HMM-Based Feature Extraction and Machine Learning Methods for Event Detection and Classification in Microgrids
Bibliographic record
Abstract
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
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".