Data Center Cooling Control via Server Load Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data centers face challenges in managing cooling device energy consumption, leading to potential overheating due to insufficient power supply, as existing methods lack a systematic approach to prioritize the reduction of cooling capacity across compartments with varying server loads.
Innovation Solution
A power grid-friendly control method and system that divides the equipment room into subspaces, prioritizes cooling device shutdown based on server power consumption, and adjusts according to real-time power supply conditions to minimize service impact during energy shortages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If cooling devices are turned off uniformly across all compartments to reduce energy consumption, then power consumption is reduced, but compartments with high server loads risk overheating
Solution Approach 1:
The equipment room is divided into multiple compartments, each with independent cooling control. This allows differential cooling strategies where high-load compartments maintain full cooling while low-load compartments reduce or shut off cooling, resolving the contradiction between energy reduction and reliable cooling supply.
Solution Approach 2:
Different compartments receive different cooling levels based on their specific server load characteristics. High-load compartments receive full cooling capacity while low-load compartments receive reduced cooling, ensuring each compartment's cooling needs are met locally rather than applying a uniform reduction across all areas.
2Use of energy by moving object
If cooling capacity is reduced to match insufficient power supply, then energy consumption aligns with available power, but server cooling reliability deteriorates
Solution Approach 1:
The system continuously monitors server power consumption in real-time and dynamically adjusts cooling device operation accordingly. When power supply is insufficient, the feedback mechanism identifies which compartments can safely reduce cooling based on current server loads, maintaining reliability while matching energy consumption to available power.
Solution Approach 2:
The cooling system transitions from static uniform operation to dynamic adaptive operation. Cooling capacity is continuously adjusted based on real-time server load conditions and power availability, allowing the system to optimize energy consumption while maintaining cooling reliability when needed.
3Loss of energy
If operators manually adjust cooling devices during power shortages, then energy consumption can be controlled, but operational complexity and decision-making difficulty increase
Solution Approach 1:
The system automatically monitors server loads and controls cooling devices without requiring operator intervention. The control system independently makes decisions about which cooling devices to adjust based on real-time power consumption data, eliminating the operational complexity and decision-making burden on operators.
Solution Approach 2:
Manual operator control is replaced with automated electronic control systems that continuously monitor and adjust cooling based on server load. This substitution of manual mechanical adjustment with automated electronic control simplifies operation while achieving precise energy management.
Data Source
AI summary
Disclosed are a power grid-friendly control method and system for a data center cooling system. The method includes: dividing an equipment room into a plurality of pieces of subspace in advance, with a plurality of servers and a cooling device comprised in each piece of subspace; obtaining total power consumption of the servers in each piece of subspace; performing priority sorting on the total power consumption of the servers in each piece of subspace; obtaining a real-time power supply energy consumption value of a power grid; determining, whether an energy supply is sufficient; and if the energy supply is sufficient, skipping turning off the cooling device in the subspace; or if the energy supply is not sufficient, turning off a cooling device, till it is determined that the energy supply is sufficient, thus minimizing impact of turning off the cooling system on stability.