Energy and Fairness-Aware Task Offloading Using Genetic Algorithm in Multi-Server Mobile Edge Computing
TL;DR
An energy-and fairness-aware task offloading (EFATO) scheme through a GA to achieve the optimal task scheduling and loading within multiple edge servers and a novel fitness function is proposed that combines energy cost, computational delay and fairness index.
Abstract
: The rapid growth of low-latency, computation-heavy mobile applications have led to Mobile Edge Computing (MEC) as a promising paradigm that shortens the latency and reduces the energy consumption by placing cloud services close to the end-users. Nevertheless, promoting tradeoffs among energy efficiency (EE), computational fairness and latency minimization is still a challenging issue compared to in multi-server MEC systems. To this end, this paper introduces an energy-and fairness-aware task offloading (EFATO) scheme through a GA to achieve the optimal task scheduling and loading within multiple edge servers. The GA based model of the paper refers a multi-objective optimization problem that minimizes total energy consumption and end-to-end latency involving fair treatment between mobile users. To guarantee fair resource utilization, a novel fitness function is proposed that combines energy cost, computational delay and fairness index. Simulation results show that our EFATO model can outperform the existing methods on energy savings, completion time of task and the fairness index. The proposed scheme also achieves better scalability and faster convergence, which can be used in dynamic MEC for real time applications. In general, the combination of GA-based optimization with fairness constraints can result in fair and sustainable edge computing resource management.