Research on the Interpretability Analysis Method of Transient Stability Assessment in Power Systems Based on Deep Learning

DOI

10.2991/978-94-6463-490-7_44How to use a DOI?

Keywords

Power System Transient Stability; Deep Learning; Interpretability

Abstract

In this paper, application of deep learning techniques and their interpretability analysis are explored in transient stability assessment of power systems. With the continuous expansion and increasing complexity of power system scales, traditional stability assessment methods are facing new challenges. Due to their outstanding data processing and learning capabilities, deep learning techniques are able to provide new insights for improving the accuracy and efficiency of transient stability assessment. By elaborating on the application process of deep learning models in power system stability assessment, which includes model selection, training and optimization strategies, this study demonstrates the advantages of deep learning in handling complex system data. Furthermore, this work emphasizes the importance of model interpretability, analyzes several mainstream interpretability methods, and explores their potential applications in power system stability assessment, highlighting the crucial role of enhancing model transparency in understanding prediction results, boosting decision-makers’ confidence, and optimizing system design. Finally, a summary of the research findings on deep learning-based transient stability assessment methods for power systems is presented, and future research directions are outlined, indicating that integrating deep learning and interpretability analysis is able to support reasonable decision making for the safe operation of power systems.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Qinfeng Ma
AU  - Qingqing Zhang
AU  - Mingshun Liu
AU  - Jie Zhang
AU  - Yihua Zhu
AU  - Zhuohang Liang
AU  - Su An
AU  - Qingxin Pu
AU  - Jiang Dai
PY  - 2024
DA  - 2024/08/31
TI  - Research on the Interpretability Analysis Method of Transient Stability Assessment in Power Systems Based on Deep Learning
BT  - Proceedings of the 2024 3rd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2024)
PB  - Atlantis Press
SP  - 398
EP  - 406
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-490-7_44
DO  - 10.2991/978-94-6463-490-7_44
ID  - Ma2024
ER  -