UAV Path Planning With QoS Constraint in Device-to-Device 5G Networks Using Particle Swarm Optimization

Unmanned Ariel Vehicles (UAVs) are tasked to collect sensory data which are typically retrieved after the flight. The emergence of 5G and Device-to-Device (D2D) networks enables high speed network communication for UAVs to transfer data during a flight mission instead of post flight. UAVs are now subject to constraints of area coverage, battery capacity and network quality of service, making their path planning more challenging. In this paper, we formulate the issue as a combinatorial optimization problem which minimizes the flight cost of multiple UAVs covering the entire area. We show this problem is NP-hard, therefore we propose a Particle Swarm Optimization heuristic along with path encoding and local search techniques to solve the problem. Our numerical simulations demonstrate the effectiveness of the approach and how the size of the area and D2D link affect the number of UAVs needed and their flight time.