On Multi-Task Learning for Energy Efficient Task Offloading in Multi-UAV Assisted Edge Computing

Unmanned aerial vehicles (UAVs) have emerged as a promising platform for mobile edge computing (MEC) due to their ability to provide flexible and efficient on-demand computing and communication services. However, deploying UAVs in MEC systems raises concerns about energy efficiency since both the UAVs and users' devices are typically energy-limited. In this paper, we consider a multi-UAV assisted MEC heterogeneous network with two types of UAVs: edge UAVs equipped with computing resources and relay UAVs that assist users in transmitting their tasks to Ground Base Stations. We aim to minimize the total energy consumption of users and UAVs by optimizing task offloading decisions. We use a metaheuristic genetic algorithm to solve the optimization problem, and propose a novel multi-task convolutional neural network (MT-CNN) to efficiently predict near-optimal solutions. Simulation results demonstrate the effectiveness of our proposed model.