{"title":"利用支持向量回归预测太阳能潜力","authors":"Subham Shaw, M. Prakash","doi":"10.1109/DEVIC.2019.8783431","DOIUrl":null,"url":null,"abstract":"Solar energy is one of the most commonly used renewable energy resources. To obtain reliable output from solar energy, prediction of solar radiation is necessary. In this paper, a solar radiation prediction model has been developed for New Alipore, Kolkata. Easily available meteorological parameters like temperature, pressure and humidity have been utilized as inputs, to build the prediction model. Two years data (2011–2012) have been used to develop the Support Vector Regression (SVR) based solar radiation prediction model. The results obtained from the prediction model have been validated with the help of statistical metrics, Root-Mean-Square Error (RMSE) and Coefficient of Determination $(\\mathrm{R}^{2})$. The results signifies that the performance of the developed model is better in comparison with the models existing in the literature.","PeriodicalId":294095,"journal":{"name":"2019 Devices for Integrated Circuit (DevIC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Forecasting Solar Potential Using Support Vector Regression\",\"authors\":\"Subham Shaw, M. Prakash\",\"doi\":\"10.1109/DEVIC.2019.8783431\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Solar energy is one of the most commonly used renewable energy resources. To obtain reliable output from solar energy, prediction of solar radiation is necessary. In this paper, a solar radiation prediction model has been developed for New Alipore, Kolkata. Easily available meteorological parameters like temperature, pressure and humidity have been utilized as inputs, to build the prediction model. Two years data (2011–2012) have been used to develop the Support Vector Regression (SVR) based solar radiation prediction model. The results obtained from the prediction model have been validated with the help of statistical metrics, Root-Mean-Square Error (RMSE) and Coefficient of Determination $(\\\\mathrm{R}^{2})$. The results signifies that the performance of the developed model is better in comparison with the models existing in the literature.\",\"PeriodicalId\":294095,\"journal\":{\"name\":\"2019 Devices for Integrated Circuit (DevIC)\",\"volume\":\"63 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 Devices for Integrated Circuit (DevIC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DEVIC.2019.8783431\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 Devices for Integrated Circuit (DevIC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DEVIC.2019.8783431","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Forecasting Solar Potential Using Support Vector Regression
Solar energy is one of the most commonly used renewable energy resources. To obtain reliable output from solar energy, prediction of solar radiation is necessary. In this paper, a solar radiation prediction model has been developed for New Alipore, Kolkata. Easily available meteorological parameters like temperature, pressure and humidity have been utilized as inputs, to build the prediction model. Two years data (2011–2012) have been used to develop the Support Vector Regression (SVR) based solar radiation prediction model. The results obtained from the prediction model have been validated with the help of statistical metrics, Root-Mean-Square Error (RMSE) and Coefficient of Determination $(\mathrm{R}^{2})$. The results signifies that the performance of the developed model is better in comparison with the models existing in the literature.