Multi-Scale Temporal Analysis for Failure Prediction in Energy Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909377848410112 |
|---|---|
| author | Le, Anh Huynh, Phat K. Yadav, Om P. Le, Chau Pirim, Harun Le, Trung Q. |
| author_facet | Le, Anh Huynh, Phat K. Yadav, Om P. Le, Chau Pirim, Harun Le, Trung Q. |
| contents | Many existing models struggle to predict nonlinear behavior during extreme weather conditions. This study proposes a multi-scale temporal analysis for failure prediction in energy systems using PMU data. The model integrates multi-scale analysis with machine learning to capture both short-term and long-term behavior. PMU data lacks labeled states despite logged failure records, making it difficult to distinguish between normal and disturbance conditions. We address this through: (1) Extracting domain features from PMU time series data; (2) Applying multi-scale windows (30s, 60s, 180s) for pattern detection; (3) Using Recursive Feature Elimination to identify key features; (4) Training multiple machine learning models. Key contributions: Identifying significant features across multi-scale windows; Demonstrating LightGBM's superior performance (0.896 precision); Showing multi-scale analysis outperforms single-window models (0.841). Our work focuses on weather-related failures, with plans to extend to equipment failure and lightning events. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_02857 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Scale Temporal Analysis for Failure Prediction in Energy Systems Le, Anh Huynh, Phat K. Yadav, Om P. Le, Chau Pirim, Harun Le, Trung Q. Signal Processing Many existing models struggle to predict nonlinear behavior during extreme weather conditions. This study proposes a multi-scale temporal analysis for failure prediction in energy systems using PMU data. The model integrates multi-scale analysis with machine learning to capture both short-term and long-term behavior. PMU data lacks labeled states despite logged failure records, making it difficult to distinguish between normal and disturbance conditions. We address this through: (1) Extracting domain features from PMU time series data; (2) Applying multi-scale windows (30s, 60s, 180s) for pattern detection; (3) Using Recursive Feature Elimination to identify key features; (4) Training multiple machine learning models. Key contributions: Identifying significant features across multi-scale windows; Demonstrating LightGBM's superior performance (0.896 precision); Showing multi-scale analysis outperforms single-window models (0.841). Our work focuses on weather-related failures, with plans to extend to equipment failure and lightning events. |
| title | Multi-Scale Temporal Analysis for Failure Prediction in Energy Systems |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2411.02857 |