Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters
This work addresses the problem of environmental sustainability for cloud computing providers and data center operators, offering an incremental solution to an existing challenge.
The authors tackled the problem of reducing the environmental impact of cloud computing by optimizing workload distribution and cooling in data center clusters, achieving improved sustainability metrics. The system optimizes multiple data centers synchronously, with specific numbers on carbon emissions and sustainability metrics.
Reducing the environmental impact of cloud computing requires efficient workload distribution across geographically dispersed Data Center Clusters (DCCs) and simultaneously optimizing liquid and air (HVAC) cooling with time shift of workloads within individual data centers (DC). This paper introduces Green-DCC, which proposes a Reinforcement Learning (RL) based hierarchical controller to optimize both workload and liquid cooling dynamically in a DCC. By incorporating factors such as weather, carbon intensity, and resource availability, Green-DCC addresses realistic constraints and interdependencies. We demonstrate how the system optimizes multiple data centers synchronously, enabling the scope of digital twins, and compare the performance of various RL approaches based on carbon emissions and sustainability metrics while also offering a framework and benchmark simulation for broader ML research in sustainability.