Vehicle cooperative planning method based on global traffic situation
To address urban traffic congestion, low vehicle throughput, and high energy consumption, a vehicle cooperative planning method based on global traffic conditions is proposed. Combining the spatiotemporal evolution characteristics of traffic conditions, a multi-objective vehicle cooperative planning model considering traffic flow density, throughput, and energy consumption is constructed. An improved particle swarm optimization algorithm is designed to solve the model, addressing its multi-constraint and multiobjective characteristics, thereby improving optimization efficiency and solution optimality. To verify the effectiveness and innovation of the method, multi-scenario experiments are constructed based on the SUMO traffic simulation platform, and a comprehensive comparison is made with the traditional Dijkstra's path planning method (TPM) and the cooperative planning method based on local traffic information (LCPM). Simulation experiments show that this method significantly improves average travel time, road network throughput, and vehicle energy consumption compared to traditional planning methods, and exhibits stronger adaptability under high congestion conditions. The research results provide a new technical approach for improving the operational efficiency of urban road networks and alleviating traffic congestion.