Data-driven Calibration Sample Selection and Forecast Combination in Electricity Price Forecasting: An Application of the ARHNN Method

2025-10-16

AI Summary

To address the insufficient joint optimization of calibration sample selection and forecast combination in electricity price forecasting, this paper proposes a data-driven framework based on Autoregressive Hybrid Nearest Neighbor (ARHNN), applied to long-horizon price forecasting in the German, Spanish, and New England markets. ARHNN is innovatively introduced to this domain, and two lightweight variants are designed—reducing computational time by over 50% with only marginal accuracy degradation. The framework integrates dynamic calibration sample selection with multi-model forecast combination, achieving up to 10% higher accuracy than state-of-the-art benchmarks. In battery energy storage arbitrage trading simulations, it attains 80% of the theoretical maximum profit, demonstrating its strong predictive accuracy, low computational complexity, and practical commercial viability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization

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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Calibration sample selection and forecast combination are two simple yet powerful tools used in forecasting. They can be combined with a variety of models to significantly improve prediction accuracy, at the same time offering easy implementation and low computational complexity. While their effectiveness has been repeatedly confirmed in prior scientific literature, the topic is still underexplored in the field of electricity price forecasting. In this research article we apply the Autoregressive Hybrid Nearest Neighbors (ARHNN) method to three long-term time series describing the German, Spanish and New England electricity markets. We show that it outperforms popular literature benchmarks in terms of forecast accuracy by up to 10%. We also propose two simplified variants of the method, granting a vast decrease in computation time with only minor loss of prediction accuracy. Finally, we compare the forecasts' performance in a battery storage system trading case study. We find that using a forecast-driven strategy can achieve up to 80% of theoretical maximum profits while trading, demonstrating business value in practical applications.

Problem

• Selecting optimal calibration samples for electricity price forecasting
• Combining forecasts to improve prediction accuracy in energy markets
• Applying ARHNN method to reduce computational complexity while maintaining accuracy

Innovation

• ARHNN method for electricity price forecasting
• Two simplified variants reduce computation time
• Data-driven calibration and forecast combination