scholarly journals Evaluation of Temperature-Based Empirical Models and Machine Learning Techniques to Estimate Daily Global Solar Radiation at Biratnagar Airport, Nepal

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Sandeep Dhakal ◽  
Yogesh Gautam ◽  
Aayush Bhattarai
Keyword(s):  
Machine Learning ◽  
Relative Humidity ◽  
Linear Regression ◽  
Solar Radiation ◽  
Ambient Temperature ◽  
Sunshine Duration ◽  
Global Solar Radiation ◽  
Empirical Models ◽  
Stepwise Linear Regression ◽  
Better Than

Global solar radiation (GSR) is a critical variable for designing photovoltaic cells, solar furnaces, solar collectors, and other passive solar applications. In Nepal, the high initial cost and subsequent maintenance cost required for the instrument to measure GSR have restricted its applicability all over the country. The current study compares six different temperature-based empirical models, artificial neural network (ANN), and other five different machine learning (ML) models for estimating daily GSR utilizing readily available meteorological data at Biratnagar Airport. Amongst the temperature-based models, the model developed by Fan et al. performs better than the rest with an R2 of 0.7498 and RMSE of 2.0162 MJm−2d−1. Feed-forward multilayer perceptron (MLP) is utilized to model daily GSR utilizing extraterrestrial solar radiation, sunshine duration, maximum and minimum ambient temperature, precipitation, and relative humidity as inputs. ANN3 performs better than other ANN models with an R2 of 0.8446 and RMSE of 1.4595 MJm−2d−1. Likewise, stepwise linear regression performs better than other ML models with an R2 of 0.8870 and RMSE of 1.5143 MJm−2d−1. Thus, the model developed by Fan et al. is recommended to estimate daily GSR in the region where only ambient temperature data are available. Similarly, a more robust ANN3 and stepwise linear regression models are recommended to estimate daily GSR in the region where data about sunshine duration, maximum and minimum ambient temperature, precipitation, and relative humidity are available.

scholarly journals Global solar radiation modeling using different machine learning and empirical models in Northeast China

2021 ◽  
Author(s):  
Yue Jia ◽  
Yongjun Su ◽  
Fengchun Wang ◽  
Pengcheng Li ◽  
Shuyi Huo
Keyword(s):  
Machine Learning ◽  
Solar Radiation ◽  
Solar Energy ◽  
Northeast China ◽  
Sunshine Duration ◽  
Meteorological Data ◽  
Global Solar Radiation ◽  
Empirical Models ◽  
Learning Models ◽  
Machine Learning Models

Abstract Reliable global solar radiation (Rs) information is crucial for the design and management of solar energy systems for agricultural and industrial production. However, Rs measurements are unavailable in many regions of the world, which impedes the development and application of solar energy. To accurately estimate Rs, this study developed a novel machine learning model, called a Gaussian exponential model (GEM), for daily global Rs estimation. The GEM was compared with four other machine learning models and two empirical models to assess its applicability using daily meteorological data from 1997–2016 from four stations in Northeast China. The results showed that the GEM with complete inputs had the best performance. Machine learning models provided better estimates than empirical models when trained by the same input data. Sunshine duration was the most effective factor determining the accuracy of the machine learning models. Overall, the GEM with complete inputs had the highest accuracy and is recommended for modeling daily Rs in Northeast China.

scholarly journals General Formula for Estimation of Monthly Mean Global Solar Radiation in Different Climates on the South and North Coasts of Iran

2007 ◽  
Vol 2007 ◽  
pp. 1-7 ◽  
Author(s):  
Ali A. Sabziparvar
Keyword(s):  
Relative Humidity ◽  
Solar Radiation ◽  
General Formula ◽  
Sunshine Duration ◽  
Global Radiation ◽  
Global Solar Radiation ◽  
Maximum Temperature ◽  
The South ◽  
Coastal Regions ◽  
Different Climates

Using sunshine duration, cloud cover, relative humidity, average of maximum temperature, and ground albedo as the input of several radiation models, the monthly average daily solar radiation on horizontal surface in various coastal cities of the South (25.23∘N) and the North (38.42∘N) of Iran are estimated. Several radiation models are tested and further are revised by taking into consideration the effects of relative humidity, ground albedo, and Sun-Earth distance. Model validation is performed by using up to 13 years (1988–2000) of daily solar observations. Errors are calculated using MBE, MABE, MPE, and RMSE statistical criteria (see nomenclature) and further a general formula which estimates the global radiation in different climates of coastal regions is suggested. The proposed method shows a good agreement (less than7%deviation) with the long-term pyranometric data. In comparison with other works done so far, the suggested method performs a higher degree of accuracy for those of two regions. The model results can be extended to other locations in coastal regions where solar data are not available.

