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

Haidong Huang; Xindong Li; Xiaofan Hou; Daojun Zha; Wei Dai; Dan Wu

doi:10.1117/12.2611410

14 October 2021 Commutation failure suppression strategy of HVDC transmission system based on deep double Q-Network

Haidong Huang, Xindong Li, Xiaofan Hou, Daojun Zha, Wei Dai, Dan Wu

Proceedings Volume 11930, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation; 119300K (2021) https://doi.org/10.1117/12.2611410
Event: International Conference on Mechanical Engineering, Measurement Control, and Instrumentation (MEMCI 2021), 2021, Guangzhou, China

Abstract

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.

Citation Download Citation

Haidong Huang, Xindong Li, Xiaofan Hou, Daojun Zha, Wei Dai, and Dan Wu "Commutation failure suppression strategy of HVDC transmission system based on deep double Q-Network", Proc. SPIE 11930, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation, 119300K (14 October 2021); https://doi.org/10.1117/12.2611410

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available