Skip to Main Content
In this paper, we propose a novel architecture for optimizing the overall performance of vehicular dynamic spectrum access (VDSA) networks. Due to the high level of mobility for vehicles operating under highway conditions, coupled with spatially variant spectrum allocation across a large geographical region, we envision that future vehicular communications will employ a form of dynamic spectrum access (DSA) in order to facilitate wireless transmissions between vehicles and with roadside infrastructure. In particular, the VDSA concept will be enabled by a combination of software-defined radio (SDR) technology, spectral occupancy databases, and machine learning techniques for enabling network automation. A vehicular networking scenario is substantially different relative to a generic mobile scenario with respect to the high level of mobility involved, the predictable trajectories of the vehicular traffic, and the overall scale of the network range. Consequently, the proposed architecture is designed to enable VDSA in a more flexible wireless spectrum environment by leveraging the cognitive radio concept and existing wireless spectrum databases actively being developed while simultaneously being compatible with current spectrum regulations. Regarding practical issues for vehicular communications, vehicle mobility is taken into account in order to ensure primary user protection, databases and channel priority schemes are used in order to record temporal and spatial channel heterogeneity, and vehicle path prediction techniques are employed in order to enhance channel access in this operating environment. Specifically, we show the advantages of employing the proposed learning architecture via a case study where reinforcement learning is used in order to achieve intelligent channel selection within a realistic VDSA environment. Moreover, performance enhancements in terms of channel switching times, interference, and throughput are shown via computer simulations.