Figure 1 - available via license: Creative Commons Attribution-NonCommercial 4.0 International
Content may be subject to copyright.
Source publication
This study presents a detailed examination of using artificial neural networks for predicting global solar radiation. The research aims to develop an artificial neural network model using five years of solar radiation and meteorological variables (precipitation, wind speed, relative humidity, vapor pressure, cloudiness, current pressure, average te...
Context in source publication
Context 1
... enables us to better understand and visually observe the distribution of the relationship between the data. The heat map illustrating the data distribution is depicted in Figure 1. The relationship distribution between the data is shown in Figure 2. A relationship between solar radiation and total insolation intensity data has been identified. ...
Similar publications
Study region: The Três Marias 396 MW power plant located on the São Francisco River in Brazil. Study focus: Hydropower generation is directly and indirectly affected by climate change. It is also a relevant source of energy for electricity generation in many countries. Thus, methodologies need to be developed to assess the impacts of future climate...
Citations
... This model can find systematic errors in the output of the NWP model and relevant variables in the estimation of historical data and observations by comparing the basis of the two data and providing the best assessment with a short time and a more detailed model [32], [33]. In several studies about forecast hourly GHI, DNI, and DHI with several machine learning models and solar radiation as input, as well as aerosol observations against wind and aerosol forecasts, were evaluated to obtain the best ANN model performance [34], while a comparison of models with feed-forward artificial neural networks and recurrent neural networks to estimate global solar radiation at the research location which shows that, artificial neural networks can improve prediction performance, but incur additional computational costs [35] and the results are getting closer solar radiation one day ahead via SVM with NWP data from the meteorology, climatology, and geophysics agency scale model produces an RMSE of 15.98%, while using artificial neural networks to approximate solar radiation with NWP from the WRF model, a reduction in model bias is obtained, MSE and RMSE [36]. Meanwhile, ML models have been developed to be applied to solar irradiation forecasting with a focus on GHI which is used to obtain an approach to the power output of solar energy systems with temporal resolution and forecast time horizons that are not synchronous with real-time forecasts. ...
Operational forecasting of solar radiation is critical for better decision-making by solar energy system operators, due to the variability of energy resources and demand. Although the numerical weather forecasting (NWP) model can predict solar radiation variables, there are often significant errors, especially in direct normal irradiation (DNI), which are influenced by the type and concentration of aerosols and clouds. This paper presents an artificial neural network (ANN) based method to generate operational DNI forecasts using weather and aerosol forecast data from the European Center for medium-range weather forecasts (ECMWF) and Copernicus atmospheric monitoring service (CAMS) respectively. The ANN model is designed to predict weather and aerosol variables at a certain time as input, while other models use the DNI forecast improvement period before the instant forecast. The model was developed using North Sumatra location observations and obtained DNI forecasting results every 10 minutes on the first day with DNI forecasting compared to the initial forecasting which was scaled down with the R 2 , mean absolute error (MAE), and relative mean square error (RMSE) models were 0.6753, 151.2, and 210.2 W/m 2 , so that and provides good agreement with experimental data.
... The study concluded that results obtained using sigmoidal units were superior. In reference [12], a 5-year period of solar radiation and meteorological data from Kocaeli province are used to develop an artificial neural network model. The model makes use of neural networks' capability to examine relationships and data structures in order to handle the complexity of solar radiation. ...
When designing solar systems and assessing the effectiveness of their many uses, estimating sun irradiance is a crucial first step. This study examined three approaches (ANN, GA-ANN, and ANFIS) for estimating daily global solar radiation (GSR) in the south of Algeria: Adrar, Ouargla, and Bechar. The proposed hybrid GA-ANN model, based on genetic algorithm-based optimization, was developed to improve the ANN model. The GA-ANN and ANFIS models performed better than the standalone ANN-based model, with GA-ANN being better suited for forecasting in all sites, and it performed the best with the best values in the testing phase of Coefficient of Determination (R = 0.9005), Mean Absolute Percentage Error (MAPE = 8.40%), and Relative Root Mean Square Error (rRMSE = 12.56%). Nevertheless, the ANFIS model outperformed the GA-ANN model in forecasting daily GSR, with the best values of indicators when testing the model being R = 0.9374, MAPE = 7.78%, and rRMSE = 10.54%. Generally, we may conclude that the initial ANN stand-alone model performance when forecasting solar radiation has been improved, and the results obtained after injecting the genetic algorithm into the ANN to optimize its weights were satisfactory. The model can be used to forecast daily GSR in dry climates and other climates and may also be helpful in selecting solar energy system installations and sizes.
