Carbon Footprint Reduction for Sustainable Data Centers in Real-Time

Unknown Date

AI Summary

To address the challenge of real-time low-carbon operation in data centers, this paper proposes a multi-agent reinforcement learning (MARL) framework that jointly optimizes cooling systems, IT load scheduling, and UPS battery energy storage—dynamically responding to weather variations and grid carbon intensity fluctuations. We innovatively formulate a thermal-electric coupling model and integrate a carbon-intensity-aware control mechanism to enable online, simultaneous optimization of carbon emissions, energy consumption, and electricity cost. Evaluated across multiple geographic regions under realistic dynamic grid and meteorological conditions, our approach achieves average annual reductions of 14.5% in carbon emissions, 14.4% in energy consumption, and 13.7% in electricity cost compared to the ASHRAE-standard controller. This work represents the first demonstration of full-stack, real-time, coordinated optimization in production-scale data centers—overcoming the limitations of conventional static, rule-based policies.

Technology Category

• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

As machine learning workloads significantly increase energy consumption, sustainable data centers with low carbon emissions are becoming a top priority for governments and corporations worldwide. This requires a paradigm shift in optimizing power consumption in cooling and IT loads, shifting flexible loads based on the availability of renewable energy in the power grid, and leveraging battery storage from the uninterrupted power supply in data centers, using collaborative agents. The complex association between these optimization strategies and their dependencies on variable external factors like weather and the power grid carbon intensity makes this a hard problem. Currently, a real-time controller to optimize all these goals simultaneously in a dynamic real-world setting is lacking. We propose a Data Center Carbon Footprint Reduction (DC-CFR) multi-agent Reinforcement Learning (MARL) framework that optimizes data centers for the multiple objectives of carbon footprint reduction, energy consumption, and energy cost. The results show that the DC-CFR MARL agents effectively resolved the complex interdependencies in optimizing cooling, load shifting, and energy storage in real-time for various locations under real-world dynamic weather and grid carbon intensity conditions. DC-CFR significantly outperformed the industry standard ASHRAE controller with a considerable reduction in carbon emissions (14.5%), energy usage (14.4%), and energy cost (13.7%) when evaluated over one year across multiple geographical regions.

Problem

• Optimizing data center energy use and carbon emissions in real-time
• Balancing cooling, load shifting, and energy storage dynamically
• Addressing variable factors like weather and grid carbon intensity

Innovation

• Multi-agent Reinforcement Learning optimizes data centers
• Real-time control for cooling, load shifting, storage
• Dynamic adaptation to weather and grid conditions