Machine Learning Based Unmanned Aerial Vehicle Enabled Fog-Radio Access Network and Edge Computing

Machine Learning Based Unmanned Aerial Vehicle Enabled Fog-Radio Access Network and Edge Computing

Mohammed Seid1, 2, Stephen Anokye1,3 and SUN Guolin1

(1. University of Electronic Science and Technology of China, Chengdu 611731, China;
2. Dilla University, Dilla, Ethiopia;
3. University of Mines and Technology, Tarkwa 237, Ghana)

Abstract: The rapid growth of unmanned aerial vehicle (UAV) technology and its applications have become part of the massive Internet of Things (mIoT) ecosystem for future cellular networks. Internet of things (IoT) devices have limited computation capacity and battery life and the cloud is not suitable for offloading IoT tasks due to the distance, latency and high energy consumption. Mobile edge computing (MEC) and fog radio access network (F-RAN) together with machine learning algorithms are an emerging approach to solving complex network problems as described above. In this paper, we suggest a new orientation with UAV enabled F-RAN architecture. This architecture adopts the decentralized deep reinforcement learning (DRL) algorithm for edge IoT devices which makes independent decisions to perform computation offloading, resource allocation, and association in the aerial to ground (A2G) network. Additionally, we summarized the works on machine learning approaches for UAV networks and MEC networks, which are related to the suggested architecture and discussed some technical challenges in the smart UAV-IoT, F-RAN 5G and Beyond 5G (6G).
Keywords: unmanned aerial vehicle; machine learning; F-RAN; edge computing