Multi-Task Cross-Server Double Auction for Resource Allocation in Mobile Edge Computing

Mobile edge computing (MEC) enables a distributed computing environment closer to mobile devices (MDs) and substantially reduces the response time for a MD computing task. However, lightweight servers may be incapable of keeping up with all the tasks from MDs due to the limited resources. Therefore, how to effectively allocate resources of edge servers for profit-driven multi-task users is a key issue in MEC. In this paper, we study the cross-server resource allocation scheme in MEC from the perspective of network economics. Because of the supply-demand relationship between the edge servers providing services and the MDs requesting the services, we regard the resource allocation as an auction problem in the network economics. In particular, we propose a multi-task resource allocation algorithm based on double auction (MADA) to maximize the system efficiency. The simulation results indicate that MADA can efficiently allocate resources while maintaining the economic properties of individual rationality, truthfulness and weakly balanced budget.