A Trade-Off Task-Offloading Scheme in Multi-User Multi-Task Mobile Edge Computing

Abstract

Mobile edge computing is a novel technique that can reduce computational burden of local terminal devices by tasks offloading, which emerges as a promising paradigm to provide computing capabilities near mobile users. In this paper, the task offloading decision to solve the queuing problem of tasks to be processed in the local terminals was being considered, with an application of Lyapunov theory to ensure the queue stability. Then, a trade-off model was formulated to minimize the delay and energy consumption to achieve a minimum execution cost. Moreover, an improved Dynamic Niche-based Self-organizing Learning Algorithm was presented to accelerate the speed of the search process to gain an optimal task offloading scheme. The simulation results provided supporting evidence that the proposed optimal scheme IDO could achieve a lower average energy consumption than LFO and a lower average execution delay than EFO under the scenarios of the waiting queue length varies within [10, 50], the number of users varies within [4, 20], and the number of tasks varies within [20, 100].