Predicting daily diffuse horizontal solar radiation in various climatic regions of China using support vector machine and tree-based soft computing models with local and extrinsic climatic data

Abstract Knowledge of diffuse horizontal solar radiation (Rd) on horizontal surfaces is a prerequisite for the design and optimization of active and passive solar energy systems such as the solar illumination system within a building, but it is unavailable in many worldwide locations and commonly predicted by readily available climatic variables. However, reliable prediction of Rd is difficult when lack of complete or previous climatic data at the target station. This study evaluated the performance of support vector machine (SVM) and four tree-based soft computing models, i.e. M5 model tree (M5Tree), random forest (RF), extreme gradient boosting (XGBoost) and gradient boosting with categorical features support (CatBoost), for prediction of daily horizontal Rd when using limited local (Scenario 1) and extrinsic (Scenarios 2 and 3) climatic data. Six input combinations of daily global solar radiation (Rs), sunshine hour (n), maximum/minimum temperature (Tmax/Tmin) and relative humidity (RH) during 1996–2015 at 15 weather stations across various climatic rons of China were considered. The results demonstrated that, when lack of Rs, the average root mean square error (RMSE) was considerably increased across China (42.4%) in Scenario 1, especially in the (sub)tropical monsoon ron (68.3%). SVM offered the best combination of prediction accuracy and generalization capability in all scenarios, followed by CatBoost. CatBoost produced the closest daily Rd estimates to SVM and satisfactory generalization capability. In Scenario 2, CatBoost and SVM models developed with climatic data from Beijing gave the overall best daily Rd estimates over the 15 stations, while models developed with data from 14 weather stations in Scenario 3 produced even better and steadier Rd estimates across China compared with those in Scenario 2. The average computational time of SVM (6.6 s) for a single sample was approximately 1.9 times that of CatBoost (3.5 s) in Scenarios 1 and 2, while the corresponding value (842.6 s) was approximately 33.9 times that of CatBoost (24.9 s) in Scenario 3. Comprehensively considering prediction accuracy, generalization capability and computational efficiency, CatBoost is highly recommended to develop general models for daily Rd prediction in various climatic rons of China, particularly when lack of previous local climatic data.

[1]  S. C. Kaushik,et al.  Assessment of diffuse solar energy under general sky condition using artificial neural network , 2009 .

[2]  Ozgur Kisi,et al.  Local vs. external training of neuro-fuzzy and neural networks models for estimating reference evapotranspiration assessed through k-fold testing , 2015 .

[3]  A. A. El-Sebaii,et al.  Estimation of horizontal diffuse solar radiation in Egypt , 2003 .

[4]  M. Iqbal,et al.  Correlation of average diffuse and beam radiation with hours of bright sunshine , 1979 .

[5]  Farid Melgani,et al.  Multi-step ahead forecasting of daily global and direct solar radiation: A review and case study of Ghardaia region , 2018, Journal of Cleaner Production.

[6]  Jie Xia,et al.  Application of a new information priority accumulated grey model with time power to predict short-term wind turbine capacity , 2019, Journal of Cleaner Production.

[7]  Lifeng Wu,et al.  Daily reference evapotranspiration prediction based on hybridized extreme learning machine model with bio-inspired optimization algorithms: Application in contrasting climates of China , 2019, Journal of Hydrology.

[8]  Kadir Bakirci,et al.  Models for the estimation of diffuse solar radiation for typical cities in Turkey , 2015 .

[9]  Weibin Ma,et al.  Estimating monthly average daily diffuse solar radiation with multiple predictors: A case study , 2011 .

[10]  Hui Li,et al.  Pan evaporation modeling using six different heuristic computing methods in different climates of China , 2017 .

[11]  ESTIMATION OF DIFFUSE SOLAR RADIATION IN THE NORTH AND FAR NORTH OF CAMEROON , 2013 .

[12]  Lifeng Wu,et al.  Potential of kernel-based nonlinear extension of Arps decline model and gradient boosting with categorical features support for predicting daily global solar radiation in humid regions , 2019, Energy Conversion and Management.

[13]  Elizabeta Lazarevska,et al.  A neuro-fuzzy model of the solar diffuse radiation with relevance vector machine , 2011, 11th International Conference on Electrical Power Quality and Utilisation.

[14]  Lifeng Wu,et al.  Evaluating the effect of air pollution on global and diffuse solar radiation prediction using support vector machine modeling based on sunshine duration and air temperature , 2018, Renewable and Sustainable Energy Reviews.

[15]  Lawrence L. Kazmerski,et al.  Solar energy dust and soiling R&D progress: Literature review update for 2016 , 2018 .

[16]  Lifeng Wu,et al.  Hybrid support vector machines with heuristic algorithms for prediction of daily diffuse solar radiation in air-polluted regions , 2020 .

[17]  Mohamed Mohandes,et al.  Splitting Global Solar Radiation into Diffuse and Direct Normal Fractions Using Artificial Neural Networks , 2012 .

[18]  H. Cai,et al.  Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China , 2018, Agricultural and Forest Meteorology.

