Deep Learning Models Compared for Cross-Border Electricity Price Forecasting

Hadeer Elashhab, Sai Srijan Papineni, Marvin Dorn, Veit Hagenmeyer, Benjamin Sch\"afer· August 19, 2026 View original

Key takeaways

  • Standardized benchmarks are crucial for comparing electricity price forecasting models effectively.
  • N-HiTS and NBEATSx models show strong performance in low-data electricity market forecasting.
  • Transformer models can be accurate but demand more adaptation and tuning for optimal results.
  • Feature selection and hyperparameter tuning significantly influence forecasting model accuracy.

Who benefits

EnergyUtilitiesFinanceLogisticsManufacturing

Summary

This study evaluates six deep learning models for electricity price forecasting across multiple market settings, focusing on generalization and performance in low-data scenarios. It establishes a reproducible framework for consistent model evaluation using public electricity market data.

Researchers have conducted a comparative study on deep learning models for electricity price forecasting, specifically addressing the challenge of cross-border markets and limited data availability. The work aims to create a standardized, reproducible framework for evaluating forecasting models, which has been lacking in the field due to varied datasets and metrics used in previous studies. The study tested six different deep learning architectures, including state-space, MLP, RNN, and Transformer-based models, emphasizing their ability to generalize across different market conditions. They simulated low-data environments using zero-shot, one-shot, and few-shot learning approaches. The findings indicate that N-HiTS and NBEATSx models perform strongly in data-scarce situations, while Transformer models can achieve similar accuracy but often require more extensive tuning.

Why it matters

Professionals in energy trading, grid management, and financial analysis need accurate electricity price forecasts to optimize operations, manage risk, and make informed investment decisions. This research provides insights into reliable deep learning models for these critical predictions, especially in complex cross-border markets.

How to implement this in your domain

  1. 1Evaluate N-HiTS and NBEATSx models for electricity price forecasting in data-limited or new market contexts.
  2. 2Develop a standardized data pipeline for electricity market data, including calendar, historical price, and market-derived features.
  3. 3Implement a reproducible framework for comparing forecasting models, ensuring consistent metrics and datasets.
  4. 4Investigate the impact of careful feature selection and hyperparameter tuning on model performance in your specific market.
  5. 5Consider zero-shot, one-shot, or few-shot learning techniques when expanding forecasting to new regions with minimal historical data.

Original post by Hadeer Elashhab, Sai Srijan Papineni, Marvin Dorn, Veit Hagenmeyer, Benjamin Sch\"afer

"arXiv:2608.17091v1 Announce Type: new Abstract: While publicly available electricity market data presents a valuable resource for forecasting research, the field lacks established benchmark datasets for standardized comparison. As a result, many studies have relied on different d…"

View on X

Originally posted by Hadeer Elashhab, Sai Srijan Papineni, Marvin Dorn, Veit Hagenmeyer, Benjamin Sch\"afer on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Research