Hybrid Kolmogorov-Arnold Network and XGBoost Framework for Week-Ahead Price Forecasting in Australia's National Electricity Market

2026-05-21

AI Summary

This study addresses the challenge of day-ahead electricity price forecasting in Australia’s National Electricity Market (NEM), where high renewable energy penetration introduces significant volatility and complexity. To tackle this, the authors propose a novel hybrid learning framework that integrates Kolmogorov–Arnold Networks (KANs) with XGBoost. This approach uniquely combines KAN’s capacity for global nonlinear modeling with XGBoost’s robustness to local fluctuations, effectively capturing both long-term dependencies and short-term abrupt changes in price dynamics. Evaluated on real-world NEM data using an expanding-window strategy, the proposed model substantially outperforms established benchmarks—including SARIMAX, LSTM, standalone KAN, and XGBoost—achieving approximately a 12% reduction in mean absolute error (MAE) compared to XGBoost and over 50% improvement relative to naive baselines, thereby demonstrating its superior predictive accuracy and methodological innovation.

Abstract

Accurate electricity price forecasting (EPF) is essential for market participants to support operational planning and risk management, yet remains challenging due to strong volatility, nonlinear dynamics, and frequent extreme price spikes. These challenges are particularly pronounced in the Australian National Electricity Market (NEM), where high renewable penetration further increases uncertainty. This paper investigates week-ahead electricity price forecasting and proposes a hybrid KAN+XGBoost framework that integrates Kolmogorov-Arnold Networks (KAN) with tree-based learning. The proposed approach combines the global nonlinear representation capability of KAN with the local robustness of XGBoost to capture both long-term dependencies and short-term price fluctuations. Experiments are conducted on real-world NEM data using an expanding window evaluation strategy. The results demonstrate that the proposed model outperforms benchmark methods, including SARIMAX, Long Short-Term Memory (LSTM), standalone KAN, and XGBoost, reducing MAE by approximately 12% compared to XGBoost and by over 50% compared to a naive baseline. The results suggest that hybrid learning strategies provide an effective and robust solution for electricity price forecasting in highly dynamic electricity markets.

Problem

• electricity price forecasting
• Australian National Electricity Market
• price volatility
• renewable energy integration
• extreme price spikes

Innovation

• Kolmogorov-Arnold Network
• XGBoost
• electricity price forecasting
• hybrid model
• renewable energy integration