Offloading computation based on mobile edge computing paradigms can augment the computational capabilities of resource-scarce mobile devices. However, the capacity limitations of edge servers constrain the performance improvement achieved through computation offloading. In this article, we consider a three-tier computation offloading schema with multiple users, edge servers, and cloud servers. Computation can be offloaded from mobile devices to edge servers or can be further offloaded to remote cloud servers if necessary. Since a number of mobile devices connected to edge servers will share a common wireless communication network, which may contain both uplink and downlink channels, the assignment of bandwidth assignment the channels also constrains the performance improvement of computation offloading. In this paper, the problems of how to determine the offloading strategy and of how to assign the bandwidth are jointly studied and formulated as a programming problem to minimize the average application response time. We analyze the joint problem and further transform it into a piecewise convex programming problem. We propose an efficient algorithm that can find the optimal solution. Extensive experiments demonstrate that our algorithm significantly outperforms previous algorithms. The experimental results also show that the performance of our algorithm is highly robust.

In this paper, we focus on the problem of offloading computation intensive tasks of mobile applications from resource-scarce mobile devices to the servers located at the edge networks in order to minimize the average response time of the applications. We consider a number of mobile devices connected by a shared communication channel to a server located in the edge network and therefore transmission collision occurs if more than one mobile device attempts to transmit data simultaneously. We first formulate the offloading problem as a mixed integer programming (MIP) problem. Since the problem is NP-hard, we design a heuristic algorithm that considers possible transmission collision over the shared channel and offloads efficiently tasks of a mobile application to the server. We demonstrated that our proposed algorithm outperforms previous offloading algorithms significantly in terms of the average response time. Furthermore, we showed that our proposed algorithm yields less energy consumption than previous algorithms in realistic system scenarios.