摘要
Being the building block of network infrastructure for Vehicular Ad-hoc Networks (VANETs), Roadside Units (RSUs) can facilitate vehicle-to-vehicle communications and bridge communications between vehicles and the Internet. However, RSUs are expensive and will be in serious shortage state for a relative long time when deploying VANETs gradually. Hence, maximizing expected deployment profit with limited number of RSUs in road network systems is of great importance. In this paper, we create a novel powerful RSU Deployment Problem Model (RDPM) consisting of a road-network model and a profit model. The road-network model in RDPM supports complicated road shapes meanwhile taking into consideration of key influential factors such as lane number, popularity. Since that the optimal RSU deployment solution of a RDPM problem is hard to obtain, we proposed a genetic algorithm based method to solve it heuristically. Simulation results confirm that our proposed method outperforms the exiting typical BEH method.