Comparative Between Neural Networks Generate Predictions for Global Solar Radiation and Air Temperature (original) (raw)
Related papers
Prediction of Solar Radiation Using Neural Networks Forecasting
Information Management and Big Data , 2021
Solar radiation and wind data play an important role in renewable energy projects to produce electricity. In Ecuador, these data are not always available for locations of interest due to absences of meteorological stations. In the scope of this paper, a low-cost automatic meteorological station prototype based on Raspberry technology was developed to measure the aforementioned variables. The objective of this paper is twofold: a) to present a proposal for the design of a low-cost automatic weather station using the Raspberry Pi microcomputer, showing the feasibility of this technology as an alternative for the construction of automatic meteorological station and; b) to use Machine learning (ML) method in order to predict solar radiation in Manta, Ecuador, based on the historical data collected for these three variables to date. We proved that both technology feasibility and Machine learning has a high potential as a tool to use in this field of study.
2010
The main objective of present study is to predict daily global solar radiation (GSR) on a horizontal surface, based on meteorological variables, using different artificial neural network (ANN) techniques. Daily mean air temperature, relative humidity, sunshine hours, evaporation, and wind speed values between 2002 and 2006 for Dezful city in Iran (32°16 0 N, 48°25 0 E), are used in this study. In order to consider the effect of each meteorological variable on daily GSR prediction, six following combinations of input variables are considered: (I) Day of the year, daily mean air temperature and relative humidity as inputs and daily GSR as output. (II) Day of the year, daily mean air temperature and sunshine hours as inputs and daily GSR as output. (III) Day of the year, daily mean air temperature, relative humidity and sunshine hours as inputs and daily GSR as output. (IV) Day of the year, daily mean air temperature, relative humidity, sunshine hours and evaporation as inputs and daily GSR as output. (V) Day of the year, daily mean air temperature, relative humidity, sunshine hours and wind speed as inputs and daily GSR as output. (VI) Day of the year, daily mean air temperature, relative humidity, sunshine hours, evaporation and wind speed as inputs and daily GSR as output. Multi-layer perceptron (MLP) and radial basis function (RBF) neural networks are applied for daily GSR modeling based on six proposed combinations. The measured data between 2002 and 2005 are used to train the neural networks while the data for 214 days from 2006 are used as testing data. The comparison of obtained results from ANNs and different conventional GSR prediction (CGSRP) models shows very good improvements (i.e. the predicted values of best ANN model (MLP-V) has a mean absolute percentage error (MAPE) about 5.21% versus 10.02% for best CGSRP model (CGSRP 5)).
Smart Grid and Renewable Energy, 2016
Solar radiation is one of the most important parameters for applications, development and research related to renewable energy. However, solar radiation measurements are not a simple task for several reasons. In the cases where data are not available, it is very common the use of computational models to estimate the missing data, which are based mainly on the search for relationships between weather variables, such as temperature, humidity, precipitation, cloudiness, sunshine hours, etc. But, many of these are subjective and difficult to measure, and thus they are not always available. In this paper, we propose a method for estimating daily global solar radiation, combining empirical models and artificial neural networks. The model uses temperature, relative humidity and atmospheric pressure as the only climatic input variables. Also, this method is compared with linear regression to verify that the data have nonlinear components. The models are adjusted and validated using data from five meteorological stations in the province of Tucumán, Argentina. Results show that neural networks have better accuracy than empirical models and linear regression, obtaining on average, an error of 2.83 [MJ/m2] in the validation dataset.
IJERT-A Survey on Predicting Solar Radiation Based on Neural Networks
International Journal of Engineering Research and Technology (IJERT), 2014
https://www.ijert.org/a-survey-on-predicting-solar-radiation-based-on-neural-networks https://www.ijert.org/research/a-survey-on-predicting-solar-radiation-based-on-neural-networks-IJERTV3IS091073.pdf This paper presents a survey on predicting the global solar radiation based on neural networks. Solar radiation is considered as the primary factor in many applications that makes use of solar energy. This solar radiation data provides information about the use of solar energy in various locations. Hence the need for predicting the solar radiation is increasing day-by-day. The solar radiation can be predicted by considering some climatic parameters such as air temperature, air pressure, humidity, wind speed, wind direction and so on. There are various algorithms in neural networks. The ultimate goal of this survey is to provide an overview of predicting solar radiation based on neural networks and training the network using back-propagation algorithm.
A Survey on Predicting Solar Radiation Based on Neural Networks
2014
This paper presents a survey on predicting the global solar radiation based on neural networks. Solar radiation is considered as the primary factor in many applications that makes use of solar energy. This solar radiation data provides information about the use of solar energy in various locations. Hence the need for predicting the solar radiation is increasing day-by-day. The solar radiation can be predicted by considering some climatic parameters such as air temperature, air pressure, humidity, wind speed, wind direction and so on. There are various algorithms in neural networks. The ultimate goal of this survey is to provide an overview of predicting solar radiation based on neural networks and training the network using back-propagation algorithm.
