HMM-Based Feature Extraction and Machine Learning Methods for Event Detection and Classification in Microgrids

The increasing penetration of inverter-based distributed generation (DG) into power grids improves access to electricity and provides a significant possibility for decarbonization. However, this can result in unexpected events and protection challenges that can threaten the resilience and stability of the entire power grid. One approach to address protection challenges is to detect events accurately. This study proposes a new feature extraction approach by the HMM to extract informative features from event signals. These extracted features are used by XGBoost to detect and classify the type and phase of a wide range of events, including both fault and non-fault events. The case study utilizes various simulated events of the IEEE 34-bus system. Furthermore, the effectiveness of the proposed model is validated using real-world experimental data obtained from a relay tester device. The performance of the proposed approach is evaluated using various metrics under realistic scenarios, including an imbalanced dataset and the presence of different levels of noise and missing data. The results demonstrate that combining HMM for feature extraction with XGBoost as a classifier offers an interpretable and robust approach, achieving reliable performance with high accuracy as well as timely detection and classification of event types and phases compared to state-of-the-art techniques. All codes are available at: https://github.com/hassan-sam-daliri/HMMXGB.git