demand response event and/or an energy storage event, which may be selected to co-optimize an integrated utilization of demand response resources 111 and energy storage resources 109, 124 to meet a given objective based at least in part on the respective marginal savings of the demand response event and/or the energy storage event. [0022] the control strategy may be further based on parameters, (e.g., demand response and energy storage parameters) which may be stored in a database 136 and may be indicative of an aggregate of hybrid operational capabilities resulting from the integrated utilization of the demand response energy storage resources relative to the given objective. For example, the energy storage resources may include at least some energy storage resources (e.g., certain batteries), which may be suitable for applications involving a discharge over a period of hours with a similarly long period for recharging (e.g., one charge/discharge cycle per day) while other types of batteries may be suitable for a relatively fast discharge over a period of seconds or minutes, which may involve multiple cycles per day. Similarly, the respective response of each DR group may have its own operational capabilities, which may appropriately complement the operational capabilities of the energy storage resources relative to the specific requirements of the given objective).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein with Tyagi to include each candidate model of the plurality of candidate models comprises an energy management strategy that maps one or more inputs to a power distribution among the one or more energy storage devices associated with the electric vehicle, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Claim 14
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Tyagi teaches:
The system of claim 36, wherein: each candidate model of the plurality of candidate models comprises- an energy storage device model that maps one or more inputs to an output relating to an energy storage device associated with the electric vehicle - an energy application model that maps one or more inputs to an output relating to the electric vehicle; or an environment model that maps one or more inputs to an output relating to the environment in which the electric vehicle is operating([0021]A controller 129, as may include appropriate circuitry, may be configured to determine a control strategy to perform a dispatch made up of a demand response event, an energy storage event, or both. That is, a demand response event and/or an energy storage event, which may be selected to co-optimize an integrated utilization of demand response resources 111 and energy storage resources 109, 124 to meet a given objective based at least in part on the respective marginal savings of the demand response event and/or the energy storage event. [0022] the control strategy may be further based on parameters, (e.g., demand response and energy storage parameters) which may be stored in a database 136 and may be indicative of an aggregate of hybrid operational capabilities resulting from the integrated utilization of the demand response energy storage resources relative to the given objective. For example, the energy storage resources may include at least some energy storage resources (e.g., certain batteries), which may be suitable for applications involving a discharge over a period of hours with a similarly long period for recharging (e.g., one charge/discharge cycle per day) while other types of batteries may be suitable for a relatively fast discharge over a period of seconds or minutes, which may involve multiple cycles per day. Similarly, the respective response of each DR group may have its own operational capabilities, which may appropriately complement the operational capabilities of the energy storage resources relative to the specific requirements of the given objective).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein with Tyagi to include each candidate model of the plurality of candidate models comprises- an energy storage device model that maps one or more inputs to an output relating to an energy storage device associated with the energy application- an energy application model that maps one or more inputs to an output relating to the energy application; or an environment model that maps one or more inputs to an output relating to the environment in which the energy application is operating, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Claim 36/33/35
Millstein teaches:

