Distributed Imitation-Orientated Deep Reinforcement Learning Method for Optimal PEMFC Output Voltage Control

In order to improve the stability of proton exchange membrane fuel cell (PEMFC) output voltage, a data-driven output voltage control strategy based on regulation of the duty cycle of the DC-DC converter is proposed in this paper. In detail, an imitation-oriented twin delay deep deterministic (IO-TD3) policy gradient algorithm which offers a more robust voltage control strategy is demonstrated. This proposed output voltage control method is a distributed deep reinforcement learning training framework, the design of which is guided by the pedagogic concept of imitation learning. The effectiveness of the proposed control strategy is experimentally demonstrated.

Finite-time disturbance observer–based funnel voltage control strategy for vehicle-to-grid inverter in islanded mode

Based on vehicle-to-grid technology, electric vehicles can be used as power sources in the case of power failure. With the aim to reduce voltage overshoot and improve the anti-disturbance ability of the vehicle-to-grid inverter, a high-performance voltage control strategy based on funnel control and finite-time disturbance observer is developed. First, the dynamic model of the inverter in dq-frame is established, and the lumped disturbance including the unmodeled part is considered. Next, a novel funnel variable is proposed to ensure that the voltage tracking error can be stabilized within the prescribed funnel boundary, and thus enhance the transient performance. Then, a novel finite-time disturbance observer is designed to estimate the lumped disturbance in the system such as load fluctuations, and improve the anti-disturbance ability of the controller. Moreover, the second-order sliding mode differentiator is introduced to estimate the derivative of the virtual control law and eliminate the explosion of complexity problem in the derivation process. Finally, the finite-time stability of the proposed voltage control strategy is analyzed via the Lyapunov theory. The effectiveness of the proposed control strategy is verified by two cases.