A Non-Intrusive, Traffic-Aware Prediction Framework for Power Consumption in Data Center Operations

Abstract

Modern cloud computing relies heavily on data centers, which usually host tens of thousands of servers. Predicting the power consumption accurately in data center operations is crucial for energy optimization. In this paper, we formulate the power consumption prediction at both the fine-grained and coarse-grained level. We carefully discuss the desired properties of an applicable prediction model and propose a non-intrusive, traffic-aware prediction framework for power consumption. We design a character-level encoding strategy for URIs and employ both convolutional and recurrent neural networks to develop a unified prediction model. We use real datasets to simulate requests and analyze the characteristics of the collected power consumption series. Extensive experiments demonstrate that our proposed framework can achieve superior prediction performance compared to other popular leading prediction methods.