SustainDC: Benchmarking for Sustainable Data Center Control
This addresses the problem of reducing energy use and climate impact in data centers for AI and computing industries, but it is incremental as it focuses on benchmarking rather than a new control method.
The paper tackles the problem of unsustainable energy consumption in data centers by introducing SustainDC, a set of Python environments for benchmarking multi-agent reinforcement learning (MARL) algorithms, showing significant opportunities for improvement in data center operations using these algorithms.
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.