An Efficient Dynamic Offloading Approach Based on Optimization Technique for Mobile Edge Computing

Mobile Cloud Computing (MCC) is a new paradigm to provide computation capabilities at the edge networks near mobile devices to speed up the executions of mobile applications and reduce the power consumptions at mobile devices. In this paper, we focus on the problem of how to dynamically offload the computation intensive tasks of newly executed mobile applications from resource-scarce mobile devices to the servers located at the edge networks in order to minimize the average application completion time. We consider a system model in which there are a set of mobile devices connected to an edge server by a shared communication network. Furthermore, we take into account of possible transmission collisions at the shared network when more than one mobile device attempts to transmit data simultaneously. We first formulate a static offloading problem as an MIP problem that can be solved using an appropriate optimization tool such as Gurobi optimizer. Then, we extend the static problem to solve the dynamic offloading problem considered in this paper. Using simulation experiments, we show that our proposed approach outperforms significantly previous approaches for a wide range of system parameters.