Parameter Configuration Model Optimizing Power-Computing Ratio
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data processing devices face challenges in achieving an optimal ratio of power consumption to computing power due to intricate correlations among various factors such as working frequency, power supply voltage, temperature, and environmental conditions, making precise control difficult and adaptive adjustments hard to implement.
Innovation Solution
A training method for a parameter configuration model using a deep learning algorithm and historical data to establish a relationship between operation parameters and power consumption, allowing for the determination of optimized operation parameters to achieve an optimized ratio of power consumption to computing power.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the computing power of the data processing device is increased, then the processing capability is improved, but the power consumption increases
Solution Approach 1:
The patent applies parameter changes by adjusting operation parameters (such as working frequency, power supply voltage, and temperature) to optimize the ratio of power consumption to computing power. The parameter configuration model dynamically modifies these parameters based on environmental conditions and operational requirements, achieving optimal performance without linearly increasing power consumption.
Solution Approach 2:
The patent implements dynamics by enabling adaptive adjustments of operation parameters based on real-time environmental conditions and operational states. The parameter configuration model continuously learns from historical data and adjusts parameters dynamically, allowing the system to maintain optimal power-computing ratio under varying conditions rather than using fixed parameters.
2Productivity
If multiple operation parameters are adjusted to optimize power consumption to computing power ratio, then the efficiency is improved, but the control complexity increases
Solution Approach 1:
The patent introduces an intermediary - the parameter configuration model - that mediates between environmental inputs and operation parameter adjustments. This model simplifies the control complexity by automatically processing the relationships between multiple parameters and environmental factors, eliminating the need for manual complex control while optimizing efficiency.
Solution Approach 2:
The patent implements feedback mechanisms where the parameter configuration model continuously monitors environmental conditions and operational outcomes, then adjusts operation parameters accordingly. This closed-loop feedback system simplifies control by automatically correcting deviations and optimizing parameters based on actual performance, reducing the burden on external control systems.
3Adaptability or versatility
If adaptive adjustments are implemented to respond to environmental changes, then the adaptability is improved, but the system complexity increases
Solution Approach 1:
The patent applies self-service by enabling the parameter configuration model to autonomously adapt to environmental changes without requiring complex external control systems. The model independently processes environmental inputs, determines optimal parameters, and implements adjustments automatically, improving adaptability while minimizing additional system complexity.
Solution Approach 2:
The patent implements preliminary action by pre-training the parameter configuration model on historical data and environmental patterns before deployment. This pre-learning phase enables the system to quickly adapt to new conditions without requiring complex real-time analysis, reducing the operational system complexity while maintaining high adaptability.
Data Source
AI summary
The present disclosure relates to a training method for a parameter configuration model, a parameter configuration method, and a parameter configuration device. The training method includes: obtaining a training sample set of a data processing device, wherein the training sample set includes operation parameters and benefit parameters in one-to-one correspondence with the operation parameters, the operation parameter includes at least one of a global operation parameter or a local operation parameter associated with position distribution, the benefit parameter is configured to reflect a ratio of power consumption to computing power of the data processing device; training the parameter configuration model based on the training sample set, wherein the operation parameter is configured as an input of the parameter configuration model, and the benefit parameter is configured as an output of the parameter configuration model; and in a case that a training accuracy of the parameter configuration model is greater than or equal to a first preset accuracy, ending the training and obtaining a trained parameter configuration model.