Secure Social Networks in 5G Systems with Mobile Edge Computing, Caching, and Device-to-Device Communications

Abstract

Mobile social networks (MSNs) have continuously been expanding and trying to be innovative. Recent advances of mobile edge computing (MEC), caching, and device-to-device (D2D) communications can have significant impacts on MSNs in 5G systems. In addition, the knowledge of social relationships among users is important in these new paradigms to improve the security and efficiency of MSNs. In this article, we present a social trust scheme that enhances the security of MSNs. When considering the trust-based MSNs with MEC, caching, and D2D, we apply a novel deep reinforcement learning approach to automatically make a decision for optimally allocating the network resources. Google TensorFlow is used to implement the proposed deep reinforcement learning approach. Simulation results with different network parameters are presented to show the effectiveness of the proposed scheme.