Efficient solar radiation estimation using cohesive artificial neural network technique with optimal synaptic weights (original) (raw)
Related papers
Modeling Solar Energy Potential in Tehran Province using Artificial Neural Networks
International Journal of Green Energy, 2012
Prediction of daily global solar radiation (GSR) plays an important role in design of renewable energy systems. Artificial Neural Networks (ANNs) are powerful tools for modeling and estimating GSR even though using few inputs. In order to train the networks, a dataset of meteorological daily time series for 15 years (1993–2008) collected in Tehran by Iran Meteorological Office were used. The meteorological parameters used to estimate GSR were daily values of maximum, minimum, and mean temperatures; relative humidity; sunshine duration; and precipitation as inputs and the daily GSR in MJ m−2 day−1 as output. Various ANN models were designed and implemented by combining different meteorological data. The optimum model for estimating GSR had one hidden layer multilayer perceptron (MLP) with 37 neurons in it when the inputs were number of the maximum and minimum temperature, sunshine duration, daylight hours, extraterrestrial radiation, and number of day in the year. The empirical Hargreaves and Samani equation (HS) was also considered for the comparison. To estimate the difference between measured and estimated values of ANN and empirical models, mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient (r) were determined. For 6-37-1 topology, r, RMSE, and MAE values were found to be 0.968, 3.09, and 2.57, respectively. Obtained results showed that ANN model outperformed HS model and can be successfully used for estimating the daily GSR for Tehran province and any other location.
Artificial Neural Network based Solar Radiation Estimation: A Case Study of Indian Cities
2020
Estimation of Solar radiation is the integral part of optimization of solar energy applications. Solar energy equipments perform better if the radiation to be received is estimated well in advance. Due to the limited availability of meteorological stations (equipped with solar measuring devices), various solar radiation estimation models are developed. This paper presents the development of a solar radiation estimation model using Artificial Neural Network with a case study of five Indian stations (Sri Nagar, Calcutta, Trivandrum, Dwarka, and Bhopal) comprising different climatic zones. Latitude, longitude, altitude, months of a year, maximum temperature, minimum temperature, relative humidity, wind velocity, and sunshine hour are considered for input and solar radiation is obtained at output. Climatic conditions, geographical profile, model complexity are the major challenges behind solar radiation estimation. Present study addresses them. Simulation is carried out with MATLAB 2016...
Estimation of Global Solar Radiation using Artificial Neural Network in Kathmandu, Nepal
— There is no doubt that information of the measured data of solar radiation is the best for designing any reliable solar energy systems but in Nepal the measured solar radiation data are not available for most of the sites due to high cost and requirement of daily maintenance of the measuring instruments. The alternative is to use the estimated data of solar radiation using any of available estimation models. In this study an Artificial Neural Network (ANN) was used to estimate the solar radiation in Kathmandu with the help of meteorological data of maximum and daily average temperature, relative humidity, rainfall amount, sunshine hour and solar radiation available for Tribhuvan International Airport. Data from 2002 to 2011 were used to train the Network and it was tested by using the data of 2012 and 2013. A multi-layer feed-forward neural network was devised using MATLAB programming. Five different models with different input combinations were modeled with Feed-Forward Multilayer Preceptors. The results of ANN model were compared with measured data on the basis of root mean square error (RMSE), mean bias error (MBE), mean percentage error (MPE) and Correlation Coefficients (CC) in order to check the performance of developed model. The obtained result indicate that the ANN based model for estimating solar radiation is precise in the selected location thus the model can be used anywhere in the Nepal having similar climate conditions where the meteorological data are available. The best prediction was from Model 1 as it exhibit minimum value of RMSE (0.2781) and maximum value of CC (0.9880).
Artificial Neural Network based Solar Radiation Estimation
2020
Solar radiation is well estimated by Artificial Neural Network. Meteorological data, Location details and Solar radiation data of 13 stations of Sri Lanka belonging from each part are used for Training, Testing and Validation of Neural Network. The present study is performed with all three types of training algorithm, Levenberg-Marquardt (LM), Bayesian Regularization (BR) and Scaled Conjugate Gradient (SCG). Their performance are compared on the basis of Mean Square Error (MSE), Regression Value (R), Slope of Regression line (m) and Intercept of Regression line (c), which are found in the range of 0-0.18131, 0.955810.99991, 0.89-1.0 and 0.00019-0.087 respectively for selected stations of Sri Lanka.
Indonesian Journal of Electrical Engineering and Computer Science, 2021
The estimation of the daily average global solar radiation is important since it increases the cost efficiency of solar power plant, especially in developing countries. Therefore, this study aims at developing a multi layer perceptron artificial neural network (ANN) to estimate the solar radiation in the city of Surabaya. To guide the study, seven (7) available meteorological parameters and the number of the month was applied as the input of network. The ANN was trained using five-years data of 2011-2015. Furthermore, the model was validated by calculating the mean average percentage error (MAPE) of the estimation for the years of 2016-2019. The results confirm that the aforementioned model is feasible to generate the estimation of daily average global solar radiation in Surabaya, indicated by MAPE of less than 15% for all testing years.
