SustainDC: Benchmarking for Sustainable Data Center Control

TL;DR

SustainDC introduces a benchmarking platform with Python environments to evaluate multi-agent reinforcement learning algorithms for optimizing data center operations, aiming to enhance sustainability amid rising energy demands.

Contribution

This paper presents SustainDC, a novel benchmarking framework for MARL algorithms tailored to diverse data center control tasks and configurations.

Findings

MARL algorithms show varied performance across different data center scenarios

Significant potential exists for improving data center efficiency with MARL

SustainDC enables systematic evaluation of algorithms under real-world conditions

Abstract

Machine learning has driven an exponential increase in computational demand, leading to massive data centers that consume significant amounts of energy and contribute to climate change. This makes sustainable data center control a priority. In this paper, we introduce SustainDC, a set of Python environments for benchmarking multi-agent reinforcement learning (MARL) algorithms for data centers (DC). SustainDC supports custom DC configurations and tasks such as workload scheduling, cooling optimization, and auxiliary battery management, with multiple agents managing these operations while accounting for the effects of each other. We evaluate various MARL algorithms on SustainDC, showing their performance across diverse DC designs, locations, weather conditions, grid carbon intensity, and workload requirements. Our results highlight significant opportunities for improvement of data center operations using MARL algorithms. Given the increasing use of DC due to AI, SustainDC provides a crucial platform for the development and benchmarking of advanced algorithms essential for achieving sustainable computing and addressing other heterogeneous real-world challenges.