18061834. Machine Learning-Based Multitenant Server Application Dependency Mapping System simplified abstract (Bank of America Corporation)
Contents
- 1 Machine Learning-Based Multitenant Server Application Dependency Mapping System
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 Machine Learning-Based Multitenant Server Application Dependency Mapping System - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Key Features and Innovation
- 1.6 Potential Applications
- 1.7 Problems Solved
- 1.8 Benefits
- 1.9 Commercial Applications
- 1.10 Prior Art
- 1.11 Frequently Updated Research
- 1.12 Questions about Multitenant Server Application Dependency Mapping System
- 1.13 Original Abstract Submitted
Machine Learning-Based Multitenant Server Application Dependency Mapping System
Organization Name
Inventor(s)
Conor Mitchell Liam Nodzak of Charlotte NC (US)
Fernando Maisonett of Charlotte NC (US)
Shreyas Srinivas of Charlotte NC (US)
Brian Busch of Charlotte NC (US)
Kyle Scott Sorensen of Charlotte NC (US)
Machine Learning-Based Multitenant Server Application Dependency Mapping System - A simplified explanation of the abstract
This abstract first appeared for US patent application 18061834 titled 'Machine Learning-Based Multitenant Server Application Dependency Mapping System
Simplified Explanation
The multitenant server application dependency mapping system uses a machine learning model to predict server states and data flows in a network, based on historical telemetry data.
- Maps data flows through multitenant infrastructure components
- Machine learning model framework continually learns data flow patterns
- Predicts the state of any given server
- Treats network architecture as a whole
- Computes state probabilities based on historical data
- Forecasts future states of infrastructure components
Key Features and Innovation
- Utilizes machine learning model to predict server states
- Considers network architecture as a whole
- Learns data flow patterns continuously
- Computes state probabilities based on historical telemetry data
- Forecasts future states of infrastructure components
Potential Applications
The technology can be applied in various industries such as:
- Cloud computing
- Data centers
- Network management
Problems Solved
- Predicting server states accurately
- Mapping data flows through multitenant infrastructure
- Forecasting future states of infrastructure components
Benefits
- Improved network management
- Enhanced data flow mapping
- Accurate prediction of server states
Commercial Applications
Predictive Network Management System for Data Centers
This technology can be used to optimize data center operations by accurately predicting server states and data flows.
Prior Art
No prior art related to this technology is known at this time.
Frequently Updated Research
Currently, there is no frequently updated research relevant to this technology.
Questions about Multitenant Server Application Dependency Mapping System
Question 1
How does the machine learning model framework learn data flow patterns?
The machine learning model framework learns data flow patterns by analyzing historical telemetry data and computing state probabilities based on observed prior states.
Question 2
What are the potential commercial applications of this technology?
One potential commercial application is in predictive network management systems for data centers, where the technology can optimize operations by accurately predicting server states and data flows.
Original Abstract Submitted
A multitenant server application dependency mapping system maps data flows through multitenant infrastructure components through the use of a machine learning model framework that continually learns data flow patterns across the enterprise network and predicts the state of any given server. The multitenant server application dependency mapping system treats the network architecture as a whole and collects data accordingly, and uses that data to compute state probabilities conditioned upon both a point in time (and the observed prior states retrieved from the historical telemetry data. This provides a way to predict the likelihood of observing a tenant state being occupied, while also accounting for variations among the activity levels of various application. To forecast future states of all infrastructure components, the transition probabilities from tenant state to tenant state are then computed through time and used as inputs to the model to provide an accurate reconstruction of the data flows through all multitenant infrastructure components.