Research On Video Caching Strategy In Mobile Edge Computing Networks

With the rapid development of multimedia services in wireless mobile networks,the video data traffic has increased exponentially.Traditional video traffic service based on cloud computing causes a large amount of traffic load and longer access delay,which severely reduces the quality of service(QoS)of users.Mobile Edge Computing(MEC),as a key technology in the emerging 5G network,provides storage and computing resources at the edge of the network to support low-latency and computationally intensive mobile applications.At the same time,the mobile edge server not only provides computing resources,but also provides storage resources,which can be taken as cache nodes to store popular content requested by users.The cache on the mobile edge server is called the mobile edge cache.As a use case of MEC,it can directly serve user requests,thereby greatly reducing the traffic load and shortening the access delay.At present,distributed caching is widely used in the cache deployment of base stations.However,the cache capacity of a single base station is usually particularly limited,which will reduce the cache performance of the wireless mobile network.For this reason,this paper proposes a collaborative caching scheme in the heterogeneous MEC network to achieve efficient management of cached content.In addition,many existing researches on video caching have not thoroughly explored the characteristics of Adaptive Bitrate(ABR),and mainly use storage and transmission methods without any processing operations.Therefore,it is very important to design an efficient caching strategy that efficiently utilizes the provided storage and processing resources.Then,this paper proposes a joint caching and processing architecture,which uses the caching and processing resources on the MEC server to meet the needs of users for videos with different bit rates.Finally,the main contributions of this paper are summarized in the following two aspects:(1)Research on the management strategy of collaborative video caching in mobile edge computing network.This paper first proposes a collaborative caching model,in which both the macro base station and the small base station deploy an MEC server to make the storage resources closer to users.At the same time,this paper presents a content cache optimization problem to minimize the total delay cost of all users requesting video content in the MEC network.In order to facilitate the solution of the problem,this paper transforms the above problem into the problem of maximizing the monotone submodular set function under the constraints of matroids.Then,this paper proposes a caching management strategy,which includes a greedy cache placement strategy and a greedy cache update strategy.The simulation results show that the caching strategy effectively improves the cache hit rate,and significantly reduces the average delay and backhaul traffic load.(2)Research on adaptive bitrate video caching strategy in mobile edge computing network.This paper first proposes a joint collaborative caching and processing framework that supports ABR video streaming in MEC network.In addition,this paper also describes an Integer Linear Program(ILP),which minimizes the delay cost of accessing the video while satisfying the caching and processing capacity constraints of each MEC server.Due to the complexity of the considered ILP problem and the lack of information before the video request arrives,this paper decomposes the original problem into cache placement problem and request scheduling problem.Then,this paper proposes the following two schemes to solve the problem.When the content popularity is unknown,this paper adopts the popular Least Recently Used(LRU)caching strategy.When the content popularity is known,this paper designs a low complexity ABR-aware cache placement algorithm.The simulation results show that compared with the traditional scheme,the strategy proposed in this paper has a significant improvement in cache hit rate,backhaul traffic and content access delay.