Research On Resource Scheduling Based On Multi-objective Optimization In Cloud Computing Environment

Cloud computing platform with virtualization technology for dynamic resource allocation is possible,through the re distribution of the application resources,the use of physical node resources has been opened,the way to reduce the physical node activation and achieve the purpose of energy saving.Currently,most scholars put forward the dynamic resource allocation scheme in cloud computing environment often only consider a single target or only considering the stability of the resource distribution under the current condition,without considering the excitation of the virtual machine to a new round of migration in the dynamic load in future applications,resulting in unnecessary waste of resources.According to varying workload information of applications,a new virtual machine placement method based on multi-objective optimization was proposed for node stability,considering both the overhead of virtual machine reallocation and the stability of new virtual machine placement,and a new mult-Objective optimization based Genetic Algorithm for Node Stability(MOGANS)Was designed to solve this problem.The simulation results show that compared with the genetic algorithm for energy saving and virtual machine redistribution overhead(GA-NN),stable longer virtual machine distribution obtained by MOGANS;Meanwhile,MOGANS Can well balance stability time and migration overhead.Simulation results show that when the number of nodes increases physical and virtual resources,MOGANS computing time of exponential growth,lack of performance for the MOGANS calculation,this paper proposes a multi-objective optimization based dynamic resource allocation method for virtual machine based on the distribution and stability of MOEA/D(MOGA-D),the simulation shows that in the same time scale calculation MOGA-D,faster convergence,and obtained similar results of multi-objective optimization.