Intelligent Network Access System for Vehicular Real-Time Service Provisioning

With mobile operating systems becoming increasingly common in vehicles, it is undoubted that vehicular demands for real-time Internet access would get a surge in the soon future. The vehicular ad hoc network (VANET) offloading represents a promising solution to the overwhelming traffic problem engrossed to cellular networks. With a vehicular heterogeneous network formed by a cellular network and VANET, efficient network selection is crucial to ensuring vehicles’ quality of service (QoS), avoiding network congestions and other performance degradation. To address this issue, we develop an intelligent network access system using the control theory to provide seamless vehicular communication. Specifically, our system comprises two components. The first component recommends vehicles an appropriate network to access by employing an analytic framework which takes traffic status, user preferences, service applications and network conditions into account. In the second one, a distributed automatic access engine is developed by utilizing a learning method, which enables individual vehicles to make access decisions based on access recommender, local observation and historic information. Lastly, simulations show that our proposal can effectively select the optimum network to ensure the QoS of vehicles, and network resource is fully utilized without network congestions in the meantime.