Machine Learning Models and Intra-Daily Market Information for the Prediction of Italian Electricity Prices
In this paper we assess how intra-day electricity prices can improve the prediction of zonal day-ahead wholesale electricity prices in Italy. We consider linear autoregressive models with exogenous variables (ARX) with and without interactions among predictors, and non-parametric models taken from t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Forecasting |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-9394/5/1/3 |
| _version_ | 1797611671372431360 |
|---|---|
| author | Silvia Golia Luigi Grossi Matteo Pelagatti |
| author_facet | Silvia Golia Luigi Grossi Matteo Pelagatti |
| author_sort | Silvia Golia |
| collection | DOAJ |
| description | In this paper we assess how intra-day electricity prices can improve the prediction of zonal day-ahead wholesale electricity prices in Italy. We consider linear autoregressive models with exogenous variables (ARX) with and without interactions among predictors, and non-parametric models taken from the machine learning literature. In particular, we implement Random Forests and support vector machines, which should automatically capture the relevant interactions among predictors. Given the large number of predictors, ARX models are also estimated using LASSO regularization, which improves predictions when regressors are many and selects the important variables. In addition to zonal intra-day prices, among the predictors we include also the official demand forecasts and wind generation expectations. Our results show that the prediction performance of the simple ARX model is mostly superior to those of machine learning models. The analysis of the relevance of exogenous variables, using variable importance measures, reveals that intra-day market information successfully contributes to the forecasting performance, although the impact differs among the estimated models. |
| first_indexed | 2024-03-11T06:32:02Z |
| format | Article |
| id | doaj.art-6cbe29ffd59d45ba8bd2339a87c4aa4c |
| institution | Directory Open Access Journal |
| issn | 2571-9394 |
| language | English |
| last_indexed | 2024-03-11T06:32:02Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forecasting |
| spelling | doaj.art-6cbe29ffd59d45ba8bd2339a87c4aa4c2023-11-17T11:08:13ZengMDPI AGForecasting2571-93942022-12-01518110110.3390/forecast5010003Machine Learning Models and Intra-Daily Market Information for the Prediction of Italian Electricity PricesSilvia Golia0Luigi Grossi1Matteo Pelagatti2Department of Economics and Management, University of Brescia, 25122 Brescia, ItalyDepartment of Statistical Sciences, University of Padova, 35121 Padova, ItalyDepartment of Economics, Management and Statistics, University of Milano-Bicocca, 20126 Milano, ItalyIn this paper we assess how intra-day electricity prices can improve the prediction of zonal day-ahead wholesale electricity prices in Italy. We consider linear autoregressive models with exogenous variables (ARX) with and without interactions among predictors, and non-parametric models taken from the machine learning literature. In particular, we implement Random Forests and support vector machines, which should automatically capture the relevant interactions among predictors. Given the large number of predictors, ARX models are also estimated using LASSO regularization, which improves predictions when regressors are many and selects the important variables. In addition to zonal intra-day prices, among the predictors we include also the official demand forecasts and wind generation expectations. Our results show that the prediction performance of the simple ARX model is mostly superior to those of machine learning models. The analysis of the relevance of exogenous variables, using variable importance measures, reveals that intra-day market information successfully contributes to the forecasting performance, although the impact differs among the estimated models.https://www.mdpi.com/2571-9394/5/1/3electricity spot pricesforecastingintra-day electricity pricesrandom forestssupport vector machinesvariable importance |
| spellingShingle | Silvia Golia Luigi Grossi Matteo Pelagatti Machine Learning Models and Intra-Daily Market Information for the Prediction of Italian Electricity Prices Forecasting electricity spot prices forecasting intra-day electricity prices random forests support vector machines variable importance |
| title | Machine Learning Models and Intra-Daily Market Information for the Prediction of Italian Electricity Prices |
| title_full | Machine Learning Models and Intra-Daily Market Information for the Prediction of Italian Electricity Prices |
| title_fullStr | Machine Learning Models and Intra-Daily Market Information for the Prediction of Italian Electricity Prices |
| title_full_unstemmed | Machine Learning Models and Intra-Daily Market Information for the Prediction of Italian Electricity Prices |
| title_short | Machine Learning Models and Intra-Daily Market Information for the Prediction of Italian Electricity Prices |
| title_sort | machine learning models and intra daily market information for the prediction of italian electricity prices |
| topic | electricity spot prices forecasting intra-day electricity prices random forests support vector machines variable importance |
| url | https://www.mdpi.com/2571-9394/5/1/3 |
| work_keys_str_mv | AT silviagolia machinelearningmodelsandintradailymarketinformationforthepredictionofitalianelectricityprices AT luigigrossi machinelearningmodelsandintradailymarketinformationforthepredictionofitalianelectricityprices AT matteopelagatti machinelearningmodelsandintradailymarketinformationforthepredictionofitalianelectricityprices |