Explainable Bayesian Neural Network for Probabilistic Transient Stability Analysis Considering Wind Energy
- Resource Type
- Conference
- Authors
- Tan, Bendong; Zhao, Junbo; Su, Tong; Huang, Qiuhua; Zhang, Yingchen; Zhang, Hongming
- Source
- 2022 IEEE Power & Energy Society General Meeting (PESGM) Power & Energy Society General Meeting (PESGM), 2022 IEEE. :1-5 Jul, 2022
- Subject
- Engineering Profession
Power, Energy and Industry Applications
Renewable energy sources
Uncertainty
Power system stability
Probabilistic logic
Stability analysis
Numerical models
Bayes methods
Bayesian Neural Network
probabilistic transient stability assessment
Gradient Shap
model interpretability
- Language
- ISSN
- 1944-9933
While several data-driven models have been developed for transient stability assessment, how to consider the uncertainties from load and renewable generations and provide interpretation of data-driven assessment results are still open. This paper proposes an explainable Bayesian Neural Network (BNN) for probabilistic transient stability assessment (TSA). By extracting the uncertainties from loads and wind farms, the BNN model can make a reliable prediction and quantify the prediction uncertainties. We also develop the Gradient Shap algorithm to make the global and local explanations for the probabilistic TSA model, a significant advantage over existing black-box data-driven methods. Numerical results on the modified IEEE 39-bus system show that the proposed method outperforms the existing methods in terms of prediction accuracy and uncertainty quantification capabilities. The explainability of the proposed method allows system operators to design preventive controls for enhancing system stability.