Short-term electricity load forecasting with multi-frequency reconstruction diffusion

2026-01-10

arXiv.org

AI Summary

Short-term electric load forecasting faces significant challenges due to the strong nonlinearity and high volatility of load data, which existing methods struggle to model effectively. This work proposes the Multi-Frequency Reconstruction Diffusion (MFRD) model, the first to apply diffusion models to this task. MFRD decomposes and reconstructs load sequences across multiple frequency bands and integrates LSTM and Transformer architectures within both the forward noising and reverse denoising processes to enhance denoising efficiency and prediction accuracy. By innovatively combining multi-frequency signal analysis with diffusion mechanisms, the model substantially improves its capacity to capture complex load dynamics. Experiments on two real-world datasets—AEMO and ISO-NE—demonstrate that MFRD consistently outperforms state-of-the-art methods, confirming its effectiveness and strong generalization capability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Diffusion models have emerged as a powerful method in various applications. However, their application to Short-Term Electricity Load Forecasting (STELF) -- a typical scenario in energy systems -- remains largely unexplored. Considering the nonlinear and fluctuating characteristics of the load data, effectively utilizing the powerful modeling capabilities of diffusion models to enhance STELF accuracy remains a challenge. This paper proposes a novel diffusion model with multi-frequency reconstruction for STELF, referred to as the Multi-Frequency-Reconstruction-based Diffusion (MFRD) model. The MFRD model achieves accurate load forecasting through four key steps: (1) The original data is combined with the decomposed multi-frequency modes to form a new data representation; (2) The diffusion model adds noise to the new data, effectively reducing and weakening the noise in the original data; (3) The reverse process adopts a denoising network that combines Long Short-Term Memory (LSTM) and Transformer to enhance noise removal; and (4) The inference process generates the final predictions based on the trained denoising network. To validate the effectiveness of the MFRD model, we conducted experiments on two data platforms: Australian Energy Market Operator (AEMO) and Independent System Operator of New England (ISO-NE). The experimental results show that our model consistently outperforms the compared models.

Problem

• Short-Term Electricity Load Forecasting
• Diffusion Models
• Nonlinear Characteristics
• Load Forecasting Accuracy
• Multi-frequency Reconstruction

Innovation

• diffusion model
• multi-frequency reconstruction
• short-term load forecasting
• LSTM-Transformer
• denoising network