Carbon Footprint Reduction for Sustainable Data Centers in Real-Time
Preprint
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.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels2023
- Concurrent Carbon Footprint Reduction (C2FR) Reinforcement Learning Approach for Sustainable Data Center Digital Twin2023
- Deep reinforcement learning towards real-world dynamic thermal management of data centersApplied Energy, 2022
- DRL-S: Toward safe real-world learning of dynamic thermal management in data centerExpert Systems with Applications, 2022
- Optimizing Energy Efficiency for Data Center via Parameterized Deep Reinforcement LearningIEEE Transactions on Services Computing, 2022
- Energy saving evaluation of an energy efficient data center using a model-free reinforcement learning approachApplied Energy, 2022
- Carbon-Aware Computing for DatacentersIEEE Transactions on Power Systems, 2022
- Battery energy storage control using a reinforcement learning approach with cyclic time-dependent Markov processInternational Journal of Electrical Power & Energy Systems, 2022
- Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC controlApplied Energy, 2021
- Deep Reinforcement Learning-Based Energy Storage Arbitrage With Accurate Lithium-Ion Battery Degradation ModelIEEE Transactions on Smart Grid, 2020