HOPS: High-order Polynomials with Self-supervised Dimension Reduction for Load Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909536037634048 |
|---|---|
| author | Song, Pengyang Feng, Han Shukla, Shreyashi Wang, Jue Hong, Tao |
| author_facet | Song, Pengyang Feng, Han Shukla, Shreyashi Wang, Jue Hong, Tao |
| contents | Load forecasting is a fundamental task in smart grid. Many techniques have been applied to developing load forecasting models. Due to the challenges such as the Curse of Dimensionality, overfitting, and limited computing resources, multivariate higher-order polynomial models have received limited attention in load forecasting, despite their desirable mathematical foundations and optimization properties. In this paper, we propose low rank approximation and self-supervised dimension reduction to address the aforementioned issues. To further improve computational efficiency, we also utilize a fast Conjugate Gradient based algorithm for the proposed polynomial models. Based on the load datasets from the ISO New England, the proposed method high-order polynomials with self-supervised dimension reduction (HOPS) demonstrates higher forecasting accuracy over several competitive models. Additionally, experimental results indicate that our approach alleviates redundant variable construction, achieving better forecasts with fewer input variables. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_10637 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HOPS: High-order Polynomials with Self-supervised Dimension Reduction for Load Forecasting Song, Pengyang Feng, Han Shukla, Shreyashi Wang, Jue Hong, Tao Machine Learning Systems and Control Load forecasting is a fundamental task in smart grid. Many techniques have been applied to developing load forecasting models. Due to the challenges such as the Curse of Dimensionality, overfitting, and limited computing resources, multivariate higher-order polynomial models have received limited attention in load forecasting, despite their desirable mathematical foundations and optimization properties. In this paper, we propose low rank approximation and self-supervised dimension reduction to address the aforementioned issues. To further improve computational efficiency, we also utilize a fast Conjugate Gradient based algorithm for the proposed polynomial models. Based on the load datasets from the ISO New England, the proposed method high-order polynomials with self-supervised dimension reduction (HOPS) demonstrates higher forecasting accuracy over several competitive models. Additionally, experimental results indicate that our approach alleviates redundant variable construction, achieving better forecasts with fewer input variables. |
| title | HOPS: High-order Polynomials with Self-supervised Dimension Reduction for Load Forecasting |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2501.10637 |