Research On Capacity Of Mobile Edge Caching System

The popularity of mobile terminal devices such as smartphones and tablet computers,and the emergence of real-time systems make the core network face severe challenges.A large number of terminal devices consume a lot of bandwidth and energy for data transmission.The current backbone network has no enough ability to handle such a huge amount of data.As the key technology of 5G,mobile edge computing migrates computing,communication,and storage functions from the core of the network to the edge of the network,i.e.,more closer to the users.It has high bandwidth,low latency,and location awareness functions,which can effectively relieve the pressure on the backbone network.Mobile edge computing and cloud computing are complementary.The latter focuses on overall control and is mainly responsible for long-term,non-real-time tasks;the former emphasizes locality and is responsible for short-term,real-time tasks.Compared with cloud computing,mobile edge computing is more flexible.The disadvantage is that the computing and storage capabilities of edge devices are limited,and the edge cache system needs to be optimized to improve the user experience.Based on the cache problem of mobile edge computing,this paper takes the capacity as the optimization target to improve the mobile edge caching system.Traditional researchs on capacity usually assumed that the nodes work independently and the network status does not change over time,ignoring the cooperation between nodes and the dynamic both in users and content on capacity over time.This paper studies the impact of nodes collaboration,users’ mobility,and user-content relationship evolution on the capacity of mobile edge system.First,the problem of maximizing the capacity is transformed into the problem of minimizing the transmission distance respectively;second,the Lagrangian multiplier method is used to solve the optimal copies number in order to minimize the transmission distance and maximize the capacity.The number of copies changes according popularity.Finally,the simulation results analyze the change of the content copy number,the influence of various parameters on the capacity,and the comparison between the proposed scheme and the classic schemes.The main works of this paper are as follows:(1)Aiming at the problem that the storage space of a single node is limited,node cooperation is proposed to increase the capacity of the mobile edge caching system.The capacity is optimized while accepting the cost of collaboration.The optimal number of copies that can minimize the transmission distance and maximize the capacity is calculated.A caching scheme is proposed based on the number of copies.This solution aims at the cache of the ith content and divides all the nodes into areas to ensure that there is a node in each area to cache the ith content,so that users can request the content at a relatively close distance.Simulation results show that compared with non-cooperative schemes,nodes cooperation can increase the capacity of the mobile edge caching system.(2)Aiming at the user terminal’s mobility over time,the influence of the users’ arrival and departure the coverage area of the base station on the system capacity is studied.The bipartite graph is used to represent the relationship between the users and the content.The users and content are taken as the vertices at both ends of the bipartite graph,and the degree of content is calculated according to the user’s request for the content in the bipartite graph.We calculate the probability that the content is requested,the transmission distance when the user requests the content,and the capacity based on the degrees of content.(3)Aiming at the time-varying state of the network,the influence of user and content evolution on capacity is studied.The bipartite graph is used to represent the evolutionary relationship between users and content over time.The probability of content being requested is represented by the arrival and departure of usres,and the storage or deletion of content.According to the probability that the content is requested at the current moment,the current optimal number of copies is calculated,so as to calculate the minimum transmission distance and maximum capacity,and provide users with higher quality of service.In this paper,the capacity of the mobile edge caching system is optimized.First,the effect of the cooperation of edge nodes on the capacity of the mobile edge cache system is studied which is based on the stable network condition.In reality,the network topology may continuously change with time because of the mobility of users.Then,the impact of users’ arrival and departure on capacity is studied.At the same time,considering the fact that not only users arrival and departure the coverage of the base station over time,but also content will be continuously stored or deleted.The impact of user-content relationship on capacity over time is thus studied.