Sparsity-exploiting Gaussian Process for Robust Transient Learning of Power System Dynamics
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909852269281280 |
|---|---|
| author | Gao, Tina Li, Shimiao Pileggi, Lawrence |
| author_facet | Gao, Tina Li, Shimiao Pileggi, Lawrence |
| contents | Advances in leveraging Gaussian processes (GP) have enabled learning and inferring dynamic grid behavior from scarce PMU measurements. However, real measurements can be corrupted by various random and targeted threats, leading to inaccurate and meaningless results. This paper develops robust transient learning to overcome this challenge by exploiting the sparse corruption patterns in the data flow. Specifically, we integrate sparse optimization with method of moments (MoM) to make learning robust to a sparse distribution of data corruptions; then, we optimize sparse weights to identify corrupted meter locations. To improve inference speed on large-scale systems, we further adopt K-medoid clustering of locations to develop dimension reduction (DR) and aggregate representation (AR) heuristics. Experimental results demonstrate robustness against random large errors, targeted false data injections, and local PMU clock drifts. On a 1354-bus system, inference turns out to be 18x faster using DR and 400x faster when further combined with AR heuristics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15150 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sparsity-exploiting Gaussian Process for Robust Transient Learning of Power System Dynamics Gao, Tina Li, Shimiao Pileggi, Lawrence Systems and Control Signal Processing Advances in leveraging Gaussian processes (GP) have enabled learning and inferring dynamic grid behavior from scarce PMU measurements. However, real measurements can be corrupted by various random and targeted threats, leading to inaccurate and meaningless results. This paper develops robust transient learning to overcome this challenge by exploiting the sparse corruption patterns in the data flow. Specifically, we integrate sparse optimization with method of moments (MoM) to make learning robust to a sparse distribution of data corruptions; then, we optimize sparse weights to identify corrupted meter locations. To improve inference speed on large-scale systems, we further adopt K-medoid clustering of locations to develop dimension reduction (DR) and aggregate representation (AR) heuristics. Experimental results demonstrate robustness against random large errors, targeted false data injections, and local PMU clock drifts. On a 1354-bus system, inference turns out to be 18x faster using DR and 400x faster when further combined with AR heuristics. |
| title | Sparsity-exploiting Gaussian Process for Robust Transient Learning of Power System Dynamics |
| topic | Systems and Control Signal Processing |
| url | https://arxiv.org/abs/2510.15150 |