一种新的蚁群算法优化的虚拟机放置策略

ACA-VMP: A new ant colony algorithm optimized virtual machine placement strategy

摘要:

提出了一种新的蚁群算法优化的虚拟机放置策略ACA-VMP(Ant Colony Algorithm based virtual machine placement)。ACA-VMP以云数据中心的总体能量消耗降低、服务质量最佳及减少虚拟机迁移次数为目标函数；根据蚁群优化算法,ACA-VMP采用了全局最优解和局部最优解信息素强度更新规则；全局最优解经过多次迭代后,蚂蚁路径的多次寻优,保证这个虚拟机放置优化策略的完成。局部信息素强度参数更新可以补充蚂蚁其他局部最优路径的寻找,这样也可以使得ACA-VMP虚拟机放置优化算法更快的接近全局最优解。仿真结果表明： ACA-VMP策略使得云数据中心的各类性能指标都可以改善,该实验结果对于其他企业构造节能云数据中心有很好的参考价值。

Abstract:

A new ant Colony Algorithm optimized approach for virtual machine placement called ACA-VMP was proposed. ACA-VMP is depended on Cloudsim project which is a popular tool for cloud data center simulation. The objectives of ACA-VMP are to reduce energy consumption, minimize the number of VM migrations, and maintain the desired QoS. ACA-VMP used a vector based resource utilization capturing technique and multi-dimensional resource demands was described. The global pheromone trail evaporation rule is applied towards the end of iteration after all ants complete their migration plans. The local pheromone trail update rule is also applied on a tuple when an ant traverses the tuple while making its migration plan.The experimental results and performance analysis show our strategy leads to a further improvement compared with the old optimized algorithm strategies. ACA-VMP is valuable for other cloud providers to build a low energy consumption cloud data center.