A. Mohammad, Hasanen M. Hussen, Hussein J. Akeiber
{"title":"基于神经元数优化的人工神经网络模型预测光伏组件输出功率","authors":"A. Mohammad, Hasanen M. Hussen, Hussein J. Akeiber","doi":"10.14710/ijred.2023.49972","DOIUrl":null,"url":null,"abstract":"Artificial neural networks (ANNs) is an adaptive system that has the ability to predict the relationship between the input and output parameters without defining the physical and operation conditions. In this study, some queries about using ANN methodology are simply clarified especially about the neurons number and their relationship with input and output parameters. In addition, two ANN models are developed using MATLAB code to predict the power production of a polycrystalline PV module in the real weather conditions of Iraq. The ANN models are then used to optimize the neurons number in the hidden layers. The capability of ANN models has been tested under the impact of several weather and operational parameters. In this regard, six variables are used as input parameters including ambient temperature, solar irradiance and wind speed (the weather conditions), and module temperature, short circuit current and open circuit voltage (the characteristics of PV module). According to the performance analysis of ANN models, the optimal neurons number is 15 neurons in single hidden layer with minimum Root Mean Squared Error (RMSE) of 2.76% and 10 neurons in double hidden layers with RMSE of 1.97%. Accordingly, it can be concluded that the double hidden layers introduce a higher accuracy than the single hidden layer. Moreover, the ANN model has proven its accuracy in predicting the current and voltage of PV module. ","PeriodicalId":44938,"journal":{"name":"International Journal of Renewable Energy Development-IJRED","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Prediction the output power of photovoltaic module using artificial neural networks model with optimizing the neurons number\",\"authors\":\"A. Mohammad, Hasanen M. Hussen, Hussein J. Akeiber\",\"doi\":\"10.14710/ijred.2023.49972\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Artificial neural networks (ANNs) is an adaptive system that has the ability to predict the relationship between the input and output parameters without defining the physical and operation conditions. In this study, some queries about using ANN methodology are simply clarified especially about the neurons number and their relationship with input and output parameters. In addition, two ANN models are developed using MATLAB code to predict the power production of a polycrystalline PV module in the real weather conditions of Iraq. The ANN models are then used to optimize the neurons number in the hidden layers. The capability of ANN models has been tested under the impact of several weather and operational parameters. In this regard, six variables are used as input parameters including ambient temperature, solar irradiance and wind speed (the weather conditions), and module temperature, short circuit current and open circuit voltage (the characteristics of PV module). According to the performance analysis of ANN models, the optimal neurons number is 15 neurons in single hidden layer with minimum Root Mean Squared Error (RMSE) of 2.76% and 10 neurons in double hidden layers with RMSE of 1.97%. Accordingly, it can be concluded that the double hidden layers introduce a higher accuracy than the single hidden layer. Moreover, the ANN model has proven its accuracy in predicting the current and voltage of PV module. \",\"PeriodicalId\":44938,\"journal\":{\"name\":\"International Journal of Renewable Energy Development-IJRED\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2023-02-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Renewable Energy Development-IJRED\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.14710/ijred.2023.49972\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Renewable Energy Development-IJRED","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14710/ijred.2023.49972","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
Prediction the output power of photovoltaic module using artificial neural networks model with optimizing the neurons number
Artificial neural networks (ANNs) is an adaptive system that has the ability to predict the relationship between the input and output parameters without defining the physical and operation conditions. In this study, some queries about using ANN methodology are simply clarified especially about the neurons number and their relationship with input and output parameters. In addition, two ANN models are developed using MATLAB code to predict the power production of a polycrystalline PV module in the real weather conditions of Iraq. The ANN models are then used to optimize the neurons number in the hidden layers. The capability of ANN models has been tested under the impact of several weather and operational parameters. In this regard, six variables are used as input parameters including ambient temperature, solar irradiance and wind speed (the weather conditions), and module temperature, short circuit current and open circuit voltage (the characteristics of PV module). According to the performance analysis of ANN models, the optimal neurons number is 15 neurons in single hidden layer with minimum Root Mean Squared Error (RMSE) of 2.76% and 10 neurons in double hidden layers with RMSE of 1.97%. Accordingly, it can be concluded that the double hidden layers introduce a higher accuracy than the single hidden layer. Moreover, the ANN model has proven its accuracy in predicting the current and voltage of PV module.