Energy Minimization for Cellular-Connected Aerial Edge Computing System with Binary Offloading

Due to the characteristic of wide coverage, flexible deployment, and low cost, unmanned aerial vehicles (UAVs) have been employed to provide mobile crowdsensing and edge computing. However, the limited computation and onboard battery capacities of UAVs impose a changeling for timely computation and endurance. In this article, we consider an aerial edge computing system where multiple cellular-connected UAVs are employed to perform sensing and computation tasks over target subregions, and the UAVs can offload their computation tasks to the ground base station (BS) with the binary offloading scheme. We aim to minimize the maximum energy consumption of all UAVs by optimizing 3-D UAV trajectories jointly with the binary offloading indicator as well as computation resource allocation, subject to the target sensing constraints and the computation completion time constraints. The optimization problem we formulated is nonconvex and involves binary design variables, making it difficult to find the optimal solution. To address this challenge, we propose an efficient alternating optimization algorithm that can obtain a high-quality suboptimal solution, where the exact penalty method with equilibrium constraints is adopted to tackle the binary constraints. To tackle the nonconvexity of the optimization subproblems, we utilize the successive convex approximation approach to obtain a suboptimal solution. Extensive simulations are conducted and the results demonstrate that the proposed design significantly reduces the energy consumption of the UAVs over several baseline methods.