Secure and Energy-Efficient Communication for Internet of Drones Networks: A Deep Reinforcement Learning Approach

Internet of Drones (IoD)-aided wireless networks are proving their efficiency in various commercial and military applications, such as object recognition, surveillance, and data acquisition. IoD networks employ several drones to acquire data from ground entities and transmit this data to a gateway agent for further analysis. However, IoD-aided wireless networks face various challenges. The first challenge originates from the IoD networks' line-of-sight and broadcast wireless communication nature, which raises significant security issues. The second challenge is energy efficiency, where battery capabilities highly constrain IoD networks. This Thesis investigates drone-to-ground communication subject to eavesdroppers in urban environments. We aim to provide secure communication utilizing physical layer security by increasing network secrecy rates while reducing energy consumption. This is achieved by optimizing drones' transmitting and jamming power and employing energy harvesting techniques to charge drones wirelessly. We formulate Our optimization problem utilizing Markov decision process (MDP), and to solve our problem we propose a deep deterministic policy gradient (DDPG) algorithm. The extensive simulations show that our proposed algorithm is able to solve the optimization problem to achieve the maximum average secrecy rate while minimum energy consumption is used.