Optimizing Renewable Energy Utilization in Cloud Data Centers Through Dynamic Overbooking: An MDP-Based Approach

Abstract

The shift towards renewable energy sources for powering data centers is increasingly important in the era of cloud computing. However, integrating renewable energy sources into cloud data centers presents a challenge due to their variable and intermittent nature. The unpredictable workload demands in cloud data centers further complicate this problem. In response to this pressing challenge, we propose a novel approach in this paper: adapting the workload to match the renewable energy supply. Our solution involves dynamic overbooking of resources, providing energy flexibility to data center operators. We propose a framework that stochastically models both workload and energy source information, leveraging Markov Decision Processes (MDP) to determine the optimal overbooking degree based on the workload flexibility of data center clients. We validate the proposed algorithm in realistic settings through extensive simulations. Results demonstrate the superiority of our proposed method over existing approaches, achieving better matching with the renewable energy supply by 55.6%, 34.65%, and 40.7% for workload traces from Nectar Cloud, Google, and Wikipedia, respectively.