Joint Optimization of Base Station Clustering and Service Caching in User-Centric MEC

Edge service caching can effectively reduce the delay or bandwidth overhead for acquiring and initializing applications. To address single-base station (BS) transmission limitation and serious edge effect in traditional cellular-based edge service caching networks, in this paper, we proposed a novel user-centric edge service caching framework where each user is jointly provided with edge caching and wireless transmission services by a specific BS cluster instead of a single BS. To minimize the long-term average delay under the constraint of the caching cost, a mixed integer non-linear programming (MINLP) problem is formulated by jointly optimizing the BS clustering and service caching decisions. To tackle the problem, we propose JO-CDSD, an efficiently joint optimization algorithm based on Lyapunov optimization and generalized benders decomposition (GBD). In particular, the long-term optimization problem can be transformed into a primal problem and a master problem in each time slot that is much simpler to solve. The near-optimal clustering and caching strategy can be obtained through solving the primal and master problem alternately. Extensive simulations show that the proposed joint optimization algorithm outperforms other algorithms and can effectively reduce the long-term delay and caching cost.

I. Introduction

With the rapid development of the mobile Internet, data traffic is experiencing explosive growth due to pervasive mobile devices, ubiquitous social networking, and resource-intensive applications [1]. When running newly emerging applications such as augmented reality (AR) and virtual reality (VR), massive computing tasks will be generated (video rendering, etc.). Processing some of the computing tasks depends on various types of services. For example, in an AR application, the object databases and visual recognition models are required to process the user's input data and run classification or object recognition [2]. However, in rush hours or traffic jams, direct service dissemination from remote data centers in real-time may lead to unprecedented network traffic load and congestion, and may also induce long transmission delay [3]. By deploying servers in the radio access network (RAN), mobile edge computing (MEC) [4], [5] can provide users with low-latency computing, caching, and transmission capabilities [6]. MEC servers can pre-cache the popular services in advance, and process user's offloaded requests instead of routing the requests to the remote data centers [7]. Through caching services in a distributed manner that is close to users, edge service caching overcomes the problems of high transmission delay caused by long-distance data transmission of the cloud server, alleviates the burden on the backhaul links, and reduces the risk of being attacked by the malicious nodes.