Research On Mobile Service Migration Model Based On Improved Genetic Algorithm

With the development of mobile communication technology and the popularization of mobile devices,more and more mobile service applications such as augmented reality and face recognition have been developed.Although mobile devices have the advantage of being able to provide mobile services to users anytime and anywhere,mobile devices are mostly small in size and limited in resources,and it is difficult to withstand complex calculations with large amounts of data,so it is not guaranteed to provide users with high-quality mobile services.The emergence of mobile edge computing technology provides a solution to the problem of resource constraints on mobile devices.By migrating some of the computing tasks performed on the mobile device to the edge server for execution,it can not only relieve the computing pressure of the mobile server,but also ensure that mobile users get a high-quality service experience.In this paper,based on the analysis and research of mobile services and mobile edge computing technologies,the mobile service migration problem in the mobile edge computing environment is studied in depth.In this paper,the mobile device is constructed as a mobile server,and the mobile service deployed on the mobile server is divided into multiple sub-services with dependencies.First,the mobile service migration problem is transformed into a nonlinear 0-1 programming problem.Considering the monitoring cost,service execution cost and data transmission cost of mobile servers,an edge server selection algorithm based on energy consumption threshold is designed,and a service migration model with energy consumption and delay as optimization goals is constructed.Then,in order to solve the service migration model,this paper improves the traditional genetic algorithm,that is,the traditional genetic algorithm is integrated with a reverse learning mechanism to improve the execution efficiency and convergence speed of the algorithm;the Levy Flight mechanism is integrated to expand the diversity of the population and improve the convergence accuracy of the target value.After that,the improved genetic algorithm is used to solve the service migration model.Experimental results show that the edge server selection strategy and mobile service migration model proposed in this paper have obvious advantages in terms of algorithm convergence speed,convergence accuracy,energy consumption,and accuracy.Finally,an application case is given to verify the effectiveness of the service migration model studied in this paper.