Min-Max Joint Task Offloading and Resource Allocation Optimization in MEC Empowered Air-ground Integrated Networks

Abstract Recent years, unmanned aerial vehicle (UAV) has become an important assistant that could act as access points (APs) for communication, and can also act as edge nodes for task offloading in mobile edge computing (MEC), etc., in many scenarios. We consider a multiuser mobile offloading network consisting multiple UAV based MEC nodes. The tasks could be processed locally, or offloaded to the UAV edge nodes, or migrated to the cloud further on. We formulate the offloading problem as the joint optimization of offloading decision making of all the SMEs, the computation resource allocation among the edge-executing applications, and radio resource assignment among all the remote-processing applications, aiming to minimize the maximum total weighted cost of all the SMEs. It is demonstrated that the problem is NP-hard. To tackle this challenge, offloading decisions are obtained using SDR. Next a firework algorithm is adopted novelly in radio resource allocation, and the computation resource is distributed uniformly among all the fog-executing users. Simulation results exhibit that as a result of the collaboration of the fog and cloud, the proposed joint algorithm could achieves nearly optimal performance in the aspects of energy consumption, delay, and a weighted cost of the both compared with others algorithms.