Energy aware smartphone tasks offloading to the cloud using gray wolf optimization

Abstract

In recent era, the task offloading to cloud servers from the smartphones is a promising strategy in improving the smartphones capability and its battery lifetime. The effectiveness of task offloading is found by considering the communication cost and energy consumption, which is considered as crucial factors. These two factors enables the smartphone devices to incur proper decisions whether to perform task offloading or not. In this paper, a heterogeneous framework is designed to improve the energy efficiency of mobile phones by considering various system parameters like local cloudlets, remote cloud servers, task and non-task offloading smartphone and radio access networks. The task offloading framework uses a meta-heuristic algorithm namely Gray Wolf Optimization (GWO) to schedule the task by optimizing the system parameters and this enables to make optimal decision on task offloading. The GWO does the scheduling of tasks in optimal way to enable restriction free communication between the mobile device and cloud server. This reduces the consumption of energy in mobile devices. The GWO task offloading framework is simulated using CloudSim simulation tool and the results are compared in terms of various parameters. The result shows that the GWO task offloading framework is efficient than conventional Online Code Offloading and Scheduling and Adaptive Partitioning and Dynamic Selective Offloading.