Research On Scheduling Algorithm In Trusted Cloud Computing

In recent years,with the continuous improvement of people's ability of data processing and computing power,cloud computing has a rapid development,and gradually applied to the academic field,for example,business and other fields.When cloud computing users use network services it is more convenient and efficient,because it has massive resources and it is paid on demand.The core of the cloud task scheduling is to allocate reasonable resources to the task according to the different needs of the user.Among them,the cloud computing scheduling need to focus on the question that how to provide the services which should meet the cloud user service quality requirements(Qos)available to users.Cloud computing has some features: complexity,openness,dynamic changes in virtual resources and diversity of trust relationship.Because of these features of cloud computing,users are faced with some security issues when using cloud computing services.In this severe cloud security situation,cloud task scheduling is as a key research content.Its security and reliability has become an important reason to hinder the research and development of cloud computing.Therefore,this paper focuses on the mission scheduling problem on the trusted cloud.In order to provide users with a safe and reliable service environment,in this paper,reliability parameters and trust are combined to design a trust management model.Reliability is one of the Qos attribute parameters,through which users can ensure that resources obtained when using the cloud services is more reliable and more secure,it also meets the user's service needs.The trust model can enhance the security of cloud service provider's virtual resource node,it makes cloud users more comfortable and improves the credibility of cloud services when using cloud services.Particle Swarm Optimization(PSO)is a heuristic intelligent algorithm.It is a process to imitate the birds and fish in the animals,and the algorithm is simple and fast to converge to the optimal solution,but in the latter part of the optimization process it is very easy to fall into the local optimal solution.In this paper,the probabilistic sampling of the simulated annealing algorithm(SA)is added to the PSO algorithm to improve its easy to fall into the local optimum and then this paper presents the PSO-SA algorithm.SA algorithm is simulated the process of the physical annealing,using the SA algorithm Metropolis criterion for the PSO algorithm after each iteration of the individual optimal solution to do the sampling operation,it can firstly avoid the local optimal solution and ensure the diversity of the population.On the basis of the trust model,do the task scheduling of the cloud,it can effectively improve the management of tasks in the cloud environment and the rational allocation of resources.Finally,the effectiveness of the algorithm is verified through the use of CloudSim cloud simulation software,the experimental results show that the PSO-SA algorithm can better meet the user's requirement about the reliability of cloud service quality.By comparing the experimental results of the two algorithms before and after optimization,it is shown that the performance of the algorithm is improved by using the simulated annealing operator to optimize the PSO algorithm.