An overview of machine learning applied in wireless UAV networks

Unmanned aerial vehicles (UAVs) are expected to be deployed in future cellular networks in a wide range of scenarios, such as to rapidly restore network service after natural disasters, to provide extra coverage to wireless networks, or to deliver content to remote locations. However, despite their benefits, several issues are still present in UAV networks, such as how to determine their optimal positioning or trajectory, how to perform resource management or manage interference to name a few. One way of solving these issues is by analyzing data coming from the network to learn patterns and react accordingly. These solutions, rely on machine learning algorithms, and by integrating them in UAV networks, more autonomous and flexible systems can be achieved. Based on that, several recent works have explored this concept of integrating UAVs and machine learning algorithms in wireless networks. As such, this article presents an overview machine learning applications in aerial wireless networks. Before reviewing these works, an introduction to key machine learning concepts and categories is performed. After that, a literature review of current state‐of‐the‐art research is presented, followed by a discussion on future research directions and paradigms in UAV‐aided wireless networks. Lastly, conclusions are drawn