Active Disturbance Rejection Regulation Control Strategy of Microgrid Load Side Interface Converter Based on TD3 Algorithm

As a new power system structure, microgrid can effectively integrate renewable energy and improve energy utilization efficiency and power quality. In this paper, a linear active disturbance rejection control strategy based on TD3 algorithm is proposed to solve the problem that the DC-DC converter on the load side of microgrid is prone to fluctuation of output voltage caused by disturbance.Through the introduction of deep reinforcement learning strategy, the parameters of the ADRC controller were self-tuning, so that the microgrid could operate stably.The dynamic response characteristics and stability of the system under different operating conditions are compared by simulation. The results show that the stability and disturbance resistance of the control system using TD3-LADRC are better than those of the traditional PI double closed-loop control and LADRC control.