A Market-Rule-Informed Neural Network for Efficient Imbalance Electricity Price Forecasting

2026-05-09

AI Summary

Real-time imbalance price forecasting is hindered by nonlinear market rules, heterogeneous input signals, and missing data, which compromise the accuracy and efficiency of energy trading systems. This work proposes a neural network framework that integrates market rule priors, explicitly embedding the electricity pricing mechanism into the model’s latent space for the first time. By incorporating domain-specific constraints while preserving original signal information, the approach achieves high prediction accuracy with fewer parameters and lower computational overhead. It also demonstrates enhanced robustness under missing-data conditions. Experimental results show that, across various forecasting horizons and input lengths, the proposed model consistently outperforms or matches general-purpose deep learning baselines, confirming the efficacy of rule-guided neural modeling in industrial energy trading applications.

Abstract

Accurate and efficient imbalance electricity price forecasting is critical for industrial energy trading systems, especially as battery assets and automated bidding pipelines increasingly participate in balancing markets. However, real-time forecasting is complicated by nonlinear market-rule-based price formation, heterogeneous input signals, and incomplete data availability caused by communication delays, publication lags, and measurement outages. This paper proposes a market-rule-informed neural forecasting framework that embeds imbalance price formation rules into the latent space of an expressive neural network. The proposed framework preserves raw signal information while exploiting transparent market-rule priors. We further analyze operational robustness by removing price-component information and characterize how forecasting performance scales with input length and forecasting horizon. Experimental results show that the proposed model achieves competitive forecasting performance with substantially fewer trainable parameters and shorter training time than generic deep learning baselines. Experimental results show that the proposed model achieves competitive forecasting performance with substantially fewer trainable parameters and shorter training time than generic deep learning baselines, demonstrating that market-rule priors and expressive neural networks should be jointly used for accurate and computationally sustainable forecasting in industrial energy trading applications. The implementation is publicly available at https://runyao-yu.github.io/MRINN/.

Problem

• imbalance electricity price forecasting
• market rules
• real-time forecasting
• data incompleteness
• nonlinear price formation

Innovation

• market-rule-informed neural network
• imbalance electricity price forecasting
• rule-based priors
• efficient deep learning
• energy trading systems