Physical Layer Security in the 5G Heterogeneous Wireless System with Imperfect CSI

Abstract

5G is expected to serve completely heterogeneous scenarios where devices with low or high software and hardware complexity will coexist. This entails a security challenge because low complexity devices such as IoT sensors must still have secrecy in their communications. This project proposes tools to maximize the secrecy rate in a scenario with legitimate users and eavesdroppers considering: i) the limitation that low complexity users have in computational power and ii) the eavesdroppers? unwillingness to provide their channel state information to the base station. The tools have been designed based on the physical layer security field and solve the resource allocation from two different approaches that are suitable in different use cases: i) using convex optimization theory or ii) using classification neural networks. Results show that, while the convex approach provides the best secrecy performance, the learning approach is a good alternative for dynamic scenarios or when wanting to save transmitting power.