A system, comprising: at least one computer processor; and at least one computer-readable storage medium having encoded thereon instructions that, when executed, program the at least one computer processor (col. 12 lines 65- col 13 lines 1-3 computer system has one or more memory units, disks, or other physical, computer-readable storage media for storing software instructions, as well as one or more processors for executing the software instruction)to: 
for each candidate model of a plurality of candidate models: determine a reward for using the candidate model in a context (Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device),
prediction model based at least in part on the respective rewards for using the candidate models in the context, and determine an energy management strategy used to control operation of the electric vehicle based, at least in part, on the selected model (fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250).
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Tyagi teaches:
receive sensor data from one or more sensors associated with an electric vehicle ([0020] Processor 112 may execute programs for monitoring and controlling operation of various customer devices, such as electric loads 118, sensors 120, renewable 122, energy storage resources 124, and plug in electric vehicles (PEV) or plug in hybrid electric vehicles (PHEV) 126. Sensors 120 may include electric meters, thermostats, occupancy sensors, humidity gauges, and other such devices. Renewable resources 122 may include solar and/or wind power devices, for example. Fig. 2 and [0025] step 12 allows obtaining a grid system load. For example, the grid system load may be forecasted, estimated, or otherwise obtained);
wherein the context comprises a value of a feature selected from a group consisting of: a feature relating to an environment in which  the electric vehicle is operating, wherein the feature relating to the environment is determined based at least in part on the sensor data; a feature relating to the  electric vehicle; and a feature relating to one or more energy storage devices associated with  the electric vehicle, wherein the feature relating to the one or more energy storage devices is determined based at least in part on the sensor data ([0020]  Processor 112 may execute programs for monitoring and controlling operation of various customer devices, such as electric loads 118, sensors 120, renewable 122, energy storage resources 124, and plug in electric vehicles (PEV) or plug in hybrid electric vehicles (PHEV) 126. Sensors 120 may include electric meters, thermostats, occupancy sensors, humidity gauges, and other such devices. Renewable resources 122 may include solar and/or wind power devices, for example. Fig. 2 and [0025] step 12 allows obtaining a grid system load. For example, the grid system load may be forecasted, estimated, or otherwise obtained).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein with Tyagi to include the context comprises a value of a feature selected from a group consisting of: a feature relating to an environment in which an energy application is operating; a feature relating to the energy application; and a feature relating to one or more energy storage devices associated with the energy application, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state for an energy application.
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference Panda teaches:
select a model from the plurality of candidate models, […] wherein each of the plurality of candidate models is a model for estimating a value of a parameter for the electric vehicle ([0054]and [0068] the variable voltage processor 102 is further configured to select the appropriate forecasting model from the group of forecasting models having the least error measure among the error measures for each of the forecasting model. The least error measured forecasting model may be the most accurate forecasting model to predict the future workload of the variable voltage processor 102).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein and Tyagi with Panda to include select a model from the plurality of candidate models wherein each of the plurality of candidate models is a model for estimating a value of a parameter for the electric vehicle, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state for an energy application.

