A Distributed Caching Scheme Using Non-Cooperative Game for Mobile Edge Networks

• Main Authors: Huixian Gu, Haijiang Wang
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Non-cooperative game theory; nash equilibrium; distributed cache placement; cache hit rate; average edge utility
• Online Access: https://ieeexplore.ieee.org/document/9142195/

Mobile edge storage is an emerging computing paradigm which enables users to enjoy high quality of experience when they access cloud services. However, extremely fast increasing multimedia data traffic from cloud to mobile users comes with the challenges of low-latency and high-bandwidth over cloud computing model. How to design cache strategies by exploiting terminal nodes' utility is still a challenging issue. In this paper, by exploiting 5G technology and cooperative edge computing, we propose a cooperative edge caching framework to tackle three issues simultaneously in the application scenarios of massive short video services: (1) reducing data transportation latency to improve mobile uses' quality of experience; (2) mitigating data traffic pressure on backbone network; (3) decreasing the workload on cloud servers. Firstly, we define a cooperative edge caching network model, in which many edge nodes equipped with capacities of storage, user admittance and Internet access form an ad hoc network and each node serves multiple mobile users. Secondly, we design a non-cooperative game model to investigate the cooperation behavior among the edge nodes, we allow each edge node server as a player and make decision of cache (storage) initialization and replacement strategies. Thirdly, we find there is a Nash Equilibrium in the proposed game. Finally, we design a distributed algorithm to achieve the equilibrium according to our theoretical analysis. Experiment results show that the proposed game-based edge caching strategy can improve mobile uses' quality of experience by 20% latency decreasing and reduce 80% backbone traffic and cloud workload.