HOPS: High-order Polynomials with Self-supervised Dimension Reduction for Load Forecasting

TL;DR

This paper introduces HOPS, a novel load forecasting method using high-order polynomials combined with self-supervised dimension reduction, addressing challenges like high dimensionality and overfitting to improve accuracy and efficiency.

Contribution

The paper proposes a new polynomial-based load forecasting model with low-rank approximation and self-supervised dimension reduction, enhancing accuracy and computational efficiency.

Findings

HOPS outperforms several competitive models in accuracy.

The approach reduces the number of input variables needed.

It achieves better forecasts with limited computational resources.

Abstract

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.