Paper ID: 2408.05628
Forecasting Day-Ahead Electricity Prices in the Integrated Single Electricity Market: Addressing Volatility with Comparative Machine Learning Methods
Ben Harkin, Xueqin Liu
This paper undertakes a comprehensive investigation of electricity price forecasting methods, focused on the Irish Integrated Single Electricity Market, particularly on changes during recent periods of high volatility. The primary objective of this research is to evaluate and compare the performance of various forecasting models, ranging from traditional machine learning models to more complex neural networks, as well as the impact of different lengths of training periods. The performance metrics, mean absolute error, root mean square error, and relative mean absolute error, are utilized to assess and compare the accuracy of each model. A comprehensive set of input features was investigated and selected from data recorded between October 2018 and September 2022. The paper demonstrates that the daily EU Natural Gas price is a more useful feature for electricity price forecasting in Ireland than the daily Henry Hub Natural Gas price. This study also shows that the correlation of features to the day-ahead market price has changed in recent years. The price of natural gas on the day and the amount of wind energy on the grid that hour are significantly more important than any other features. More specifically speaking, the input fuel for electricity has become a more important driver of the price of it, than the total generation or demand. In addition, it can be seen that System Non-Synchronous Penetration (SNSP) is highly correlated with the day-ahead market price, and that renewables are pushing down the price of electricity.
Submitted: Aug 10, 2024