Research On Energy-saving Virtual Machine Placement Method For User Experience In Cloud Computing Environment

With the emergence and development of cloud computing models,in order to meet the requirements of large-scale distributed computing,the number and scale of cloud data centers are rapidly expanding,and huge data centers need to consume a lot of energy.Green computing focuses on the study of data center energy consumption,aiming to minimize the cost and reduce the negative impact on the environment as much as possible.Virtual machine placement is an important method for optimizing dynamic energy consumption to achieve energy saving,and it is also one of the hot issues studied by scholars in the field of green cloud computing.Therefore,how to reasonably place virtual machines to optimize energy consumption has become an urgent problem to be solved.In recent years,various placement strategies and methods have been different,but the following two problems currently exist:(1)The green cloud computing virtual machine placement algorithm should not only consider minimizing energy consumption,but also consider multiple indicators that affect user experience such as system availability,SLA violation ratio,task completion time,cost,etc.,and finally seek among multiple indicators A balance to optimize energy consumption.(2)In view of the different advantages and disadvantages of various algorithms for virtual machine placement in the current green cloud computing environment,through analysis and research on the characteristics of various algorithms,the most suitable virtual machine placement method for this research objective is proposed,and the simulation verification of the proposed algorithm is yet to be studied.In response to the above two issues,this article will meet the user experience on the basis of minimizing energy consumption as the optimization goal,and propose a new virtual machine placement method.The main research contents are as follows:Briefly describe the related research on green cloud computing and virtual machine placement methods,introduce in detail the advantages and disadvantages of several current virtual machine placement methods,and optimize the algorithms for the current energy optimization problems.Analyze the process of virtual machine placement and establish a system model to describe the functions of each module of the system model and the interaction between the modules.Clarify the constraints that this research needs to meet and the goals to be achieved,mathematically model energy consumption and user experience,and propose an objective function consistent with the expectations of this article.Based on the research of current virtual machine placement methods,optimize and improve the pheromone update mechanism,heuristic factor and roulette probability selection mechanism of the basic ant colony algorithm,and a UE-ACO algorithm is proposed to find a balance between satisfying user experience and optimizing energy consumption,thereby improving User satisfaction and effectively reduce the energy consumption of cloud data centers.Finally,the algorithm proposed in this paper is verified and compared with other classic algorithms on the simulation platform.Experimental results show that compared with basic ant colony algorithm B-ACO,Min Min algorithm and polling algorithm RR,UE-ACO algorithm can save up to 20%,24% and 30% of energy while satisfying different user experiences.It can also ensure that the improved algorithm jumps out of the local optimum and enters the global optimum,avoiding the premature maturity of the algorithm.