Carbon Footprint Reduction for Sustainable Data Centers in Real-Time
Soumyendu Sarkar, Avisek Naug, Ricardo Luna, Antonio Guillen, Vineet Gundecha, Sahand Ghorbanpour, Sajad Mousavi, Dejan Markovikj, Ashwin Ramesh Babu

TL;DR
This paper introduces a multi-agent reinforcement learning framework for real-time optimization of data center operations, significantly reducing carbon footprint, energy consumption, and costs amid dynamic environmental and grid conditions.
Contribution
The paper presents a novel MARL-based control system that effectively manages cooling, load shifting, and energy storage for sustainable data centers in real-time.
Findings
Achieved 14.5% reduction in carbon emissions.
Reduced energy usage by 14.4%.
Lowered energy costs by 13.7%.
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)…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGreen IT and Sustainability · Advanced Data Storage Technologies · Cloud Computing and Resource Management