scholarly journals Influence of Sunshine Hour and Relative Humidity on Total Solar Radiation at Nepalganj, Nepal

Patan Pragya ◽  
2020 ◽  
Vol 6 (1) ◽  
pp. 97-104
Author(s):  
Usha Joshi ◽  
P. M. Shrestha ◽  
I. B. Karki ◽  
N. P. Chapagain ◽  
K. N. Poudyal
Keyword(s):  
Relative Humidity ◽  
Solar Radiation ◽  
Meteorological Parameters ◽  
Clean Energy ◽  
Empirical Models ◽  
Energy Resources ◽  
Total Solar Radiation ◽  
Sunshine Hour ◽  
Empirical Constants ◽  
Better Than

The solar energy is the abundantly available free and clean energy resources in Nepal. There are more than 300 sunny days because of Nepal lies in solar zone in a global map. The total solar radiation was measured by using CMP6 pyranometer at Nepalgunj (lat.:28.10oN, long.: 81.67oEand Alt. 165.0masl). The main objective of this study is to select the better empirical model and its empirical constants for the prediction of TSR for the year come. In this research, six different empirical models and meteorological parameters are utilized in the presence of regression technique for the years 2011 and 2012. Finally the different empirical constants are found. After the error analysis, the Swarthman-Oguniade model is found to perform better than others models. So the empirical constants of this model is utilized to predict the TSR of similar geographical sites of Nepal.

scholarly journals Prediction of daily global solar radiation using different empirical models on the basis of meteorological parameters at Trans Himalaya Region, Nepal

BIBECHANA ◽  
2021 ◽  
Vol 18 (1) ◽  
pp. 159-169
Author(s):  
Usha Joshi ◽  
I B Karki ◽  
N P Chapagain ◽  
K N Poudyal
Keyword(s):  
Relative Humidity ◽  
Solar Radiation ◽  
Meteorological Parameters ◽  
Energy Resource ◽  
Global Solar Radiation ◽  
Empirical Models ◽  
Mean Bias Error ◽  
Percentage Error ◽  
Sunshine Hour ◽  
Empirical Constants

Global Solar Radiation (GSR) is the cleanest and freely available energy resource on the earth.  GSR  was measured for six years (2010 -2015) at the horizontal surface using calibrated first-class CMP6 pyranometer at Kathmandu (Lat. 27.70o N, Long. 85.5oE and Alt. 1350m). This paper explains the daily, monthly, and seasonal variations of GSR and also compares with sunshine hour, ambient temperature, relative humidity, and precipitation to GSR. The annual average global solar radiation is about 4.16 kWh/m2/day which is a significant amount to promote solar active and passive energy technologies at the Trans-Himalaya region. In this study, the meteorological parameters are utilized in the regression technique for four different empirical models and finally, the empirical constants are found. Thus obtained coefficients are utilized to predict the GSR using meteorological parameters for the years to come. In addition, the predicted GSR is found to be closer to the measured value of GSR. The values are justified by using statistical tools such as coefficient of determination (R2), root mean square error (RMSE), mean percentage error (MPE), and mean bias error (MBE). Finally, the values of R2, RMSE, MPE, and MBE are found to be 0.792, 1.405, -1.014, and 0.011, respectively for the model (D), which are based on sunshine hour, temperature and relative humidity. In this model, the empirical constants, a = 0.155, b = 0.134, c = 0.014 and d = 0.0007 are determined which can be utilized at the similar geographical locations of Nepal. BIBECHANA 18 (2021) 159-169

Machine Learning Models Based on Random Forest Feature Selection and Bayesian Optimization for Predicting Daily Global Solar Radiation

2021 ◽  
Vol 11 (1) ◽  
pp. 309-323
Author(s):  
Mohamed Chaibi ◽  
El Mahjoub Benghoulam ◽  
Lhoussaine Tarik ◽  
Mohamed Berrada ◽  
Abdellah El Hmaidi
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Random Forest ◽  
Solar Radiation ◽  
Predictive Accuracy ◽  
Sunshine Duration ◽  
Computational Cost ◽  
Global Solar Radiation ◽  
Bayesian Optimization ◽  
Support Vector

