考虑低资源损耗的云平台虚拟机放置策略

Placement strategy with low resource consumption for cloud platform virtual machine

针对目前数据中心内部资源损耗优化不足的现状,提出一种基于正余弦扰动和反向学习的自适应粒子群算法的虚拟机放置策略。将连续整数编码方法、反向学习策略、正余弦扰动与自适应权重策略融入粒子群算法,连续整数编码能够解决传统编码的复杂性,有效提高算法的运行效率,反向学习使算法能够快速地接近最优解,加快算法的收敛速度,使用正余弦扰动避免算法陷入局部最优解,利用自适应权重策略调节局部搜索和全局搜索的关系。使用该算法解决数据中心中虚拟机放置问题,将仿真结果与其它算法进行比较,验证了该算法在降低资源损耗和保证服务质量方面优于其它算法。

Aiming at the current situation of insufficient optimization of internal resource consumption in the data center,a virtual machine placement strategy based on adaptive particle swarm optimization based on sin-cosine disturbance and reverse learning was proposed.Continuous integer coding methods,reverse learning strategics,sine and cosine perturbations and adaptive weighting strategies were integrated into particle swarm algorithm.Continuous integer coding solved the complexity of traditional coding and effectively improved the operating efficiency of the algorithm.Reverse learning enabled the algorithm to quickly approach the optimal solution,accelerated the convergence speed of the algorithm.Sine and cosine perturbation was used to avoid the algorithm from falling into the local optimal solution,and the adaptive weight strategy was used to adjust the relationship between the local search and the global search.This algorithm was used to solve the virtual machine placement problem in the data center,and the simulation rcsults were compared with other algorithms.It verifies that the proposed algorithm is superior to other algorithms in reducing resource consumption and ensuring service quality.