基于混合粒子群算法的虚拟数据中心能耗优化

Energy Consumption Optimization in Virtualized Data Center Based on Hybrid Particle Swarm Algorithm

针对当前数据中心节能整合研究中仅考虑服务器能耗的现状,提出一种同时考虑服务器和网络设备能耗的方法。该方法通过感知数据中心的网络拓扑,使运行的服务器和网络设备最少,以此最小化能耗。对问题进行新的形式化建模,并设计一种混合的粒子群优化算法HPSO-NA来实现虚拟机整合。实验结果表明,该方法能有效降低整体能耗。

Since current researches on energy efficient consolation in data center only consider part of energy consumed by servers,this paper proposes a novel method considering both servers and network devices.The proposal achieves energy minimization by minimizing the active servers and network devices through analyzing the net topology.Moreover,the problem is modeled and a hybrid particle swarm algorithm called HPSO-NA is designed to implement virtual machine consolidation.Experimental results show that the proposed method can effectively reduce the energy consumption.