Study on energy-consumption regularities of cloud computing systems by a novel evaluation model

Jie Song, Tiantian Li, Zhi Wang, Zhiliang Zhu

Abstract: Due to the limited energy, environmental problem and fast growth of computer power consumption, energy-efficient computing has now become a critical and urgent issue. Therefore, an energy-consumption (energy consumed per task) evaluation model is necessary to be established. However, the existing models are almost qualitative rather than quantitative and with poor practicability because the EC measurement of cloud computing systems is rather difficult. In this paper, we propose an EC model and the corresponding calculation approach for cloud computing systems and prove its correctness and accuracy through a series of experiments. Based on this model, we also analyze the EC features of cloud computing systems, summarize some EC regularities and propose some EC optimization suggestions. With this model, one can calculate EC only by the values that are easily measured without special hardware, and can explore and evaluate new optimization methods.

External IDs:dblp:journals/computing/SongLWZ13