Three-Side Dynamic Task Offloading for Smart Roads Enabled Vehicular Edge Computing

Smart roads can achieve a comprehensive, real-time and accurate perception of road environment, which is of great significance for intelligent transportation systems (ITS). However, due to massive data needed to be computed, cloud computing usually imposes pressure on backhaul and produces high delay. In this context, mobile edge computing (MEC) provides a promising solution. Meanwhile, current researches of the task offloading based on MEC lack global considerations and ignore IoT devices along the roadside, so optimization on three-side is very necessary and worth researching. To this end, we consider a scenario of smart roads including vehicular terminals (VTs), IoT devices and MEC servers. And we formulate an optimization problem aiming at minimizing a weighted sum of the costs of energy consumption and time delay for users side and cost for MEC servers. On this basis, we propose a three-side dynamic joint task offloading and resource allocation (TDJORA) scheme. Moreover, considering that the optimization problem is a multi-objective optimization problem, we utilize a combination of the particle swarm optimization (PSO) algorithm and Pareto optimality to obtain the optimal solution. Simulation results show that our proposed TDJORA can realize reasonable task offloading and optimal resource allocation for three sides.