Intelligent interface switching among heterogeneous wireless networks for vehicular communications

As future vehicular communications will most likely involve multiple wireless networks, intelligent interface switching is of essential importance to support various user preferences across different performance metrics. In this paper, we present a general optimization framework for solving the interface switching problem, and develop a flexible and efficient solution based on stochastic dynamic programming (SDP). Our framework is designed to accommodate different performance metrics such as data transfer efficiency, monetary cost, and interface switching overhead. Accordingly, the proposed SDP-based policy can easily adapt its decision based on user-specified relative importance of the various metrics. Simulation study confirms the optimality of the SDP-based policy over a range of user preference choices, and shows that it consistent outperforms several heuristic schemes.