Predicting Global Solar Radiation Using an Artificial Neural Network Single‐Parameter Model

Angela, Karoro; Ssenyonga, Taddeo; James, Mubiru

doi:10.1155/2011/751908

Cited by 26 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, Karoro and other authors proposed in their study an ANN to predict daily global solar radiation in a matter of monthly average values on a horizontal surface in Kampala, Uganda depending on a single feature which is the sunshine duration. Applying 65 neurons with tansig transfer function gave the best results in this study [8]. When it comes to hourly solar radiation, it's rare to find HGSR prediction studies.…”

Section: Introductionmentioning

confidence: 70%

Hourly Global Solar Radiation Estimation Based on Machine Learning Methods in Eskisehir

Alsafadi¹,

Filik²

2020

Eskişehir Technical University Journal of Science and Technology a - Applied Sciences and Engineering

View full text Add to dashboard Cite

Due to the increasing importance of knowing the amount of global solar radiation (GSR) that is incident on solar panels; short term data, such as hourly global solar radiation (HGSR), is essentially required to obtain more accurate and reliable power generation prediction. Nowadays, Machine Learning (ML) methods are becoming a huge trend for data forecasting. Therefore, in this paper, a comparison between Collares-Pereira & Rabl empirical model modified by Gueymard (CPRG) and ML methods for HGSR estimation in Eskişehir city in Turkey is conducted. Artificial Neural Network (ANN), Regression Tree (RT), and Support Vector Regression (SVR) are ML methods that are used to predict HGSR. Besides, hourly metrological and geographical parameters for the year 2014 are taken as inputs in the training models. The inputs are solar time, solar hour angle, Julian day number, daily GSR, longitude, latitude, hourly average humidity, hourly temperature, and hourly pressure. To demonstrate these techniques, a comparison is implemented using MATLAB software with the help of existing toolboxes. Finally, this study proves that ML methods outperform the CPRG model, not to mention they have far more accurate results.Although almost all ML models gave similar results, SVR was the best among them with a correlation coefficient of 0.979532 for the training set and 0.978244 for the testing set. In a nutshell, ML are very efficient methods in that should be taken into consideration to perfectly estimate HGSR.

show abstract

Section: Introductionmentioning

confidence: 70%

Hourly Global Solar Radiation Estimation Based on Machine Learning Methods in Eskisehir

Alsafadi¹,

Filik²

2020

Eskişehir Technical University Journal of Science and Technology a - Applied Sciences and Engineering

View full text Add to dashboard Cite

show abstract

“…The utilisation of solar energy g l o b a l l y has increased because it is clean and abundant renewable energy, whereas nearly all potential sources of hydro-electric energy i n U g a n d a have been developed (Kandirmaz et al, 2014;Wald & Wald, 2018). Studies to measure or predict solar irradiation have been carried out in U g a n d a a n d o t h e r parts of the world (Angela et al, 2011;Kent et al, 2016;Laidi et al, 2018). Consequently, solar irradiation data availability for more locations in Uganda is destined to increase.…”

Section: Introductionmentioning

confidence: 99%

An inverse artificial neural network algorithm for retrieval of sunshine hours from ground-based global solar irradiation measurements

Nzala¹,

Muyimbwa²,

Ssebiyonga³

et al. 2022

EAJSTI

View full text Add to dashboard Cite

Availability of meteorological parameter values is important in applications that require solar irradiation. Meteorological parameters such as sunshine hours are best provided by measuring equipment mainly stationed at weather stations. The cost of purchasing the measuring equipment, and setting up and maintaining weather stations is enormous and cannot be easily afforded by many developing countries like Uganda. Furthermore, in Uganda, we have some weather stations which have been measuring global horizontal solar irradiation for quite some time but lacked sunshine duration sensors, and at some others, the sunshine measuring equipment malfunctioned. In this work we present an inverse artificial neural network algorithm that predicts sunshine hours based on horizontal global solar irradiation, the algorithm caters to cases where global horizontal solar irradiation is present but sunshine hour measuring equipment is missing or malfunctioned. A radial basis function neural network (RBF-NN) was trained for forward computation of global horizontal solar irradiation from sunshine hour values. The inverse modelling algorithm employs multidimensional unconstrained non-linear optimization to retrieve sunshine hours. The correlation coefficient (r) between the measured sunshine hour values and those predicted by the inverse artificial neural network algorithm was found to be 0.924. The average value of the ratios of the inverse artificial neural network algorithm computed values to the sunshine duration sensor measurements was 1.043. The algorithm predicted sunshine hour values with a mean bias and relative root mean square error of 0.043 and 0.394, respectively. The algorithm developed provides an affordable, fast and reliable method for determining sunshine hour values based on global horizontal solar irradiation. However, sunshine hour values prediction for low values of global horizontal solar irradiation was less precise, and this could be attributed to high levels of cloudiness. It is recommended that an inverse algorithm that retrieves sunshine hours under cloudy conditions be constructed

show abstract

“…A surfeit of studies applied ML based DDMs to forecast solar irradiance [7], which included the classical and hybrid approaches [8]. MLMs, including SVR [9], ANN [10][11][12], random forest, and gradient boosted regression [9], were commonly implemented in classical approaches [8]. Li et al.…”

Section: Introductionmentioning

confidence: 99%

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

Sibtain

Saleem

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Accuracy of solar irradiance forecasting is imperative for the effective utilization and integration of solar energy into the power system. To forecast global horizontal irradiance based on a multivariate meteorological data; this study first evaluates five standalone models, including recurrent deterministic policy gradient (RDPG), long short term memory (LSTM) neural network, extreme gradient boosting (XGB), Gaussian process regression (GPR), and support vector regression (SVR). The RDPG model outperforms the standalone counterparts by demonstrating 2.485 W/m 2 , 20.591 W/m 2 , 18.316 W/m 2 , and 23.176 W/m 2 reductions in RMSE compared to the LSTM, XGB, GPR, and SVR models. Afterward, the performance of the RDPG model is further enhanced, by developing two-stage hybrid models, including improved complete ensemble empirical mode decomposition with additive noise-RDPG (ICEEMDAN-RDPG) and variational mode decomposition-RDPG (VMD-RDPG). The subsequent construction of the hybrid model ICEEMDAN-SE-VMD-RDPG (ISVR) results in the further improvement of the two-stage hybrid models. The ISVR surpasses all the established models including VMD-RDPG, ICEEMDAN-RDPG, RDPG, LSTM, XGB, GPR, and SVR by displaying 18.401 W/m 2 , 13.908 W/m 2 , 33.223 W/m 2 , 53.111 W/m 2 , 67.704 W/m 2 , 67.502 W/m 2 and 69.943 W/m 2 , respectively, decrease in RMSE. The overall results are enlightening and reveal the extension feasibility of the IVSR model for the other forecasting tasks, e.g., renewable energy integration and electrical load forecasting. INDEX TERMS Solar irradiance forecasting, decomposition techniques, sample entropy, correlation, deep reinforcement learning.

show abstract

Predicting Global Solar Radiation Using an Artificial Neural Network Single‐Parameter Model

Cited by 26 publications

References 18 publications

Hourly Global Solar Radiation Estimation Based on Machine Learning Methods in Eskisehir

Hourly Global Solar Radiation Estimation Based on Machine Learning Methods in Eskisehir

An inverse artificial neural network algorithm for retrieval of sunshine hours from ground-based global solar irradiation measurements

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

Contact Info

Product

Resources

About