Thermal Correlation Indexes for Cooling Infrastructure Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing methods for managing cooling infrastructure in data centers are inefficient and energy-intensive, requiring manual adjustment of cooling devices which is time-consuming and disruptive, and lack a systematic approach to optimize cooling impact at specific locations.
Innovation Solution
The implementation of machine-learning based techniques to determine the relationship between cooling infrastructure adjustable settings and their impact using thermal correlation indexes (TCIs), allowing for non-intrusive modeling of temperature sensor data and identification of regions of influence for each cooling device, enabling efficient management of cooling infrastructure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual adjustment of cooling devices is used, then cooling management can be performed, but it is time-consuming and disruptive
Solution Approach 1:
The system enables self-service automation where the cooling infrastructure manages itself through machine-learning models that automatically determine relationships between cooling device settings and temperature impacts, eliminating the need for manual adjustment and disruption to electronic devices
Solution Approach 2:
The patent replaces manual mechanical adjustment operations with an automated computational system that uses machine-learning techniques and thermal correlation indexes to determine optimal cooling settings, substituting human-operated mechanical systems with automated information-processing systems
2Loss of energy
If existing cooling management methods are used, then cooling can be provided, but energy consumption is high and efficiency is low
Solution Approach 1:
The system implements feedback mechanisms by continuously analyzing temperature sensor data and using machine-learning models to determine thermal correlation indexes, which provide feedback on the actual impact of cooling device settings, enabling optimized energy consumption and improved cooling efficiency
Solution Approach 2:
The patent changes the operational parameters of the cooling system by using machine-learning-based thermal correlation indexes to dynamically optimize cooling device settings based on actual temperature impacts, rather than using fixed or manual settings, thereby reducing energy consumption and improving efficiency
3Adaptability or versatility
If cooling devices are adjusted independently, then individual device control is achieved, but systematic optimization of cooling impact is lacking
Solution Approach 1:
The patent merges individual cooling device control with systematic optimization by combining machine-learning models that analyze the collective impact of multiple cooling devices on temperature sensors, creating a unified system that maintains device flexibility while achieving precision through coordinated control based on thermal correlation indexes
Data Source
AI summary
A model is provided that produces predicted sensor data as a function of at least one input feature that includes an adjustable setting of a cooling infrastructure. The model is able to model a non-linear relationship between the predicted sensor data and the adjustable setting.