Post-disturbance trajectory prediction and transient stability assessment based on a physics-informed machine learning algorithm

Yangqing Dan; Yingjing He; Hanze Zhou; Yuhong Zhu; Yongzhi Zhou

doi:10.1117/12.2680401

18 July 2023 Post-disturbance trajectory prediction and transient stability assessment based on a physics-informed machine learning algorithm

Yangqing Dan, Yingjing He, Hanze Zhou, Yuhong Zhu, Yongzhi Zhou

Author Affiliations +

Proceedings Volume 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023); 127220R (2023) https://doi.org/10.1117/12.2680401
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 2023, Hangzhou, China

Abstract

Despite great progress in transient stability assessment (TSA) using machine learning-based approaches, one still cannot seamlessly relate data-driven TSA methods to the dynamics of post-disturbance systems. Uninterpretable black-box decisions neglecting the inherent physics information are typically unacceptable in the power industry. A physics-informed machine learning-based method is proposed to predict the post-disturbance trajectory, where the differential-algebraic equations governing physical characteristics are introduced to guide the training process. Then, a novel TSA framework is developed that combines the system stability results with the predicted post-disturbance trajectories, where the stability margins and the stability judgments can be provided simultaneously. Moreover, a physics-informed metrics is introduced to reflect the accuracy of TSA, which can be obtained immediately without performing time-domain simulation. Finally, the effectiveness of the proposed method is verified on the IEEE 39-bus system.

Citation Download Citation

Yangqing Dan, Yingjing He, Hanze Zhou, Yuhong Zhu, and Yongzhi Zhou "Post-disturbance trajectory prediction and transient stability assessment based on a physics-informed machine learning algorithm", Proc. SPIE 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 127220R (18 July 2023); https://doi.org/10.1117/12.2680401

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