Reinforcement Learning-Based Routing Protocols in Flying Ad Hoc Networks (FANET): A Review

In recent years, flying ad hoc networks have attracted the attention of many researchers in industry and universities due to easy deployment, proper operational costs, and diverse applications. Designing an efficient routing protocol is challenging due to unique characteristics of these networks such as very fast motion of nodes, frequent changes of topology, and low density. Routing protocols determine how to provide communications between drones in a wireless ad hoc network. Today, reinforcement learning (RL) provides powerful solutions to solve the existing problems in the routing protocols, and designs autonomous, adaptive, and self-learning routing protocols. The main purpose of these routing protocols is to ensure a stable routing solution with low delay and minimum energy consumption. In this paper, the reinforcement learning-based routing methods in FANET are surveyed and studied. Initially, reinforcement learning, the Markov decision process (MDP), and reinforcement learning algorithms are briefly described. Then, flying ad hoc networks, various types of drones, and their applications, are introduced. Furthermore, the routing process and its challenges are briefly explained in FANET. Then, a classification of reinforcement learning-based routing protocols is suggested for the flying ad hoc networks. This classification categorizes routing protocols based on the learning algorithm, the routing algorithm, and the data dissemination process. Finally, we present the existing opportunities and challenges in this field to provide a detailed and accurate view for researchers to be aware of the future research directions in order to improve the existing reinforcement learning-based routing algorithms.