Research On Application Of Cuckoo Search Based On Skyline Limited Space In Cloud Service Composition

With the rapid development of cloud computing technology in recent years,many enterprises publish their products as services on the Internet for users to choose.However,the needs of users are becoming more and more complex,and the functions of a single cloud service cannot meet the requirements of users,which require the composition of multiple cloud services to provide users in the form of a composition of cloud services.At the same time,because of the deployment of a large number of cloud services with the same functions but different quality of service(QoS)on the Internet,how to select services to meet the needs of users in a large number of cloud services for composition is a NP difficult problem.So it's important to choose a method to find a composition of cloud services that meet user requirements.Firstly,according to the QoS criteria in cloud services,this paper establishes a QoS model for cloud services by analyzing the impact of each criterion on cloud services.At the same time,the logical relationship between each cloud service in the cloud service portfolio is discussed,and a cloud service portfolio model is established.The calculation method of the QoS criterion in the cloud service portfolio with different logical relationships and the normalization method of the value of the QoS criterion are given to compare the performance of the cloud service portfolio.Secondly,by classifying and analyzing the methods currently used to solve the cloud service composition problem,the cloud service composition problem with QoS constraints is solved using the cuckoo search.In order to overcome the shortcomings of the current cuckoo search in solving the problem of cloud service composition,this paper improves the original cuckoo search,adds Skyline filtering and roulette method to limit the search space of the cuckoo search,and puts forward a Skyline limited range cuckoo search to help users select a high performance cloud service composition based on the QoS criterion.Finally,the cloud service composition problem is solved by the cuckoo search based on Skyline limited scope in the simulation experiment.The experiment results show that compared with the genetic algorithm and the original cuckoo search method,the proposed approach leads to better convergence and higher performance.