Research On Cloud Platform Resource Optimization Strategy Based On Virtual Machine Migration

The issue of energy consumption is an important issue for cloud platforms.With the rapid development of cloud computing and mobile Internet and the ever-increasing scale of data centers,the costs of energy consumption is becoming more and more serious.Among them,virtualization technology is an important way to improve the energy consumption of cloud computing centers.By deploying virtual machines to achieve a balanced resource configuration of the cloud platform,able achieve the purpose of energy saving.This article is based on previous research,Two different migration strategies are proposed to achieve the goal of reducing energy consumption and improving energy efficiency of cloud platforms.The main work of this paper includes the following three aspects:(1)For virtual machine clusters with compute-intensive tasks,this paper proposes a virtual machine migration strategy based on an improved genetic algorithm to abstract virtual machine migrations into twodimensional binning problems.The algorithm is optimized by improving the selection cross-mutation process of genetic algorithm.This paper proposes a strategy verification on the cloud experiment platform of H3 C.Experiments show that the improved genetic algorithm can significantly improve the energy efficiency of computationally intensive task cloud computing clusters,saving energy consumption between 8.9% and 10.3%.(2)For virtual machine clusters with both network services and compute-intensive tasks,this paper proposes an improved simulated annealing algorithm as an energy efficiency upgrade strategy with a network service cloud computing environment,from reducing data traffic between virtual machines and reducing the cloud environment.Consider the energy consumption and abstract the virtual machine migration process into a three-dimensional Bin Packing Problem.This paper proposes a verification strategy on the cloud experiment platform of H3 C.Experiments show that the improved simulated annealing algorithm can quickly select the optimal migration strategy for virtual machine clusters with network services and computeintensive tasks,and reduce the virtual machine Data traffic and energy consumption in the cloud environment.