云计算数据中心可扩展服务器节能优化研究

摘要：云计算数据中心越来越庞大，硬件规模也日益增大，而且还会有大量的计算资源、存储资源会出现在云端，促使出现了一大批十万级、百万级、乃至千万级服务器的数据中心，且服务器还可以增量扩展与增量部署，高能耗问题已经日益凸显，严重制约到云计算数据中心的可持续性发展。本文提出了一种新型的云计算数据中心可扩展服务器节能优化策略——效能优化策略，能够基于全局角度来降低能源消耗，优化服务器选择过程，并且还可促使不同服务器之间实现负载均衡。仿真实验结果表明：基于能耗大小来看，本文提出的效能优化策略要比DVFS策略、无迁移策略所对应的能耗分别节约15.23%、24.33%；基于迁移数来看，本文提出的效能优化策略要比DVFS策略所对应的迁移次数减少2425次，总之，本文提出的效能优化策略总体而言要明显比DVFS策略、无迁移策略更优越。

Cloud computing data center scalable server energy optimization

Abstract: Cloud computing data centers are getting bigger and bigger, the hardware scale is increasing, and there will be a large amount of computing resources and storage resources will appear in the cloud, prompting a large number of 100,000, millions, or even millions. The data center of the server is also available, and the server can also be incrementally expanded and incrementally deployed. The problem of high energy consumption has become increasingly prominent, which seriously restricts the sustainability of the cloud computing data center. This paper proposes a new cloud computing data center scalable server energy-saving optimization strategy-performance optimization strategy, which can reduce energy consumption based on the global perspective, optimize the server selection process, and also promote load balancing between different servers. The simulation results show that the performance optimization strategy proposed in this paper saves 15.23% and 24.33% respectively compared with the DVFS strategy and the non-migration strategy. Based on the migration number, the performance optimization proposed in this paper is based on the migration number. The strategy reduces the number of migrations corresponding to the DVFS strategy by 2,425 times. In summary, the performance optimization strategy proposed in this paper is generally superior to the DVFS strategy and the non-migration strategy.