Collaborative Multicast Proactive Caching Scheme Based on AAE

Abstract

With the increasing number of user terminals and the development of 5G technology,a network has been formed where macro base stations and small base stations co-exist.Meanwhile,applications such as ultra-high resolution video and cloud VR/AR have higher requirements for latency.In order to reduce the latency in 5G networks,a cooperative multicast proactive caching scheme based on adversarial automatic coding is proposed in this paper.In this scheme,firstly,users are divided into different groups based on their characteristics.And then the content that the group may request will be predicated by using AAE.To reduce the redundancy of cached contents,the ant colony algorithm is used to pre-deploy the predicted contents to each small base station.Finally,in the content distribution phase,if a user requests a content with high popularity,the content will be proactively cached in a multicast manner to other users in this group who don't send the request,otherwise it is distributed in a normal manner.Simulation results show that the CMPCAAE scheme outperforms the classical caching scheme in terms of average delay and missing ratio of the system.

Keywords

• edge caching|collaborative caching|proactive caching|adversarial autoencoders|multicast|ant colony algorithm