Recurrent Neural Networks with Linear Structures for Electricity Price Forecasting

2025-12-04

AI Summary

Inaccurate day-ahead electricity price forecasting hampers short-term decision-making and operational efficiency in power markets. Method: This paper proposes a hybrid modeling framework integrating linear structures with recurrent neural networks (RNNs), innovatively embedding interpretable expert models and Kalman filtering into the RNN architecture to jointly capture calendar effects, autoregressive dynamics, and multi-source influences—including load, renewable generation, and market mechanisms. The model supports high-dimensional, heterogeneous feature inputs and joint modeling of multi-source energy data. Contribution/Results: Evaluated on hourly data from Europe’s largest power market (2018–2025), the method achieves an average 12% improvement in forecasting accuracy over current state-of-the-art models. It delivers strong interpretability—through explicit incorporation of domain knowledge—and high robustness under varying market conditions. The approach thus provides reliable, actionable forecasts for short-term power market optimization.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We present a novel recurrent neural network architecture designed explicitly for day-ahead electricity price forecasting, aimed at improving short-term decision-making and operational management in energy systems. Our combined forecasting model embeds linear structures, such as expert models and Kalman filters, into recurrent networks, enabling efficient computation and enhanced interpretability. The design leverages the strengths of both linear and non-linear model structures, allowing it to capture all relevant stylised price characteristics in power markets, including calendar and autoregressive effects, as well as influences from load, renewable energy, and related fuel and carbon markets. For empirical testing, we use hourly data from the largest European electricity market spanning 2018 to 2025 in a comprehensive forecasting study, comparing our model against state-of-the-art approaches, particularly high-dimensional linear and neural network models. The proposed model achieves approximately 12% higher accuracy than leading benchmarks. We evaluate the contributions of the interpretable model components and conclude on the impact of combining linear and non-linear structures.

Problem

• Improves electricity price forecasting for energy system decisions.
• Combines linear and non-linear models for better accuracy.
• Enhances interpretability in forecasting using structured neural networks.

Innovation

• Combines linear expert models with recurrent neural networks
• Integrates Kalman filters for enhanced interpretability and efficiency
• Captures calendar, autoregressive, and market influences in electricity prices