Processor Energy Control via Dual-Model ML and Fuzzy Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional industrial computer equipment lacks intelligent automated control methods for achieving energy efficiency, relying on manual operations to configure energy-saving modes, which is inefficient and leads to energy wastage.
Innovation Solution
An energy consumption control method that integrates long-term and short-term machine learning prediction models into a single prediction model, combined with a fuzzy feedback control mechanism, to continuously detect and adjust processor performance parameters for optimal energy usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If manual power limitation is applied to reduce energy consumption, then energy saving is achieved, but CPU performance degrades and task completion is delayed
Solution Approach 1:
The patent implements dynamic power adjustment by continuously monitoring CPU temperature and task queue status, then automatically adjusting power limits in real-time. This replaces static manual power limitation with a dynamic control system that adapts to changing operational conditions, preventing performance degradation while maintaining energy efficiency.
Solution Approach 2:
The patent employs feedback mechanisms by monitoring CPU temperature, task queue depth, and power consumption metrics, then using this information to adjust power limits. The system continuously loops through detection and adjustment phases, creating a closed-loop control system that optimizes both energy consumption and performance based on actual system state.
2Loss of energy
If unconditional power limitation below 6 watts is applied, then energy consumption is reduced, but CPU enters 100% full load state causing task accumulation and energy wastage
Solution Approach 1:
The patent changes the power limit parameter dynamically based on monitored conditions rather than applying a fixed threshold. When CPU temperature is within safe ranges and task queues are manageable, the system allows higher power consumption. When temperature rises or task accumulation occurs, it reduces power limits, thus adapting parameters to maintain reliability while optimizing energy use.
Solution Approach 2:
The patent performs preliminary detection of CPU temperature and task queue status before applying power limitations. By anticipating potential overload conditions through continuous monitoring, the system can adjust power limits proactively to prevent task accumulation and ensure reliable task completion before problems occur.
3Device complexity
If simple manual power limiting is applied, then implementation is simple, but optimization capability is insufficient and automation is lacking
Solution Approach 1:
The patent implements self-service automation where the system automatically monitors its own performance metrics, analyzes task queue status, and adjusts power limits without human intervention. The CPU and control system work together to autonomously optimize power consumption based on real-time conditions, eliminating the need for manual configuration while maintaining system simplicity through automated decision-making.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
The present invention relates to an energy consumption control method (200). The method (200) includes the steps of performing (201) following steps by a processor and a firmware; continuously detecting (202) and collecting a performance data of the processor, wherein the performance data includes a first performance parameter, a second performance parameter, and a third performance parameter; executing a dual-model machine learning model to predict the first performance parameter based on the performance data; and implementing (205) a fuzzy feedback control mechanism to adjust the first performance parameter based on the detected second and third performance parameters.