Early Detection and Classification of Hidden Contingencies in Modern Power Systems: A Learning-based Stochastic Hybrid System Approach

TL;DR

The paper tackles hidden contingencies in modern power systems by proposing a learning-based stochastic hybrid system (LSHS) that classifies contingencies into physical, control-network, and sensing/monitoring categories and detects them rapidly using a closed-loop SHS with observer error dynamics. The method combines model-based SHS representations with ML classifiers trained offline on SHS outputs, achieving fast online contingency identification with high accuracy, aided by eigenvalue-anomaly signatures from $\Lambda_{1,i}$ and $\Lambda_{2,i}$. Simulations on an enhanced IEEE-33 bus demonstrate detection within $\tau_0$-scale windows (e.g., $0.02$ s) and accuracy above $98\%$, significantly outperforming prior SHS-only approaches. The approach reduces the search space for contingencies, improves robustness to unseen scenarios, and offers practical benefits for reliability and resilience of power grids under cyber-physical stress.

Abstract

This paper introduces a novel learning-based Stochastic Hybrid System (LSHS) approach for detecting and classifying various contingencies in modern power systems. Specifically, the proposed method is capable of identifying hidden contingencies that cannot be captured by existing sensing and monitoring systems, such as failures in protection systems or line outages in distribution networks. The LSHS approach detects contingencies by analyzing system outputs and behaviors. It then categorizes them based on their impact on the SHS model into physical, control network, and measurement contingencies. The stochastic hybrid system (SHS) model is further extended into an advanced closed-loop framework incorporating both system dynamics and observer-based state estimation error dynamics. Machine learning methods within the LSHS framework are employed for contingency classification and rapid detection. The practicality and effectiveness of the proposed methodology are validated through simulations on an enhanced IEEE-33 bus system. The results demonstrate that the LSHS framework significantly improves the accuracy and speed of contingency detection compared to state-of-the-art methods, offering a promising solution for enhancing power system contingency detection.

Figures (10)

• Figure 1: The time-splitting framework of the RSLS model.
• Figure 2: Feedback control using observer's state estimation lin2007robust.
• Figure 3: LSHS-based contingency detection and classification framework.
• Figure 4: One line diagram of enhanced IEEE-33 bus system dolatabadi2020enhanced
• Figure 5: Performance Comparison of KNN, SVM, and LSTM Under Varying Noise Levels ($\sigma$).