学術雑誌論文

Multi-level Power Consumption and Computation Models and　Energy-aware Server Selection Algorithms in a Server Cluster

jpn

21879923

法政大学大学院理工学・工学研究科

58

2017-03-31

Version of Record

ヘッダー部分に誤記 ; (誤) 法政大学大学院理工学・工学研究科紀要 (正) 法政大学大学院紀要. 理工学・工学研究科編

It is critical to reduce the electric energy consumed in server cluster in order to realize eco society. In our previous studies, a server is selected to perform a process by estimating the termination time of every current process and the electric energy consumption of servers. However, it is not easy and takes time to collect the state of each process and to estimate the termination time of each process. In this paper, we first propose a power consumption model, MLPCM (multi-level power consumption with multiple CPUs) model which shows how much electric power a server consumes to perform processes. We also propose a computation model MLCM (multi-level computation with multiple CPUs) model which shows the expected execution time of a process performed on a server. We newly propose SLEA (simple locally energy-aware) algorithm to select a server for each process in a cluster where only the number of processes on each server is used. In the evaluation, we show the electric energy consumption and active time of the servers and average execution time of processes can be reduced in the SLEA algorithm. Key Words : MLPCM(Multi-Level Power Consumption with Multiple CPUs) model, SLEA(Simple Locally Energy-aware) server selection algorithm

Article

AA12677220