Integrated driving behavior analysis and predictive modeling for connected electric vehicles toward energy consumption optimization

Accurate prediction of driving conditions is essential for optimizing energy consumption and enhancing the operational efficiency of connected electric vehicles (EVs). While traditional models emphasize road conditions and vehicle dynamics, they often overlook the significant influence of driving behavior. This study presents a novel predictive framework that integrates detailed driving behavior analysis with model predictive control (MPC) to improve the accuracy and robustness of driving condition prediction. Leveraging connected vehicle technologies, we develop an energy flow model for EVs and examine multi-vehicle platoon dynamics under representative urban traffic scenarios. By analyzing peak traffic periods and driver behavior characteristics, the framework enables target speed optimization and facilitates efficient “green wave” passage through signalized intersections. Simulation results under suburban conditions show that the proposed method effectively maintains safe inter-vehicle distances, reduces energy consumption, and adapts to diverse driving styles. Overall, the framework demonstrates strong potential for harmonizing traffic efficiency, driving safety, and energy economy, offering practical insights for urban traffic control and EV range estimation.