Abstract
In this paper, we propose and study an energy-efficient trajectory
optimization scheme for unmanned aerial vehicle (UAV) assisted Internet
of Things (IoT) networks. In such networks, a single UAV is powered by
both solar energy and charging stations (CSs), resulting in sustainable
communication services, while avoiding energy outage. In particular, we
optimize the trajectory design of UAV by jointly considering the average
data rate, the total energy consumption, and the fairness of coverage
for the IoT terminals. A dynamic spatial-temporal configuration scheme
is operated for terminals working in the discontinuous reception (DRX)
mode. The module-free, action-confined on-policy and off-policy
reinforcement learning (RL) approaches are proposed and jointly applied
to solve the formulated optimization problem in this paper. We evaluate
the effectiveness of the proposed strategy by comparing it with other
dynamic benchmark algorithms. The extensive simulation results provided
in this paper reveal that the proposed scheme outperforms the benchmarks
in terms of data transmission, energy efficiency and adaptivity of
avoiding battery depletion. By deploying the proposed trajectory scheme,
the UAV is able to adapt itself according to the temporal and dynamic
conditions of communication networks.