Claims 6 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Millstein (US 10, 417565 B1, hereinafter “Millstein”) in view of Rajesh Tyagi (US 2013/0282193 A1, hereinafter “Tyagi”) in view of Prasanta Panda (US 2016/0650825 A1, hereinafter “Panda”), as applied in claim 36, further in view of Qing Wang (US 2014/0081563 A1, hereinafter “Wang”).
Claim 6
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference, however analogous art Wang teaches:
The system of claim 36, wherein: the reward for using a candidate model in the context is based on data collected from performing simulation with the candidate model in that context ([0067] Use of models or simulations may reduce time and costs associated with live vehicle testing to the extent possible. Also use of simulation and testing to create tables offboard leads to reduced real-time computations by the vehicle controller when the vehicle is operated. [0031] An algorithm for use with the vehicle 10 uses pattern prediction from a driving pattern identification method and off-board simulations (or vehicle tests) to provide an EOT % estimation for the vehicle).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein and Tyagi with Wang with Wang to include the reward for using a candidate model in the context is based on data collected from performing simulation with the candidate model in that context in the determination and analyzing vehicle context information, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Claim 7
Millstein teaches:
The system of claim 36, wherein: each candidate model of the plurality of candidate models belongs to a model category; each candidate model of the plurality of candidate models has previously been deployed in the context; and the at least one computer processor is further programmed to: (Col. 6 lines 10-25 In response to receiving, via the user interface, information that enables the Analyzer to identify the components in and the configuration of a plurality of non-plug-load mechanical/electrical systems in a building (“the mechanical/electrical systems”), the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations and the factors that affect such variables are primarily measurable by a sensor or other device.  Col. 4 lines 21-33 he Analyzer is able to identify potential energy-saving measures by modeling the energy consumption of alternate physical configurations of the mechanical/electrical systems. The models for the alternate configurations are used to predict the energy consumption of the building if the alternate configurations were implemented. If an alternate configuration results in a lower energy-consumption prediction, the Analyzer identifies that configuration as a potential energy-savings measure);
While Millstein Col. 6 lines 10-25 the Analyzer identifies a component energy-consumption model (a “component-level model”) for one or more components in each of the mechanical/electrical systems (steps 120, 130). Each component-level model is an applicable energy-consumption equation (e.g., a thermodynamic equation) having one or more variables. The variables in the component energy-consumption equations (different candidate model) and the factors (context data) that affect such variables are primarily measurable by a sensor or other device and fig. 2 steps #250 and #260 for identifying energy-saving measures by modeling how alternate configurations and/or settings of the mechanical/electrical systems consume energy, where the Analyzer compares all the alternate energy-consumption predictions, as well as the baseline energy-consumption prediction, to identify the lowest energy-consumption prediction (step 250), Millstein does not explicitly teach the following, however analogous reference analogous art Wang teaches:
determine whether the model category comprises one or more candidate models that have not been deployed in the context ([0038] The algorithm may also be based on vehicle simulation models that represent the actual vehicle with built-in controllers. For example, the simulation may accurately compute the PHEV EOT % under any driving pattern represented by typical driving cycles. These simulation results may be compared with the vehicle test results for accuracy e.g. the examiner notes The simulations will deploy models under any and all driving patterns, including ones that have not been deployed for a particular context); and in response to determining that the model category comprises one or more candidate models that have not been deployed in the context, select a model from the one or more candidate models that have not been deployed in the context; and the at least one computer processor is programmed to select a model from the plurality of candidate models, which have previously been deployed in the context, in response to determining that the model category does not comprise any candidate model that has not been deployed in the context[0038] The algorithm may also be based on vehicle simulation models that represent the actual vehicle with built-in controllers. For example, the simulation may accurately compute the PHEV EOT % under any driving pattern represented by typical driving cycles. These simulation results may be compared with the vehicle test results for accuracy e.g. the examiner notes The simulations will deploy models under any and all driving patterns, including ones that have not been deployed for a particular context. [0040] If no immediate or forced aftertreatment-based engine-on state is required at 54, the algorithm proceeds to 58, and monitors for any engine-on (or engine pull up) requests that are triggered by the vehicle state, such as a driving command (i.e. total power demand and speed request) SOC condition, temperature, overvoltage protection, climate request, or the like. When such an engine-on request occurs, the algorithm proceeds to 60 and estimates the time to complete one or more designated aftertreatment procedures (T.sub.c) assuming it begins at the current time).
It would have been obvious to one of ordinary skill in the art at the time of the invention to modify the teaching of Millstein, Tyagi and Panda with Wang to include determining that the model category of  one or more candidate models that have not been deployed in the context, select a model from the one or more candidate models that have not been deployed in the context in that context in the determination and analyzing vehicle context information, because it will provide improved efficiency and accuracy of prediction of effective energy saving mode to be arranged under a current power state.

Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US 20190372345 A1
Methods And Systems for An Automated Utility Marketplace Platform
Bain; Nicholas Jordan et al.
US 20180186357 A1
Vehicle Control System and Method
Deshpande; Sharath Srinivas et al.
US 20170120773 A1
Optimization Of Cruising Voltage for Life and Fuel Economy Performance in Advanced Start-Stop Systems
Zhang; Zhenli et al.
US 9315190 B2
Hybrid electric vehicle preferred mode
Yu; Hai
US 20160068121 A1
Intelligent Determination and Usage of Energy in Energy Systems
Maini; Chetan Kumar et al.
US 20150186827 A1
Data-driven targeting of energy programs using time-series data
Kwac; Jungsuk et al.
US 20150094968 A1
Comfort-Driven Optimization of Electric Grid Utilization
Jia; Jimmy et al.
US 20140278019 A1
System And Method for Optimizing Availability of Vehicle Energy Conserving Modes
Be; Tuan Anh et al.
US 20140058673 A1
Computer-assisted method for processing cartographic data to determine energy-saving route between two geographic positions, by calculating weights for route segments based on energy consumption values provided for route segment portions
WOLF J
US 20130151179 A1
Automated Monitoring for Changes in Energy Consumption Patterns
Gray; Anthony R.
NPL
Intelligent Hybrid Vehicle Power Control—Part II: Online Intelligent Energy Management
Yi Lu Murphey


Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REHAM K ABOUZAHRA whose telephone number is (571)272-0419. The examiner can normally be reached M-F 7:00 AM to 5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Brian Epstein can be reached at (571)-270-5389. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.





/REHAM K ABOUZAHRA/Examiner, Art Unit 3625                                                                                                                                                                                                        

/BRIAN M EPSTEIN/Supervisory Patent Examiner, Art Unit 3625