Modeling Solar Energy Potential in a Tehran Province Using Artificial Neural Networks
International Journal of Green Energy, 2013
6-37-1 topology, r, RMSE, and MAE values were found to be 0.968, 3.09, and 2.57, respectively. Obtained results showed that ANN model outperformed HS model and can be successfully used for estimating the daily GSR for Tehran province and any other location. 177 178 RAMEDANI, OMID, AND KEYHANI DNI data is required. Solar thermal power plants are essentially Concentrating Solar Power (CSP) units. For designing solar thermal power plants, DNI data is therefore a prerequisite.
Energy Procedia, 2016
Solar potential assessment is very useful for various applications like solar heating, agriculture, solar lighting system and solar power plant erection etc. The objective of the current study is to identify theoretical potential of solar radiation for solar energy applications in hilly state Himachal Pradesh. Artificial Neural Network (ANN) is used to predict solar radiation using site specific measured data of Hamirpur for training and testing. The input variables used are temperature, rainfall, sunshine hours, humidity & barometric pressure to predict solar radiations. To identify the effect of various input parameters on solar radiations three ANN based models have been developed represented by ANN-I 5 , ANN-I 4 & ANN-I 3 .To obtain best prediction result, the number of input parameters of the input layer have been varied between 3 to 5 and hidden layer neuron have also been varied between 10 to 20. The best mean absolute percentage error (MAPE) calculated for these models (ANN-I 5 , ANN-I 4 & ANN-I 3) are 16.45%, 18.77% and 19.39% respectively. The ANN-I 5 (temperature, humidity, barometric pressure, rainfall and sun shine hours), model has shown good prediction accuracy as compared to other two models. This study shows that various numbers of meteorological parameters mostly affect the forecasting of solar radiation. The method in this paper can also be used to identify the solar energy potential of any location worldwide where it is not possible to install direct measuring instrument.
New Regression Model to Estimate Global Solar Radiation Using Artificial Neural Network
The main objective of the present study was to develop a new model for the solar radiation estimation in hilly areas of North India for the determination of constants 'a' and 'b' by taking only latitude and altitude of the place into consideration. In this study, new model was developed based on Angstrom-Prescott Model to estimate the monthly average daily global solar radiation only using sunshine duration data. The monthly average global solar radiation data of four different locations in North India was analyzed with the neural fitting tool (nftool) of neural network of MATLAB Version 7.11.0.584 (R2010b) with 32-bit (win 32). The neural network model was used with 10 hidden neurons. Eight months data was used to train the neural network. Two months data was used for the validation purpose and the remaining two months for the testing purpose. The new developed model estimated the values of 'a' which range from 0.209 to 0.222 and values of 'b' ranging from 0.253 to 0.407. The values of maximum percentage error (MPE) and mean bias error (MBE) were in good agreement with the actual values. Artificial neural network application showed that data was best fitted for the regression coefficient of 0.99558 with best validation performance of 0.85906 for Solan. This will help to advance the state of knowledge of global solar radiation to the point where it has applications in the estimation of monthly average daily global solar radiation.
Modeling of Solar Energy for Malaysia Using Artificial Neural Networks
This paper presents a solar energy prediction method using artificial neural networks (ANNs). An ANN predicts a clearness index that is used to calculate global solar irradiation. The ANN model is based on the feed forward multilayer perception model with four inputs and one output. The inputs are latitude, longitude, day number and sunshine ratio; the output is the clearness index. Data from 28 weather stations were used in this research, and 23 stations were used to train the network while 5 stations were used to test the network. Based on the results, the average MAPE, mean bias error and root mean square error for the predicted global solar irradiation are 5.92%, 1.46% and 7.96%.
Renewable Energy, 2010
Global solar radiation (GSR) data are desirable for many areas of research and applications in various engineering fields. However, GSR is not as readily available as air temperature data. Artificial neural networks (ANNs) are effective tools to model nonlinear systems and require fewer inputs. The objective of this study was to test an artificial neural network (ANN) for estimating the global solar radiation (GSR) as a function of air temperature and relative humidity data in a in the southwestern region of Algeria. The measured data between 02 February to 31 May 2011 were used for training the neural networks while the remaining 651 hours data from June 2011 as testing data. The testing data were not used in training the neural networks. The climatic data collected in weather station of Energy Laboratory in Drylands (ENERGARID) located in the southwestern region of Algeria. Obtained results show that neural networks are well capable of estimating GSR from temperature and relative humidity. This can be used for estimating GSR for locations where only temperature and humidity data are available.