Task Allocation for Multi-APs with Mobile Edge Computing

Mobile Edge Computing(MEC) and Ultra-Dense Network(UDN) are two key technologies in next-generation network. UDN can bring a lot of convenience to MEC because small cells in UDN are close to users. However, the integration of these two technologies may bring many problems and one of the problems is task offloading. In this paper, we consider a practical application that contains many dependent subtasks. Some of these subtasks can be executed in parallel. We model the application as a Directed Acyclic Graph (DAG). The UE decides which subtask should be uploaded to which AP. We formulate this problem as a scheduling problem, which is NP-hard. In order to solve this problem, we propose a heuristic algorithm based on the list scheduling algorithm, called Unified Minimum Finish Time Algorithm. This algorithm jointly considers transmission time between APs and offloading time from UE to APs. Simulation results show that our proposed algorithm can significantly improve performance (compared to three baseline policies).