Electricity Price Prediction for Geographically Distributed Data Centers in Multi-Region Electricity Markets

Abstract

Geographically distributed data centens (GDCs) serving as infrastructures for cloud services, are growing in both number and scale. They usually consume enormous amount of electric power, which lead to high operational costs and this has been recognized as a main challenge in cloud computing. Energy cost can be reduced by directing the requests to the favor of data center with lower electricity price by incorporating spatially and temporally price diversity, especially in the multi-region electricity markets. If the electricity prices of data centers are predicted in advance, the cloud provider can reduce energy cost. An efficient electricity price prediction is needed for minimizing electricity bill of GDCs. This paper proposes electricity price prediction for GDCs in multi-region electricity markets. Experiment is conducted on real-life electricity price data sets with machine learning algorithms. By comparatively assessing the prediction accuracy of the models, the most accurate one is selected. Experiment results show that the prediction model can provide promising accuracy.