Multi-Horizon Electricity Price Forecasting with Deep Learning in the Australian National Electricity Market

2026-02-01

AI Summary

This study addresses the significant challenges in multi-day electricity price forecasting—namely high volatility, spike-heavy distributions, and regime shifts—by systematically applying state-of-the-art deep learning time series models, including Transformer and N-BEATS, to the five regions of the Australian National Electricity Market. For the first time, hour-level evaluation is introduced to uncover diurnal patterns in prediction errors. Experimental results demonstrate that standard deep learning architectures generally outperform others across most regions, while advanced models exhibit greater robustness over longer forecast horizons. Notably, prediction errors markedly increase during evening ramp-up periods and intervals with negative prices, highlighting critical modeling difficulties inherent in these complex market dynamics.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: State Estimation

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
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate electricity price forecasting (EPF) is essential for operational planning, trading, and flexible asset scheduling in liberalised power systems, yet remains challenging due to volatility, heavy-tailed spikes, and frequent regime shifts. While deep learning (DL) has been increasingly adopted in EPF to capture complex and nonlinear price dynamics, several important gaps persist: (i) limited attention to multi-day horizons beyond day-ahead forecasting, (ii) insufficient exploration of state-of-the-art (SOTA) time series DL models, and (iii) a predominant reliance on aggregated horizon-level evaluation that obscures time-of-day forecasting variation. To address these gaps, we propose a novel EPF framework that extends the forecast horizon to multi-day-ahead by systematically building forecasting models that leverage benchmarked SOTA time series DL models. We conduct a comprehensive evaluation to analyse time-of-day forecasting performance by integrating model assessment at intraday interval levels across all five regions in the Australian National Electricity Market (NEM). The results show that no single model consistently dominates across regions, metrics, and horizons. Overall, standard DL models deliver superior performance in most regions, while SOTA time series DL models demonstrate greater robustness to forecast horizon extension. Intraday interval-level evaluation reveals pronounced diurnal error patterns, indicating that absolute errors peak during the evening ramp, relative errors inflate during midday negative-price regimes, and directional accuracy degrades during periods of frequent trend changes. These findings suggest that future research on DL-based EPF can benefit from enriched feature representations and modelling strategies that enhance longer-term forecasting robustness while maintaining sensitivity to intraday volatility and structural price dynamics.

Problem

• electricity price forecasting
• multi-horizon forecasting
• deep learning
• time series
• intraday variability

Innovation

• multi-horizon forecasting
• deep learning
• time series models
• intraday evaluation
• electricity price forecasting