A Genetic Algorithm for Task Offloading problem in Vehicular Edge Computing

In this paper, we consider task offloading in vehicular edge computing systems. The limited battery limits the mileage of electric vehicles. For a longer driving distance, the task of the vehicle can not only be performed locally, but also offload task to save energy. In this way, the energy consumption of the system is reduced and the energy utilization rate of the whole system is improved. The task offloading involves optimization variables which are where to offload tasks and the frequency, and the optimization variables are coupled. So it is hard to decide how to allocate tasks. We propose that we can solve this problem by using genetic algorithm. Specifically, our experiment shows between 20% and 25% energy savings compared to the baseline which the tasks executes workload locally.