18170739. DRIFT FORECASTING FOR ALTERNATIVE MODEL SELECTION simplified abstract (Dell Products L.P.)
Contents
DRIFT FORECASTING FOR ALTERNATIVE MODEL SELECTION
Organization Name
Inventor(s)
Vinicius Michel Gottin of Rio de Janeiro (BR)
[[:Category:Herberth Birck Fr�hlich of Florianópolis (BR)|Herberth Birck Fr�hlich of Florianópolis (BR)]][[Category:Herberth Birck Fr�hlich of Florianópolis (BR)]]
Julia Drummond Noce of Rio de Janeiro (BR)
Ítalo Gomes Santana of Rio de Janeiro (BR)
DRIFT FORECASTING FOR ALTERNATIVE MODEL SELECTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18170739 titled 'DRIFT FORECASTING FOR ALTERNATIVE MODEL SELECTION
Simplified Explanation: The patent application describes a method where a central node evaluates the performance of a reference model deployed at an edge node. If the evaluation exceeds a threshold, a counter is incremented. When the counter reaches a specified limit, an interpolation process is performed to identify a new model with better expected performance, which is then deployed in shadow mode at the edge node.
- Central node evaluates performance of reference model at edge node
- Increment counter if evaluation exceeds threshold
- Perform interpolation process to identify new model with better performance
- Deploy new model in shadow mode at edge node
Key Features and Innovation: - Evaluation of performance at edge node - Incrementing counter based on evaluation exceeding threshold - Interpolation process to identify new model with better performance - Deployment of new model in shadow mode
Potential Applications: - Edge computing optimization - Performance enhancement in IoT devices - Real-time model updating in distributed systems
Problems Solved: - Efficient evaluation of model performance at edge nodes - Automatic identification of better-performing models - Seamless deployment of new models in shadow mode
Benefits: - Improved performance in edge computing environments - Enhanced efficiency in model evaluation - Automated model updating for optimal performance
Commercial Applications: Optimizing edge computing processes for industries such as IoT, telecommunications, and autonomous vehicles can lead to improved performance and cost savings.
Questions about the Technology: 1. How does the interpolation process work in identifying a new model? 2. What are the potential challenges in deploying the new model in shadow mode?
Frequently Updated Research: Stay updated on advancements in edge computing, machine learning, and IoT technologies to enhance the performance of distributed systems.
Original Abstract Submitted
One example method includes obtaining, by a central node, an evaluation of a performance of a reference model deployed at an edge node, determining if the evaluation exceeds a threshold associated with the reference model, and incrementing a counter when the evaluation exceeds the threshold, when a counter value equals or exceeds a specified limit, performing an interpolation process to identify a new model having better expected performance than performance of the reference model, and deploying the new model in a shadow mode at the edge node.