基于改进蚁狮算法的虚拟机放置方法

Virtual machine placement method based on improved antlion algorithm

虚拟机放置是虚拟机整合过程中的关键步骤,虚拟机放置方法的好坏往往会影响云数据中心的资源使用效率和性能,这类问题可以通过建立多目标优化模型来进行求解。当前云数据中心存在能耗高、资源利用率较低以及资源碎片化的情况。针对上述情况,提出了一种基于MALO算法的虚拟机放置策略。通过建立多目标多约束的虚拟机放置模型,对能耗、资源利用率和资源碎片化3个方面进行优化。并且在蚁狮算法的基础上,通过改进解空间的边界变化策略和蚂蚁随机游走的位置选择策略,最后对蚂蚁位置越界进行修正,使得种群的多样性能得到更好保证,这样能更好地跳出局部最优解。基于虚拟机放置平台对MALO算法和另外4种虚拟机放置算法进行仿真实验,实验结果表明,相比于蚁狮算法、BRC算法、MBFD算法和FFD算法,MALO算法在降低能耗、提高资源利用率以及减少资源碎片化方面有一定的提升效果。

Virtual machine placement is a key step in the process of virtual machine consolidation.The quality of the virtual machine placement method usually affects the resource utilization efficiency and performance of the cloud data center.Such problems can be solved by establishing a multi-objective optimization model.Currently,cloud data centers have high energy consumption,low resource utilization,and resource fragmentation.In view of the above situation,a virtual machine placement strategy based on MALO algorithm is proposed.By establishing a multi-objective and multi-constrained virtual machine placement model,the energy consumption,resource utilization,and resource fragmentation are optimized.And on the basis of the Antlion algorithm,by improving the boundary change strategy of the solution space and the location selection strategy of ants random walk,finally the position of the ants is corrected beyond the boundary,so that the diversity of the population can be better guaranteed,which can better Jump out of the local optimal solution.Based on the virtual machine placement platform,the simulation experiments of MALO algorithm and four other virtual machine placement algorithms are carried out.The experimental results show that compared to the Antlion algorithm,BRC algorithm,MBFD algorithm and FFD algorithm,the MALO algorithm has a certain improvement effect in reducing energy consumption,improving resource utilization and reducing resource fragmentation.