Dell products l.p. (20240126605). GUIDED WORKLOAD PLACEMENT REINFORCEMENT LEARNING EXPERIENCE PRUNING USING RESTRICTED BOLTZMANN MACHINES simplified abstract
Contents
- 1 GUIDED WORKLOAD PLACEMENT REINFORCEMENT LEARNING EXPERIENCE PRUNING USING RESTRICTED BOLTZMANN MACHINES
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 GUIDED WORKLOAD PLACEMENT REINFORCEMENT LEARNING EXPERIENCE PRUNING USING RESTRICTED BOLTZMANN MACHINES - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
GUIDED WORKLOAD PLACEMENT REINFORCEMENT LEARNING EXPERIENCE PRUNING USING RESTRICTED BOLTZMANN MACHINES
Organization Name
Inventor(s)
Yanexis Pupo Toledo of Niteroi (BR)
[[:Category:Micael Ver�ssimo De Ara�jo of Rio de Janeiro (BR)|Micael Ver�ssimo De Ara�jo of Rio de Janeiro (BR)]][[Category:Micael Ver�ssimo De Ara�jo of Rio de Janeiro (BR)]]
Eduardo Vera Sousa of Niteroi (BR)
GUIDED WORKLOAD PLACEMENT REINFORCEMENT LEARNING EXPERIENCE PRUNING USING RESTRICTED BOLTZMANN MACHINES - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240126605 titled 'GUIDED WORKLOAD PLACEMENT REINFORCEMENT LEARNING EXPERIENCE PRUNING USING RESTRICTED BOLTZMANN MACHINES
Simplified Explanation
The patent application describes a method for optimizing the selection of microservices to execute a workload by using machine learning models to analyze experiences and probabilities associated with the microservices.
- The method involves defining experiences for a workload that are analyzed by a first machine-learning model.
- An association between the workload and microservices is established, with probabilities generated for using each microservice to execute the workload by a second machine-learning model.
- Experiences with low reward probabilities are identified and removed from analysis by the first model.
- The remaining experiences are analyzed to determine the optimal microservices for executing the workload.
Potential Applications
This technology could be applied in cloud computing environments to optimize resource allocation and improve workload performance.
Problems Solved
This technology addresses the challenge of efficiently selecting microservices to execute workloads based on their performance probabilities.
Benefits
The method can lead to improved efficiency, reduced costs, and enhanced performance in cloud computing environments.
Potential Commercial Applications
The technology could be valuable for cloud service providers, IT companies, and businesses with complex computing needs.
Possible Prior Art
Prior research may exist in the fields of machine learning, cloud computing optimization, and workload analysis.
Unanswered Questions
How does the method handle dynamic changes in workload requirements?
The patent application does not specify how the method adapts to fluctuations in workload demands.
What types of machine learning models are used in the method?
The specific machine learning algorithms and techniques employed in the method are not detailed in the abstract.
Original Abstract Submitted
one example method includes defining experiences for a workload that are to be analyzed at a first machine-learning (ml) model. the experiences define an association between the workload and microservices having computing resources that execute the workload. a probability of using each of the microservices of the experiences to execute the workload is generated at a second ml mode. a determination is made of which of the experiences have a probability that indicates that the experience will generate a low reward when analyzed by the first ml model. the experiences that generate the low reward are removed from the experiences to be analyzed at the first ml model. the experiences that have not been removed are analyzed at the first ml model to determine which experience includes microservices that should be used to execute the workload.