Stochastic Energy Efficient Cloud Service Provisioning Deploying Renewable Energy Sources

Abstract

This paper focuses on the design of cloud service provisioning schemes over converged optical network and computing infrastructures. A major issue linked with the operation of these infrastructures is their sustainability in terms of energy consumption and CO₂ emissions. Given that most of the power consumption of the converged infrastructures is attributed to the operation of computing resources, the concept of powering-up computing resources with renewable energy sources is becoming a promising solution. However, the time variability and uncertainty of cloud services as well as the stochastic nature of renewable energy sources makes the evaluation and exploitation of such systems challenging. To address this challenge, we propose a novel service provisioning scheme based on stochastic linear programming (SLP). To cope with the increasing computational complexity inherent in SLP formulations, dimensionality reduction techniques, such as the sample average approximation and Lagrangian Relaxation are adopted. Based on measurements from the National Solar Radiation Data Base, traffic statistics from the Internet² measurement archive and experimentations with real network configurations, it is proven that the proposed scheme is stable and achieves fast convergence to the optimal solution, while at the same time reduces the overall CO₂ emissions by up to 60% for different levels of demand requests. The performance of the proposed provisioning scheme is compared to traditional approaches.