Performance Analysis of a VM-PM Repair Strategy in MEC-Enabled Wireless Systems With Bursty Traffic

With the rapid development of wireless communication technology, Internet of Things (IoT) is more widely used in diverse application domains, hence bringing massive timely and bursty data flows. Mobile edge computing (MEC) enables computation and energy constrained IoT devices to offload tasks on powerful servers deployed at the edge of networks. Despite considerable advancements and merits, infrastructures in MEC systems are still lack of robustness. In order to better guarantee the response performance and effectively improve the dependability of the MEC-enabled wireless system, we propose a VM-PM repair strategy with PM preventive maintenance. By introducing Markovian arrival process (MAP) to capture bursty traffic, we model the local computing and edge computing as a MAP/M/1 queue and a MAP/M/N queue, respectively. Then, by using matrix-geometric solution, we obtain several key performance indexes, including task response latency, throughput, energy consumption level, and computation resource availability. Next, we carry out system experiments to explore the change trends of the system performance. Finally, we jointly optimize the key performance indexes by formulating a multi-objective mixed-integer optimization (MIO) problem. In addition, we develop a sine cosine based task scheduling and server maintenance (SC-TSSM) algorithm to obtain the optimal offload rate and preventive maintenance threshold.