Evolutionary algorithm for task offloading in vehicular fog computing

Internet of Things technology was introduced to allow many physical devices to connect over the Internet. The data and tasks generated by these devices put pressure on the traditional cloud due to high resource and latency demand. Vehicular Fog Computing (VFC) is a concept that utilizes the computational resources integrated into the vehicles to support the processing of end-user-generated tasks. This research first proposes a bag of tasks offloading framework that allows vehicles to handle multiple tasks and any given time step. We then implement an evolution-based algorithm called Time-Cost-aware Task-Node Mapping (TCaTNM) to optimize completion time and operating costs simultaneously. The proposed algorithm is evaluated on datasets of different tasks and computing node sizes. The results show that our scheduling algorithm can save more than $60\%$ of monetary cost than the Particle Swarm Optimization (PSO) algorithm with competitive computation time. Further evaluations also show that our algorithm has a much faster learning rate and can scale its performance as the number of tasks and computing nodes increases.