HTR: A Joint Approach for Task Offloading and Resource Allocation in Mobile Edge Computing

Abstract

With the proliferation of wireless networks, such as WiFi and LTE/5G, Mobile Edge Computing (MEC), is expected to be a promising solution to the resource constraint problem in mobile devices. Technically, MEC is composed of two types of devices: resource-hungry end devices and resource-rich base stations equipped with edge servers. Despite the popularity of MEC, efficient task offloading and resource allocation have been two challenging problems to be tackled. In this paper, we propose an innovative scheme, HTR, that jointly solves the task offloading and resource allocation problem in MEC. Specifically, the problem of task offloading and resource allocation is formulated as a Mixed Integer Non-Linear Programming (MINLP) problem. To reduce the computation complexity of the solution to the MINLP problem, HTR decouples the MINLP problem into two sub-problems: one of them solves the resource allocation problem while the other tackles the task offloading issue. With this carefully-designed approach, both the task offloading and resource allocation problem could be solved with light computation complexity. Our experiment results indicate the HTR outperforms the existing task offloading/resource allocation schemes.