Hierarchical energy management control for connected hybrid electric vehicles in uncertain traffic scenarios

For complex and uncertain traffic scenarios on urban roads, improving overall efficiency and energy optimization remains a challenging issue for connected hybrid electric vehicles. Vehicles are typically in uncertain traffic scenarios, including free driving, car following, and through traffic lights. This paper proposes a hierarchical energy management control that combines scenario-adaptive speed planning and dynamically optimized energy management to achieve higher mobility and energy efficiency. Speed planning combines uncertain scenario classification and scenario-adaptive speed solving to improve adaptation and computational efficiency. The state of charge (SOC) reference prediction model and adaptive parameters are offline optimized using an adaptive neuro-fuzzy inference system (ANFIS) and particle swarm optimization (PSO), and they are online realized in energy management. Dynamic adaptive speed planning and efficient power allocation improve adaptability and near-global optimization for uncertain traffic scenarios. The simulation comparison results with existing methods show that the proposed strategy can reduce energy consumption while ensuring safe and efficient vehicle passage in uncertain traffic scenarios.