Research On Cache Resource Optimization In Mobile Edge Networks

With the application of live video,short video,video conference,VR / AR and holographic video gradually coming into people's daily life,network traffic also shows explosive growth.The traditional centralized network architecture has already been overburdened,so the emergence of mobile edge architecture is of great significance.Mobile edge computing is an extension of cloud computing technology,which sinks computing and cache resources to the edge of the network to provide nearby services for users and improve user experience.In mobile edge network architecture,it is necessary to deploy base stations equipped with MEC servers on a large scale to provide services for users,so how to reduce the energy consumption of base stations is of great significance.Base stations and other small devices deployed on the edge of the network have limited cache resources.How to efficiently utilize the cache resources of the edge nodes makes most of the network requests be solved at the edge of the network,which directly affects the overall delay and energy consumption of the network.In this paper,an evolutionary Algorithm based on group memory strategy,Pathfinder Algorithm(PFA),is proposed to optimize the cache resource allocation scheme of mobile edge network and reduce the overall energy consumption of the network.Considering the timeliness and time-variability of the cache contents,the static cache allocation scheme will lose its effect when the popularity of the content changes greatly.In this paper,we propose a dynamic cache allocation mechanism,which can ensure the best cache allocation scheme when the popularity of cache content changes,while reducing the energy consumption and delay of the network.The specific content is as follows:1)According to the static model of mobile edge network cache,an improved PFA algorithm is proposed to reduce the overall energy consumption of the network.The strategy of group memory is introduced into PFA algorithm,and each individual will record the optimal location information they have reached.In the operation of individual renewal,it is affected by both the leader's position and the individual's historical optimal position.Experimental results show that the improved PFA algorithm is better than other algorithms and the original algorithm in performance and convergence.In the model of cache resource allocation,the cache allocation scheme obtained by this algorithm has the lowest energy consumption.The new algorithm proposed in this paper has fast convergence speed,strong global search ability,and can quickly get the global optimal solution.2)According to the dynamic cache model of mobile edge network,a dynamic cache allocation mechanism is proposed,which can optimize the energy consumption and delay of mobile edge network simultaneously.In this mechanism,the historical playback information of popular video files is collected in real time by means of real-time prediction and dynamic allocation,and the Long Short-Term Memory(LSTM)model is used to predict the next or several time slots of video playback and convert it into popularity information.Based on the prediction results,the multi-objective evolutionary algorithm is used to generate the cache allocation scheme with the optimal time delay and energy consumption.