Commutation failure suppression strategy of HVDC transmission system based on deep double Q-Network

In the case of AC system fault at the inverter side of HVDC transmission system, commutation failure will occur when the turn-off angle of the inverter is less than the limit turn-off angle. To solve the problem of commutation failure, this paper presents a commutation failure suppression strategy of HVDC transmission system based on Deep Double Q-Network (DDQN). A reinforcement learning algorithm with double neural network structure is adopted to accurately predict the DC current value at the inverter side, thus improving the commutation failure prevention and control module (CFPREV), reducing the trigger delay angle at the inverter side and dynamically adjusting the constant current reference value at the rectifier side based on predicted value. At last, the experimental results show that this strategy can effectively suppress commutation failure of HVDC transmission system.