EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning the Grid: Transformer Architectures for Electricity Price Forecasting in the Australian National Market

Mark Sinclair, Andrew J. Shepley, Farshid Hajati

Applied Sciences · 21.12.2025 · 16 (1) · 75

DOI: 10.3390/app16010075 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 21.12.2025. Verfasst von Mark Sinclair und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing adoption of highly variable renewable energy has introduced unprecedented volatility into the National Electricity Market (NEM), rendering traditional linear price forecasting models insufficient. The Australian Energy Market Operator (AEMO) spot price forecasts often struggle during periods of volatile demand, renewable variability, and strategic rebidding. This study evaluates whether transformer architectures can improve intraday NEM price forecasting. Using 34 months of market data and weather conditions, several transformer variants, including encoder–decoder, decoder-only, and encoder-only, were compared against the AEMO’s operational forecast, a two-layer LSTM baseline, the Temporal Fusion Transformer, PatchTST, and TimesFM. The decoder-only transformer achieved the best accuracy across the 2–16 h horizons in NSW, with nMAPE values of 33.6–39.2%, outperforming both AEMO and all baseline models. Retraining in Victoria and Queensland produced similarly strong results, demonstrating robust regional generalisation. A feature importance analysis showed that future-facing predispatch and forecast covariates dominate model importance, explaining why a decoder-only transformer variant performed so competitively. While magnitude estimation for extreme price spikes remains challenging, the transformer models demonstrated superior capability in delivering statistically significant improvements in forecast accuracy. An API providing real-time forecasts using the small encoder–decoder transformer model is available.

Zitieren

APA

Sinclair, M., Shepley, A. J., & Hajati, F. (2025). Learning the Grid: Transformer Architectures for Electricity Price Forecasting in the Australian National Market. Applied Sciences, 16(1), 75. https://doi.org/10.3390/app16010075

Vancouver

Sinclair M, Shepley AJ, Hajati F. Learning the Grid: Transformer Architectures for Electricity Price Forecasting in the Australian National Market. Applied Sciences. 2025;16(1):75. doi:10.3390/app16010075

BibTeX
@article{Sinclair2025,
  author = {Sinclair, Mark and Shepley, Andrew J. and Hajati, Farshid},
  title = {Learning the Grid: Transformer Architectures for Electricity Price Forecasting in the Australian National Market},
  journal = {Applied Sciences},
  year = {2025},
  volume = {16},
  number = {1},
  pages = {75},
  doi = {10.3390/app16010075}
}
Kostenlos starten →