Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters

Meenal, R.; Selvakumar, A. Immanuel

doi:10.1016/j.renene.2017.12.005

Cited by 211 publications

(72 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These results are consist with the result from Chen and Li [20] who found the modifications to A-P model by individually introducing relative humidity, atmospheric pressure and precipitation gave similar performances to the A-P model. Meenal [173] compared 16 empirical models and also reported that exclusion of relative humidity did not affect the estimation accuracy of sunshine duration models in India. While Yildirim et al [13] found both models SR8 and SR7 significantly outperformed A-P model, as well as 14 sunshine duration models in his work.…”

Section: Resultsmentioning

confidence: 99%

Empirical models for estimating monthly global solar radiation: A most comprehensive review and comparative case study in China

Chen

He²,

Yang

et al. 2019

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

Global solar radiation is a core component of scientific research and engineering application across a broad spectrum. However, its measurement is limited by a small number of observation stations due to the technical and financial restricts. Estimating solar radiation with the meteorological variables using empirical models is of benefit to obtain solar radiation data at global scale. Yet, there are various options of available empirical models to select the most suitable one. This study conducted a most comprehensive collection and review of empirical models employing the commonly measured meteorological variables and geographic factors. A total of 294 different types of empirical models were collected and classified into 37 groups according to input attributes. Such collection built an empirical model library providing an overall overview of the developed emperical models in literatures. Furthermore, the collected models were calibrated and evaluated at three meteorological stations in the Three Gorges Reservoir area in China. This study suggests that these model-comparing processes can assist the governments, scientists and engineers in tailoring the most fitted model for specific applications and in particular areas.

show abstract

Section: Resultsmentioning

confidence: 99%

Empirical models for estimating monthly global solar radiation: A most comprehensive review and comparative case study in China

Chen

He²,

Yang

et al. 2019

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

show abstract

“…Radiation data have an important impact on the generation of energy, Incidence of radiation and temperature in the power of the PVS1 which is why their prediction studies are developed in the field of Artificial Neural Networks (ANN), due to their degree of complexity and uncertainty, based on some applications: Meenal and Selvakumar, (2018); Almorox and Hontoria, (2014); and Almaraashi, (2018). Due to the scope of this 4-month study, your data is limited for the analysis at this point for the time being, for the application of these prediction models, but an example has been developed in the Figure 14, where the objective is to obtain a prediction model of solar radiation the next day (RadSolar2) from the meteorological data of the previous day.…”

Section: Radiation Predictionmentioning

confidence: 99%

Data analysis and tools applied to modeling and simulation of a PV system in Ecuador

2018

View full text Add to dashboard Cite

This paper presents a research was carried out for the management of a photovoltaic system in a Microgrid, with applications and the use of tools applied to modeling and computational simulation in the Microgrid laboratory implanted in the facilities of the University of Cuenca (Ecuador). Additionally, through the use of automatic learning techniques, the behavior of the photovoltaic system has been modeled in the study area based on radiation and temperature with very good results. In addition, several applications can be made in real engineering studies such as feasibility, performance analysis, energy estimation, educational models, etc.

show abstract

“…With the development of big data mining, machine learning technology has attracted widespread attention. For instance, artificial neural network (ANN) [12][13][14][15][16][17] and support vector machine (SVM) [18][19][20] have been widely applied in solar radiation prediction. Amrouche and Le Pivert (2014) [12] took advantage of spatial modeling and artificial neural networks (ANNs) to predict daily total solar radiation in four locations in the United States, and the empirical results indicate that the proposed model satisfies the expected accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…The empirical analysis of the solar radiation data introduced in Beijing shows that, compared with other benchmark models, the Normalized Root Mean Square Error (NRMSE) and Mean Absolute Percentage Error (MAPE) generated by the DCE learning method are smaller, and the accuracy rates are 2.96% and 2.83%, respectively. In the forecast one day ahead, Meenal and Selvakumar [20] assessed the accuracy of support vector machine (SVM), artificial neural network (ANN), and empirical solar radiation models with different combinations of input parameters. The parameters include month, latitude, longitude, bright sunshine hours, day length, relative humidity, and maximum and minimum temperature.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Model Based on Principal Component Analysis, Wavelet Transform, and Extreme Learning Machine Optimized by Bat Algorithm for Daily Solar Radiation Forecasting

Zhang

Wei

2019

Sustainability

View full text Add to dashboard Cite

Precise solar radiation forecasting is of great importance for solar energy utilization and its integration into the grid, but because of the daily solar radiation’s intrinsic non-stationary and nonlinearity, which is influenced by a lot of elements, single predicting models may have difficulty obtaining results with high accuracy. Therefore, this paper innovatively puts forward an original hybrid model that predicts solar radiation through extreme learning machine (ELM) optimized by the bat algorithm (BA) based on wavelet transform (WT) and principal component analysis (PCA). First, choose the meteorological variables on the basis of Pearson coefficient test, and WT will decompose historical solar radiation into two time series, which are de-noised signal and noise signal. In the approximate series, the lag phase of historical radiation is obtained by partial autocorrelation function (PACF). After that, use PCA to reduce the dimensions of the influencing factors, including meteorological variables and historical radiation. Finally, ELM is established to predict daily solar radiation, whose input weight and deviation thresholds gained optimization by BA, thus it is called BA-ELM henceforth. In view of the four distinct solar radiation series obtained by NASA, the empirical simulation explained the hybrid model’s validity and effectiveness compared to other primary methods.

show abstract

Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters

Cited by 211 publications

References 49 publications

Empirical models for estimating monthly global solar radiation: A most comprehensive review and comparative case study in China

Empirical models for estimating monthly global solar radiation: A most comprehensive review and comparative case study in China

Data analysis and tools applied to modeling and simulation of a PV system in Ecuador

A Hybrid Model Based on Principal Component Analysis, Wavelet Transform, and Extreme Learning Machine Optimized by Bat Algorithm for Daily Solar Radiation Forecasting

Contact Info

Product

Resources

About