A cluster-based vehicular cloud architecture with learning-based resource management

Recent advances in wireless communication technologies have made it possible to implement Intelligent Transportation Systems (ITS) to have more safety in roads and eliminating the excessive cost of traffic collisions. However, there are some resource limitations in mobile vehicles, which is a significant technical challenge in the deployment of new applications and advancement of ITS services. In this paper, a new vehicular cloud architecture is proposed which uses a clustering technique to solve the resource limitation problem by grouping the vehicles and cooperatively providing the resources. To be more specific, the clustering structure is made flexible using the fuzzy logic in the cluster head selection procedure. Resource management of the proposed architecture is improved by employing the Q-learning technique to select a service provider among participant vehicles as well as introducing three different queuing strategies to solve resource allocation problem. Finally, the performance of proposed architecture is evaluated using extensive simulation and its efficiency is demonstrated through comparison with other existing approaches.