Home // ENERGY 2024, The Fourteenth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies // View article

Day-ahead Electricity Price Forecasting of Elspot Markets in Norway

Authors:
Markus Wiik Jensen
Huamin Ren
Andrii Shalaginov

Keywords: Electricity Price Forecasting, Elspot prices, XGBoost, LSTM

Abstract:
Forecasting day-ahead electricity prices from the Elspot market holds essential importance for various stakeholders, primarily electricity producers. These producers depend on precise price forecasts when placing supply bids and fine-tuning their dispatch schedules. This paper delves into this vital area, emphasizing day-ahead Electricity Price Forecasting (EPF). Following a comprehensive assessment of EPF techniques, we have experimented with three methods: a heuristic approach, Extreme Gradient Boosting (XGBoost), and the Long Short-Term Memory (LSTM) network. We have carried out unified comparisons among these three approaches across all six Elspot markets of Norway. Our results indicate that the LSTM outperform the other models in three of the six zones, which indicates the superior efficacy of the LSTM model. We have also noticed the impact of data variance on model performance, and hence improving model generalization will be our subsequent research endeavors.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2024

Publication date: March 10, 2024

Published in: conference

ISSN: 2308-412X

ISBN: 978-1-68558-139-8

Location: Athens, Greece

Dates: from March 10, 2024 to March 14, 2024