{"title":"Multi-step ahead wind power forecasting for Ireland using an ensemble of VMD-ELM models","authors":"J. M. González-Sopeña, V. Pakrashi, Bidisha Ghosh","doi":"10.1109/ISSC49989.2020.9180155","DOIUrl":null,"url":null,"abstract":"Accurate wind power forecasts are a key tool for the correct operation of the grid and the energy trading market, particularly in regions with a large wind resource as Ireland, where wind energy comprises a large share of the electricity generated. A multi-step ahead wind power forecasting ensemble of models based on variational mode decomposition and extreme learning machines is employed in this paper to be applied for Irish wind farms. Data from two wind farms placed in different locations are used to show the suitability of the model for Ireland. The results show that the use of this full ensemble of models provides more reliable and robust forecasts for several prediction horizons and an improvement between 7% and 22% with respect to a single model. Additionally, the ensemble shows a low systematic error regardless of the prediction horizon.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"280 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 31st Irish Signals and Systems Conference (ISSC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISSC49989.2020.9180155","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
Accurate wind power forecasts are a key tool for the correct operation of the grid and the energy trading market, particularly in regions with a large wind resource as Ireland, where wind energy comprises a large share of the electricity generated. A multi-step ahead wind power forecasting ensemble of models based on variational mode decomposition and extreme learning machines is employed in this paper to be applied for Irish wind farms. Data from two wind farms placed in different locations are used to show the suitability of the model for Ireland. The results show that the use of this full ensemble of models provides more reliable and robust forecasts for several prediction horizons and an improvement between 7% and 22% with respect to a single model. Additionally, the ensemble shows a low systematic error regardless of the prediction horizon.