Collaborated eco-routing optimization for continuous traffic flow based on energy consumption difference of multiple vehicles

Transportation accounts for a large proportion of energy consumption and environmental pollution, and eco-routing is recognized as a potential solution to green mobility. In this context, this study investigates the co-optimization problem of eco-routing on a road network for heterogeneous continuous vehicle flow. Firstly, the energy consumption estimation models for 33 types of vehicles are constructed by artificial neural networks with a large amount of historical driving data. In this case, the Bureau of Public Roads function and traffic light models are imported to establish the road network model, accurately reflecting the impact of congestion and traffic lights change on vehicle speeds. Finally, based on the energy consumption difference of different vehicles, a collaborative heterogeneous multi-vehicle eco-routing optimization strategy is proposed to improve the overall economy in the road network. Simulation experiments are conducted under different traffic flow conditions and multiple road networks. The results verify that an energy-saving improvement up to 11.50% is obtained compared with the conventional path planning approach, providing efficient promotions to the energy consumption reduction of connected and automated vehicles.