Providing RS Participation for Geo-Distributed Data Centers Using Deep Learning-Based Power Prediction

Abstract

Nowadays, geo-distributed Data Centers (DCs) are very common, because of providing more energy efficiency, higher system availability as well as flexibility. In a geo-distributed cloud, each local DC responds to the specific portion of the incoming load which distributed based on different Geographically Load Balancing (GLB) policies.

As a large yet flexible power consumer, the local DC has a great impact on the local power grid. From this point of view, a local DC is a good candidate to participate in the emerging power market such as Regulation Service (RS) opportunity, that brings monetary benefits both for the DC as well as the grid. However, a fruitful collaboration requires the DC to have the capability of forecasting its future power consumption. While, given the different GLB policies, the amount of delivered load toward each local DC is a function of the whole system’s conditions, rather than the local situation. Thereby, the problem of RS participation for local DCs in a geo-distributed cloud is challenging. Motivated by this fact, this paper benefits from deep learning to predict the local DCs’ power consumption. We consider two main GLB policies, including Power-aware as well as Cost-aware, to acquire training data and construct a prediction model accordingly. Afterward, we leverage the prediction results to provide the opportunity of RS participation for geo-distributed DCs. Results show that the proposed approach reduces the energy cost by 22% on average in compared with well-known GLB policies.