Solar Radiation Prediction Using Machine Learning Techniques: A Review

Paredes, Edgar Dario Obando; Quintero, Sandra Ximena Carvajal; Agudelo, Jairo Pineda

doi:10.1109/tla.2019.8891934

Cited by 40 publications

(18 citation statements)

References 129 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Historically, the most widely used approach in the PSPEG is the Machine Learning [13,14,20] with ANN models [21][22][23][24][25]. The most cited researches in the literature, considering the citations number's in Google Scholar in February 8th, 2021, are the ANN's proposed in [21] and [22] for solar irradiance prediction over the 24-hour horizon.…”

Section: Theoretical Background and Related Workmentioning

confidence: 99%

“…Nowadays, approaches based on Machine Learning (ML) and Artificial Intelligence (AI) [12] are the most commonly studied due to their ability to solve complex problems with non-linear data structures. [13,14]. In this context, the most applied method in the PSPEG are Artificial Neural Networks (ANN's) [10] and, more recently Deep Learning models [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Artificial Neural Networks for Forecasting Photovoltaic Energy Generation with Solar Irradiance

Maciel

Wentz

Ledesma

et al. 2021

Braz. arch. biol. technol.

View full text Add to dashboard Cite

The growth in the use of solar energy has encouraged the development of techniques for shortterm prediction of solar photovoltaic energy generation (PSPEG). Machine learning with Artificial Neural Networks (ANNs) is the most widely used technique to solve this problem. However, comparative studies of these networks with distinct structural configurations, input parameters and prediction horizon, have not been observed in the literature. In this context, the aim of this study is to evaluate the prediction accuracy of the Global Horizontal Irradiance (GHI), which is often used in the PSPEG, generated by ANN models with different construction structures, sets of input meteorological variables and in three short-term prediction horizons, considering a unique database. The analyses were performed with controlled environment and experimental configuration. The results suggest that ANNs using the input GHI variable provide better accuracy (approximately 10%), and their absence increases error variability. No significant difference (p>0.05) was identified in the prediction error models trained with distinct meteorological input data sets. The prediction errors were similar for the same ANN model in the different prediction horizons, and ANNs with 30 and 60 neurons with one hidden layer demonstrated similar or higher accuracy than those with two hidden layers.

show abstract

Section: Theoretical Background and Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Analysis of Artificial Neural Networks for Forecasting Photovoltaic Energy Generation with Solar Irradiance

Maciel

Wentz

Ledesma

et al. 2021

Braz. arch. biol. technol.

View full text Add to dashboard Cite

show abstract

“…In the same way [16] also performs a short-term predictor for solar intensity with meteorological data, using Lasso and short and long-term memories, using K means for grouping the data. [17] presents a review of the literature related to the prediction of solar energy using data learning techniques from the Science Direct and IEEE databases since 1990. [18] applies a regression to chemical industrial processes based on semi-supervised Bayesian principal components comparing them with the reference that is the Tennessee Eastman process.…”

Section: Introductionmentioning

confidence: 99%

Selection of Characteristics by Hybrid Method: RFE, Ridge, Lasso, and Bayesian for the Power Forecast for a Photovoltaic System

et al. 2021

View full text Add to dashboard Cite

Currently, the generation of alternative energy from solar radiation with photovoltaic systems is growing, its efficiency depends on internal variables such as powers, voltages, currents; as well as external variables such as temperatures, irradiance, and load. To maximize performance, this research focused on the application of regularization techniques in a multiparametric linear regression model to predict the active power levels of a photovoltaic system from 14 variables that model the system under study. These variables affect the prediction to some degree, but some of them do not have so much preponderance in the final forecast, so it is convenient to eliminate them so that the processing cost and time are reduced. For this, we propose a hybrid selection method: first we apply the elimination of Recursive Feature Elimination (RFE) within the selection of subsets and then to the obtained results we apply the following contraction regularization methods: Lasso, Ridge and Bayesian Ridge; then the results were validated demonstrating linearity, normality of the error terms, without autocorrelation and homoscedasticity. All four prediction models had an accuracy greater than 99.97%. Training time was reduced by 71% and 36% for RFE-Ridge and RFE-OLS respectively. The variables eliminated with RFE were Total Energy, Daily Energy, and Irradiance, while the variable eliminated by Lasso was: "Frequency". In all cases we see that the root mean square errors were reduced for RFE. Lasso by 0.15% while for RFE-Bayesian Ridge by 0.06%.

show abstract

“…This operation provides a significant contribution to the precision, interpretation and evaluation of the model. It also reduces the duration of modelling studies [9].…”

Section: Introductionmentioning

confidence: 99%

Determining of Solar Power by Using Machine Learning Methods in a Specified Region

2021

View full text Add to dashboard Cite

In this study, it is aimed to estimate the solar power according to the hourly meteorological data of the specified location measured between 2002 and 2006 by using different Machine Learning (ML) algorithms. Data Mining Processes (DMP) were used to select the most appropriate input variables from these measured data. Data groups created using DMP were evaluated according to three different ML algorithms such as Artificial Neural Network (ANN), Support Vector Regression (SVR) and K-Nearest Neighbors (KNN). It can be concluded that DMP-ML based prediction models are more successful than models developed using all available data. The most successful model developed among these models estimated the hourly solar power potential with an accuracy of 97%. Also, different error measurement statistics were used to evaluate ML algorithms. According to Symmetric Mean Absolute Percentage Error, 6.12%, 7.22% and 12.72% values were found in the most successful prediction models developed using ANN, KNN and SVR, respectively. In addition, from the meteorological data used in this study the most effective data on solar power as a result of DMP were shown to be Temperature and Hourly Sunshine Duration.

show abstract

Solar Radiation Prediction Using Machine Learning Techniques: A Review

Cited by 40 publications

References 129 publications

Analysis of Artificial Neural Networks for Forecasting Photovoltaic Energy Generation with Solar Irradiance

Analysis of Artificial Neural Networks for Forecasting Photovoltaic Energy Generation with Solar Irradiance

Selection of Characteristics by Hybrid Method: RFE, Ridge, Lasso, and Bayesian for the Power Forecast for a Photovoltaic System

Determining of Solar Power by Using Machine Learning Methods in a Specified Region

Contact Info

Product

Resources

About