增程式电动物流车队列的能量管理策略研究

Research on energy management strategy of extended range electric logistics platoon

以增程式电动物流车队列为研究对象,为提高整个队列的燃油经济性,从队列的协同自适应巡航控制和能量管理策略两方面进行研究。利用车对车通信和前车领航车跟随式通信拓扑结构,基于分布式模型预测控制,设计了以稳定性、舒适性和经济性为优化目标的协同自适应巡航控制器。将增程式电动物流车队列的能量管理策略描述为一个完全合作类型的多智能体强化学习问题,所有智能体共同探索在不同车辆状态下的最优控制动作,提出了基于多智能体强化学习的能量管理策略。仿真结果表明,所设计的生态协同自适应巡航控制策略能够有效地平衡车辆队列的稳定性和经济性。以动态规划为基准,与单智能体算法相比,基于多智能体深度确定性策略梯度算法的能量管理策略可以在显著提高学习速率的同时获得近似最优解。

The extended-range electric logistics fleet was taken as the research object.In order to improve the fuel economy of the whole queue,the collaborative adaptive cruise control and energy management strategies of the queue were studied.Based on distributed model predictive control,a collaborative adaptive cruise controller was designed with stability,comfort and economy as optimization objectives by using vehicle-to-vehicle communication topology and vehicle-following communication topology.The energy management strategy of extended range electric logistics fleet was described as a fully cooperative multi-agent reinforcement learning problem.All agents jointly explore the optimal control actions under different vehicle states,and an energy management strategy based on multi-agent reinforcement learning was proposed.The simulation results showed that the designed ecological cooperative adaptive cruise control strategy could effectively balance the stability and economy of the vehicle queue.Based on dynamic programming,compared with the single-agent algorithm,the energy management strategy based on the multi-agent depth deterministic strategy gradient algorithm could significantly improve the learning rate and obtain the approximate optimal solution.