Electricity prices can fluctuate as much as 20 times more than stock markets daily, with hourly volatility exceeding 1,000%. Various factors, including changes in energy demand, renewable energy production, weather, and market disruptions, drive this volatility. Businesses and consumers rely on forecasts to navigate the market, but traditional models struggle to handle extreme price swings.
To address this, researchers from the European Commission's Joint Research Centre (JRC) have developed a new method to improve price prediction accuracy. The approach uses a filtering technique to refine historical price data before applying forecasting models. It leverages advanced statistical methods to detect and adjust for extreme price fluctuations, while preserving key market trends.
This method applies robust statistical techniques within a moving window framework, systematically cleaning input data for forecasting models.
The method's effectiveness has been validated using advanced statistical and deep learning models across six energy markets: the Nordic European electricity market (Nord Pool, NP), the Pennsylvania-New Jersey-Maryland market (PJM) in the United States, the day-ahead electricity markets in Belgium (EPEX-BE), France (EPEX-FR), and Germany (EPEX-DE), and the Northern Italian electricity market (IT-NORTH, ITN).
Comparing the results with unfiltered data, the new method showed improvements in forecast accuracy, with some models achieving gains of up to 4%.
“This improvement emerges not only in the value of the accuracy metrics, but also in the outcome of the statistical tests,” the academics explained. “The proposed filtering strategy exhibits reasonable and affordable computational requirements, making it suitable for daily recalibration and practical applications in a real-world business context.”
They introduced the new method in “Enhancing electricity price forecasting accuracy: A novel filtering strategy for improved out-of-sample predictions,” which was recently published in Applied Energy.
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: editors@pv-magazine.com.
By submitting this form you agree to pv magazine using your data for the purposes of publishing your comment.
Your personal data will only be disclosed or otherwise transmitted to third parties for the purposes of spam filtering or if this is necessary for technical maintenance of the website. Any other transfer to third parties will not take place unless this is justified on the basis of applicable data protection regulations or if pv magazine is legally obliged to do so.
You may revoke this consent at any time with effect for the future, in which case your personal data will be deleted immediately. Otherwise, your data will be deleted if pv magazine has processed your request or the purpose of data storage is fulfilled.
Further information on data privacy can be found in our Data Protection Policy.