LAUSR

Data from running vehicles are invaluable to numerous ITS and urban computing applications. This paper studies the issue of collecting data from multiple vehicles to a roadside base station via vehicle-to-vehicle and vehicle-to-infrastructure communications. Existing data collection approaches in VANET have mainly focused on the network problems, such as packet loss, network clustering or data aggregation, but the impact of real-time traffic condition is barely considered. In this paper, we investigate the data collection problem in VANETs under rapid evolving traffic conditions. Our approach can adaptively choose to carry or forward the data packet, based on current traffic information. The objective is to minimize the network communication overhead while satisfying the data collection time constraint. We formulate the data collection problem as a scheduling optimization problem and prove it is NP-complete. An optimal dynamic programming solution and a genetic algorithm based heuristic solution are developed to solve the problem under different application scenarios. Extensive evaluations validate that our proposed solution outperforms some existing ones in terms of effectiveness and efficiency.