A Lightweight Multi-View Approach to Short-Term Load Forecasting

TL;DR

This paper introduces a lightweight, multi-view method for short-term load forecasting that uses embeddings and scaled time inputs to improve efficiency, robustness, and interpretability over complex models.

Contribution

It presents a novel multi-view approach with embedding dropout and scaled time-range inputs, achieving competitive results with fewer parameters and better robustness.

Findings

Achieves competitive accuracy with fewer parameters.

Demonstrates robustness on noisy and sparse data.

Provides interpretability of feature contributions.

Abstract

Time series forecasting is a critical task across domains such as energy, finance, and meteorology, where accurate predictions enable informed decision-making. While transformer-based and large-parameter models have recently achieved state-of-the-art results, their complexity can lead to overfitting and unstable forecasts, especially when older data points become less relevant. In this paper, we propose a lightweight multi-view approach to short-term load forecasting that leverages single-value embeddings and a scaled time-range input to capture temporally relevant features efficiently. We introduce an embedding dropout mechanism to prevent over-reliance on specific features and enhance interpretability. Our method achieves competitive performance with significantly fewer parameters, demonstrating robustness across multiple datasets, including scenarios with noisy or sparse data, and provides insights into the contributions of individual features to the forecast.