{"title":"Forecasting next-day electricity prices by a neural network approach","authors":"D. Menniti, N. Scordino, N. Sorrentino","doi":"10.1109/EEM.2011.5953010","DOIUrl":null,"url":null,"abstract":"Forecasting short-term electricity market prices has been the focus of several studies in recent years. Although various approaches have been examined, achieving sufficiently low forecasting errors has not been always possible. However, certain applications, such as demand-side management, do not require exact values for future prices but utilize averages values as the basis for making short-term scheduling decisions. With the aim of enhancing the accuracy of the next-day electricity price forecasting, this paper proposes an approach to forecast the day-ahead electricity prices by means of n Artificial Neural Networks (ANNs), based on the estimation of the mean prices of n blocks of hours, with n identified according to the values of correlation factors computed on the basis of field records of the Italian electricity market. Simulation results show that forecasting next-day prices on an hourly basis induces to an error which results worse than the one made when average prices are forecasted according to groups of hours.","PeriodicalId":143375,"journal":{"name":"2011 8th International Conference on the European Energy Market (EEM)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 8th International Conference on the European Energy Market (EEM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EEM.2011.5953010","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Forecasting short-term electricity market prices has been the focus of several studies in recent years. Although various approaches have been examined, achieving sufficiently low forecasting errors has not been always possible. However, certain applications, such as demand-side management, do not require exact values for future prices but utilize averages values as the basis for making short-term scheduling decisions. With the aim of enhancing the accuracy of the next-day electricity price forecasting, this paper proposes an approach to forecast the day-ahead electricity prices by means of n Artificial Neural Networks (ANNs), based on the estimation of the mean prices of n blocks of hours, with n identified according to the values of correlation factors computed on the basis of field records of the Italian electricity market. Simulation results show that forecasting next-day prices on an hourly basis induces to an error which results worse than the one made when average prices are forecasted according to groups of hours.