Solar radiation forecasting based on meteorological data using artificial neural networks
2009
The main objective is to predict daily global solar radiation (GSR) in future time domain based on measured air temperature, relative humidity and sunshine hours values between 2002 and 2006 for Dezful city in Iran using artificial neural network method. The estimations of GSR were made using three combinations of data sets: (I) length of day, daily mean air temperature and relative humidity as inputs and GSR as output, (II) length of day, daily mean air temperature and sunshine hours as inputs and GSR as output, (III) length of day, daily mean air temperature, relative humidity and sunshine hours as inputs and GSR as output. The measured data between 2002 and 2005 were used for training the neural networks while 235 days data from 2006 as testing data. The testing data were not used in training the neural networks. Obtained results show that neural networks are well capable of estimating GSR from simple and available meteorological data. This can be used for estimating GSR for locations where only simple meteorological data are available.
Neural Network Prediction Models for the Global Solar Radiation in the United Arab Emirates
2013
with comprehensive training algorithms, architectures, and different combinations of inputs are used to develop these models. The measured data include the maximum temperature (°C), mean wind speed (knot), sunshine hours, mean relative humidity (%) and mean daily global solar radiation on a horizontal surface (kWh/m 2 ). This data was provided by the National Center of Meteorology and Seismology (NCMS) of Abu Dhabi. The results show the generalization capability of ANN approach and its ability to generate accurate prediction of GSR in UAE.
Solar Energy, 2016
The study focused on the use of Artificial Neural Networks (ANN) in short-term prediction of Global Solar Irradiance (GSI). It introduces a new methodology based on observations made in parallel by neighboring sensors and values for different variables (temperature, humidity, pressure, wind and other estimates), using up to 900 inputs (higher dimensions). Experiments were carried out using ANN with different architectures and parameters in order to determine which of these generated the best GSI predictions for the various time frames studied (between 1 and 6 h). The results of the study allowed us to generate ANN models that predict short-term GSI with error rates less than 20% nRMSE. In addition, using observations from neighboring stations within a 55 km as a reference radius reduced error rates in predictions for time frames between 1 and 3 h, while the best predictions for time frames between 4 and 6 h were generated by ANNs that used only initial data from the station for which the prediction was being made.
Solar Radiation Forecast Using Artificial Neural Networks
The fast increase in importance of the solar energy resource as viable and promising source of renewable energy has boosted research in methods to evaluate the short-term forecasts of the solar energy resource. There is an increase on demand from the energy sector for accurate short-term forecasts of solar energy resources in order to support the planning and management of the electricity generation and distribution systems. The Eta model is the mesoscale model running at CPTEC/INPE for weather forecasts and climate studies. It provides outputs for solar radiation flux at the surface, but these solar radiation forecasts are greatly overestimated. In order to achieve more reliable information, Artificial Neural Networks (ANN) were used to refine short-term forecast for the downward solar radiation flux at the surfaceprovided by Eta/CPTEC model. Ground measurements of downward solar radiation flux acquired in two SONDA sites located in Southern region of Brazil (Florianópolis and S?o Martinho da Serra) were used for ANN training and validation. The short-term forecasts produced by ANN have presented higher correlation coefficients and lower deviations. The ANN removed the bias observed in solar radiation forecasts provided by Eta/CPTEC model. The skill improvement in RMSE was higher than 30%when ANN was used to provide short-term forecasts of solar radiation at the surface in both measurement sites.
Performance Evaluation of Artificial Neural Networks in Estimating Global Solar Radiation , Case Study : New Borg El- arab City , Egypt, 2017
The most sustainable source of energy with unlimited reserves is the solar energy which is the main source of all types of energy on the earth. Accurate knowledge of solar radiation is considered as the first step in solar energy availability assessment, and it is the primary input for various solar energy applications. The unavailability of the solar radiation measurements for several sites around the world leads to proposing different models for predicting the global solar radiation. Artificial neural networks technique is considered as an effective tool for modelling nonlinear systems and require fewer inputs parameter. This work is purposed to investigate the performance of artificial neural networks based models in estimating global solar radiation. To achieve this goal, measured dataset of global solar radiation for the case study location (Lat. 30˚ 51 ̀ N and long. 29˚ 34 ̀ E) are utilized for models establishment and validation. Mostly common statistical indicators are employed for evaluating the performance of these models and recognizing the best model. The obtained results show that the artificial neural network models demonstrate promising performance in the prediction of global solar radiation. In addition, the proposed models provide superior consistency between the measured and estimated values.