Energy-Efficient Task Offloading and Transmit Power Allocation for Ultra-Dense Edge Computing

Abstract

In order to meet the ever-increasing demands on computational and spectrum resources in the era of 5G and Internet of Things (IoT), mobile-edge computing (MEC) and ultra-dense heterogeneous network (UDN) have been envisioned as two promising technologies, which gives rise to the so-called ultra-dense edge computing. Note that existing works on task offloading for ultra-dense edge computing mostly considered simple task offloading scenarios, ignoring the random request for types of computation tasks from the mobile devices (MDs) and the random arrival of the tasks at the edge servers. Toward this end, we provide this paper to study the multi-user task offloading problem in ultra-dense edge computing with multiple types of tasks requested by the MDs. To minimize the MDs' energy consumption and thus prolong their battery lifetime, task offloading, computation frequency scaling, and transmit power allocation are jointly optimized in this paper. After that, the problem is divided into two subproblems, i.e., local energy minimization, and joint task offloading and transmit power allocation. A game-theoretical joint offloading scheme is proposed as our solution. Extensive numerical results corroborate the superior performance of our proposed scheme rather than those with single edge server, fixed computation frequency and transmit power at the MDs.