Zemouri Nahed, Bouzgou Hassen, A. Chouder, Douak Mohamed
{"title":"基于深度学习方法的多步太阳能发电预测","authors":"Zemouri Nahed, Bouzgou Hassen, A. Chouder, Douak Mohamed","doi":"10.1109/ICATEEE57445.2022.10093688","DOIUrl":null,"url":null,"abstract":"For the effective use and integration of solar energy into the power system, precise forecasting of photovoltaic power generation is required. Currently, forecasting methods can accurately predict PV power with different step horizons, but they fail to maintain a good resolution of accurate forecasting when we increase the number of steps ahead. This paper addresses the forecasting of PV performance of a system with multi-step ahead by considering 1, 2 and 3 steps ahead of 15-minute scenarios using Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) which are kinds of Deep Learning method . The originality of this study is that the forecasted value of solar power is put against the real data issued from the PV system. All the obtained results are evaluated using different statistical indicators such as Mean Absolute Percentage Error (MAPE), Normalized Mean Square Error (NMSE), Coefficient of determination (R2) and Forecast skill (FS). The low values of the different statistical indicators justify the goodness of the proposed approaches.","PeriodicalId":150519,"journal":{"name":"2022 International Conference of Advanced Technology in Electronic and Electrical Engineering (ICATEEE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multi-Step Solar Power Forecasting using Deep Learning Methods\",\"authors\":\"Zemouri Nahed, Bouzgou Hassen, A. Chouder, Douak Mohamed\",\"doi\":\"10.1109/ICATEEE57445.2022.10093688\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"For the effective use and integration of solar energy into the power system, precise forecasting of photovoltaic power generation is required. Currently, forecasting methods can accurately predict PV power with different step horizons, but they fail to maintain a good resolution of accurate forecasting when we increase the number of steps ahead. This paper addresses the forecasting of PV performance of a system with multi-step ahead by considering 1, 2 and 3 steps ahead of 15-minute scenarios using Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) which are kinds of Deep Learning method . The originality of this study is that the forecasted value of solar power is put against the real data issued from the PV system. All the obtained results are evaluated using different statistical indicators such as Mean Absolute Percentage Error (MAPE), Normalized Mean Square Error (NMSE), Coefficient of determination (R2) and Forecast skill (FS). The low values of the different statistical indicators justify the goodness of the proposed approaches.\",\"PeriodicalId\":150519,\"journal\":{\"name\":\"2022 International Conference of Advanced Technology in Electronic and Electrical Engineering (ICATEEE)\",\"volume\":\"5 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 International Conference of Advanced Technology in Electronic and Electrical Engineering (ICATEEE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICATEEE57445.2022.10093688\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference of Advanced Technology in Electronic and Electrical Engineering (ICATEEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICATEEE57445.2022.10093688","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Multi-Step Solar Power Forecasting using Deep Learning Methods
For the effective use and integration of solar energy into the power system, precise forecasting of photovoltaic power generation is required. Currently, forecasting methods can accurately predict PV power with different step horizons, but they fail to maintain a good resolution of accurate forecasting when we increase the number of steps ahead. This paper addresses the forecasting of PV performance of a system with multi-step ahead by considering 1, 2 and 3 steps ahead of 15-minute scenarios using Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) which are kinds of Deep Learning method . The originality of this study is that the forecasted value of solar power is put against the real data issued from the PV system. All the obtained results are evaluated using different statistical indicators such as Mean Absolute Percentage Error (MAPE), Normalized Mean Square Error (NMSE), Coefficient of determination (R2) and Forecast skill (FS). The low values of the different statistical indicators justify the goodness of the proposed approaches.