Estimation of the daily global solar radiation based on the Gaussian process regression methodology in the Saharan climate

Guermoui, Mawloud; Gairaa, Kacem; Rabehi, Abdelaziz; Djafer, Djelloul; Benkaciali, Saïd

doi:10.1140/epjp/i2018-12029-7

Cited by 41 publications

(17 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the performances are comparable or better than those obtained in [21,22,[24][25][26]. On the other hand, they are worse than those reported in [23,27].…”

Section: Feature Re-examination Of Ligtgbmmentioning

confidence: 52%

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

et al. 2021

View full text Add to dashboard Cite

Machine learning (ML) models are commonly used in solar modeling due to their high predictive accuracy. However, the predictions of these models are difficult to explain and trust. This paper aims to demonstrate the utility of two interpretation techniques to explain and improve the predictions of ML models. We compared first the predictive performance of Light Gradient Boosting (LightGBM) with three benchmark models, including multilayer perceptron (MLP), multiple linear regression (MLR), and support-vector regression (SVR), for estimating the global solar radiation (H) in the city of Fez, Morocco. Then, the predictions of the most accurate model were explained by two model-agnostic explanation techniques: permutation feature importance (PFI) and Shapley additive explanations (SHAP). The results indicated that LightGBM (R2 = 0.9377, RMSE = 0.4827 kWh/m2, MAE = 0.3614 kWh/m2) provides similar predictive accuracy as SVR, and outperformed MLP and MLR in the testing stage. Both PFI and SHAP methods showed that extraterrestrial solar radiation (H0) and sunshine duration fraction (SF) are the two most important parameters that affect H estimation. Moreover, the SHAP method established how each feature influences the LightGBM estimations. The predictive accuracy of the LightGBM model was further improved slightly after re-examination of features, where the model combining H0, SF, and RH was better than the model with all features.

show abstract

“…For instance, the performances are comparable or better than those obtained in [21,22,[24][25][26]. On the other hand, they are worse than those reported in [23,27].…”

Section: Feature Re-examination Of Ligtgbmmentioning

confidence: 52%

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Lack of a swift, accurate and easily done predictive tool, which can directly correlate the main parameters of this technology and predict the efficiencies of the system based on main parameters only, was an essence need. This paper pioneers in bringing the Gaussian Process Regression (GPR), which has been applied to a wide range of fields [17][18][19][20][21][22][23][24][25] , as a predictive tool to investigate the performance of a solar/waste energy driven dehumidification/regeneration cycle, as well as, to introduce a new application for GPR. This, to the authors' knowledge, is the first statistical modeling study that applies GPR to investigate the performance of dehumidification systems.…”

Section: Nomenclature Dmentioning

confidence: 99%

Statistical investigation of a dehumidification system performance using Gaussian process regression

Akhlaghi

Zhao

Shittu

et al. 2019

Energy and Buildings

View full text Add to dashboard Cite

Swift performance assessment of dehumidification systems, in design stage and while operation of the system is of substantial importance for commercialization and wide implementation of this technology. This paper presents a novel statistical model, employing Gaussian Process Regression (GPR) to investigate performance of a solar/waste energy driven dehumidification/regeneration cycle with a solid adsorbent bed. The statistical model takes thousands of operating conditions derived from a numerical model to predict the performance of the system. This predictive tool directly correlates the main operating parameters with the performance parameters of the system. The operating parameters considered in this study are: temperature, relative humidity and flow rate of process air, temperature of regeneration air, length of the desiccant bed, solar radiation intensity and operating time, and the selected performance parameters are: moisture extraction efficiency for the dehumidification cycle and moisture removal efficiency for the regeneration cycle. The model is evaluated by three metrics, namely: root mean square error (RSME), mean absolute percentage error (MAPE), and coefficient of determination (R 2). The maximum RSME and MAPE for moisture extraction are only 0.045, 0.21%, and for moisture removal efficiencies are 0.082 and 0.39%, respectively, while the R 2 value is derived as 0.97. The developed model is used to investigate the impact of four selected operating parameters on system performance. Additionally, the system performance is predicted for randomly generated operating conditions as well as warm and humid climates. The developed GPR model provides a swift and highly accurate predictive tool for design of the dehumidification systems and for commercialization of the investigated dehumidification systems.

show abstract

“…Support vector machine can be implemented as SVR for regression problems. The solar radiation forecasting tasks were also implemented by employing models including XGB [19,20] and GPR [21,22]. The popularity of the GPR model has increased over recent years.…”

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

Estimation of the daily global solar radiation based on the Gaussian process regression methodology in the Saharan climate

Cited by 41 publications

References 32 publications

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

Statistical investigation of a dehumidification system performance using Gaussian process regression

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

Contact Info

Product

Resources

About