ML-to-ML Orchestration for IHS Resource Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Information Handling Systems (IHS) face limited overall optimization due to independent operation of multiple machine learning (ML)-based optimization services, leading to conflicting resource adjustments and suboptimal performance.
Innovation Solution
A machine learning-to-machine learning (ML-to-ML) orchestration system that coordinates the operation of ML-based optimization services across various resources in an IHS, generating augmented hints to optimize the performance of target applications by combining ML-based hints and internally generated hints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple ML-based optimization services operate independently to optimize individual resources, then each resource can be optimized by its dedicated service, but overall system optimization is limited due to lack of coordination and conflicting resource adjustments
Solution Approach 1:
An ML-to-ML orchestration service is introduced as an intermediary between multiple ML-based optimization services. This orchestration service receives hints from individual optimization services, translates them into a common format, and coordinates their execution to ensure system-wide optimization without conflicts. The intermediary enables cooperation between previously independent services, resolving the contradiction between individual resource optimization and overall system optimization.
2Reliability
If ML-based optimization services function individually without coordination, then each service can operate autonomously with simple design, but resource adjustments conflict and performance is suboptimal
Solution Approach 1:
The patent merges multiple independent ML-based optimization services into a coordinated system through a central orchestration service. Individual optimization services continue to operate autonomously at their level, but the orchestration service combines their hints and coordinates their actions, merging their efforts into a unified optimization strategy. This combining approach maintains the simplicity and autonomy of individual services while achieving reliable, conflict-free system-wide optimization.
Data Source
AI summary
Embodiments of systems and methods for managing performance optimization of applications executed by an Information Handling System (IHS) are described. In an illustrative, non-limiting embodiment, an IHS may include computer-executable instructions to, for each of multiple resources used to execute a target application, receive one or more machine learning (ML)-based hints associated with each resource that have been generated by a ML-based optimization service, and generate one or more augmented hints for at least one of the resources using a ML-to-ML orchestration service. The ML-to-ML orchestration service then transmits the augmented hints to the ML-based optimization service that combines the augmented ML-based hints with the one or more internally generated hints to generate augmented profile recommendations that are, in turn, used to adjust one or more settings of the resource to optimize a performance of the target application executed by the resource.