Prediction of daily global solar radiation  with simple and highly accurate models would be beneficial for solar energy conversion systems. In this paper, we proposed a hybrid machine learning methodology integrating two feature selection methods and a Bayesian optimization algorithm to predict H in the city of Fez, Morocco. First, we identified the most significant predictors using two Random Forest methods of feature importance: Mean Decrease in Impurity (MDI) and Mean Decrease in Accuracy (MDA). Then, based on the feature selection results, ten models were developed and compared: (1) five standalone machine learning (ML) models including Classification and Regression Trees (CART), Random Forests (RF), Bagged Trees Regression (BTR), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP); and (2) the same models tuned by the Bayesian optimization (BO) algorithm: CART-BO, RF-BO, BTR-BO, SVR-BO, and MLP-BO. Both MDI and MDA techniques revealed that extraterrestrial solar radiation and sunshine duration fraction were the most influential features. The BO approach improved the predictive accuracy of MLP, CART, SVR, and BTR models and prevented the CART model from overfitting. The best improvements were obtained using the MLP model, where RMSE and MAE were reduced by 17.6% and 17.2%, respectively. Among the studied models, the SVR-BO algorithm provided the best trade-off between prediction accuracy (RMSE=0.4473kWh/m²/day, MAE=0.3381kWh/m²/day, and R²=0.9465), stability (with a 0.0033kWh/m²/day increase in RMSE), and computational cost.

Evaluation of temperature-based machine learning and empirical models for predicting daily global solar radiation

2019 ◽  
Vol 198 ◽  
pp. 111780 ◽  
Author(s):  
Yu Feng ◽  
Daozhi Gong ◽  
Qingwen Zhang ◽  
Shouzheng Jiang ◽  
Lu Zhao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Solar Radiation ◽  
Global Solar Radiation ◽  
Empirical Models

scholarly journals Empirical Models for the Evaluation of Global Solar Radiation in the Different Sites of Nepal

2019 ◽  
Vol 5 (1) ◽  
pp. 67-73
Author(s):  
B. P. Pant ◽  
K. N. Poudyal ◽  
B. Acharya ◽  
B. Budha
Keyword(s):  
Solar Radiation ◽  
Alternative Energy ◽  
Meteorological Parameters ◽  
Global Solar Radiation ◽  
Vital Role ◽  
Empirical Models ◽  
Model Order ◽  
The Earth ◽  
Good Possibility ◽  
Better Than

To operate many phenomenon’s on the earth surface such as physical, chemical and biological process solar radiation plays vital role. A common practice is to estimate average daily global solar radiation (GSR) using appropriate empirical models for the areas lacking the actual measured values. In this context several single and multiple meteorological parameters were selected to estimate the GSR for Jumla, Nepalgunj and Kathmandu. In order to validate the selected models various statistical test were employed. The selected models were compared on the basis of statistical errors. In the statistical analysis the value of root mean square error (RMSE) and coefficient o determination R2 is found to 0.15.0.23, 0.26 and 0.98, 0.96, 0.96 respectively for Jumla, Nepalgunj and Kathmandu in Samuel model. These values were comparatively better than other models. It is concluded that Samuel model (order three) is the best among the used models. The established result uncover that there is a good possibility of solar energy as a alternative energy source in Nepal.

scholarly journals Performance evaluation of existing sunshine-based computing models for estimating global solar radiation at Lagos, Nigeria

2017 ◽  
Vol 5 (2) ◽  
pp. 106
Author(s):  
Samuel Nwokolo ◽  
Julie Ogbulezie
Keyword(s):  
Performance Evaluation ◽  
Solar Radiation ◽  
Sunshine Duration ◽  
Global Solar Radiation ◽  
Empirical Models ◽  
Environmental Research ◽  
Substantial Cost ◽  
Radiation Data ◽  
Statistical Indicators ◽  
Computing Models

Several empirical models have been fitted in literature for estimating global solar radiation across the globe in order to produce global solar radiation data and also as a baseline for further scientific and environmental research without the substantial cost of instrumental network that would otherwise be needed. However, peers and researchers have reported that the most commonly employed parameter for predicting global solar radiation is sunshine duration as a result of its availability and simplicity in course of measurement globally. In this research, the author considered the performance of 63 sunshine-based models for the prediction of global solar radiation at Lagos, Nigeria. Numerous models are found unreliable for use in this location, and others vary in performance. On the whole, the best model was identified due to its values of statistical indicators.

Sign in / Sign up

Export Citation Format

Share Document