[19]  Laurel Saito,et al.  Estimating daily global solar radiation by day of the year in six cities located in the Yucatán Peninsula, Mexico , 2017 .

[20]  R. Saidur,et al.  Application of support vector machine models for forecasting solar and wind energy resources: A review , 2018, Journal of Cleaner Production.

[21]  Xurong Mei,et al.  Evaluation of temperature-based global solar radiation models in China , 2009 .

[22]  Junliang Fan,et al.  Spatiotemporal trends of temperature and precipitation extremes across contrasting climatic zones of China during 1956–2015 , 2019, Theoretical and Applied Climatology.

[23]  G. Abal,et al.  Performance of empirical models for diffuse fraction in Uruguay , 2017 .

[24]  B. E. Psiloglou,et al.  Meteorological Radiation Model (MRM v6.1): Improvements in diffuse radiation estimates and a new approach for implementation of cloud products , 2017 .

[25]  Lifeng Wu,et al.  Daily pan evaporation modeling from local and cross-station data using three tree-based machine learning models , 2018, Journal of Hydrology.

[26]  Yingni Jiang,et al.  Prediction of monthly mean daily diffuse solar radiation using artificial neural networks and comparison with other empirical models , 2008 .

[27]  Anna Veronika Dorogush,et al.  CatBoost: gradient boosting with categorical features support , 2018, ArXiv.

[28]  Mamdouh El Haj Assad,et al.  Comparison of artificial intelligence methods in estimation of daily global solar radiation , 2018, Journal of Cleaner Production.

[29]  Muhammed A. Hassan,et al.  Exploring the potential of tree-based ensemble methods in solar radiation modeling , 2017 .

[30]  Lifeng Wu,et al.  Empirical and machine learning models for predicting daily global solar radiation from sunshine duration: A review and case study in China , 2019, Renewable and Sustainable Energy Reviews.

[31]  Milan Despotovic,et al.  Review and statistical analysis of different global solar radiation sunshine models , 2015 .

[32]  O. Kisi.  Pan evaporation modeling using least square support vector machine, multivariate adaptive regression splines and M5 model tree , 2015 .

[33]  B. E. Psiloglou,et al.  Recent improvements of the Meteorological Radiation Model for solar irradiance estimates under all-sky conditions , 2016 .

[34]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[35]  Xin Ma,et al.  Evaluation and development of empirical models for estimating daily and monthly mean daily diffuse horizontal solar radiation for different climatic regions of China , 2019, Renewable and Sustainable Energy Reviews.

[36]  T. E. Boukelia,et al.  General models for estimation of the monthly mean daily diffuse solar radiation (Case study: Algeria) , 2014 .

[37]  C. C. Enweremadu,et al.  Prediction of global horizontal solar irradiance in Zimbabwe using artificial neural networks , 2016 .

[38]  Dennis Y.C. Leung,et al.  A review on the energy production, consumption, and prospect of renewable energy in China , 2003 .

[39]  Yagob Dinpashoh,et al.  Evaluation and development of empirical models for estimating daily solar radiation , 2017 .

[40]  Ricardo Nicolau Nassar Koury,et al.  Prediction of hourly solar radiation in Abu Musa Island using machine learning algorithms , 2018 .

[41]  Por Lip Yee,et al.  Estimating the diffuse solar radiation using a coupled support vector machine–wavelet transform model , 2016 .

[42]  Danny H.W. Li,et al.  Prediction of diffuse solar irradiance using machine learning and multivariable regression , 2016 .

[43]  M. EL-Shimy,et al.  A new empirical model for forecasting the diffuse solar radiation over Sahara in the Algerian Big South , 2018 .

[44]  P. C. Jain.  A model for diffuse and global irradiation on horizontal surfaces , 1990 .

[45]  Yingni Jiang,et al.  Estimation of monthly mean daily diffuse radiation in China , 2009 .

[46]  Xin Ma,et al.  Carbon-dioxide mitigation in the residential building sector: A household scale-based assessment , 2019, Energy Conversion and Management.

[47]  Indira Karakoti,et al.  Predicting monthly mean daily diffuse radiation for India , 2012 .

[48]  Arif Hepbasli,et al.  Estimating the horizontal diffuse solar radiation over the Central Anatolia Region of Turkey , 2006 .

[49]  Carlo Renno,et al.  ANN model for predicting the direct normal irradiance and the global radiation for a solar application to a residential building , 2016 .

[50]  A. T. Siddiqui,et al.  Generalized models for estimation of diffuse solar radiation based on clearness index and sunshine duration in India: Applicability under different climatic zones , 2017 .

[51]  Chanchal Kumar Pandey,et al.  A comparative study to estimate daily diffuse solar radiation over India , 2009 .

[52]  Xinhua Xue,et al.  Prediction of daily diffuse solar radiation using artificial neural networks , 2017 .

[53]  Ravinesh C. Deo,et al.  Global solar radiation prediction by ANN integrated with European Centre for medium range weather forecast fields in solar rich cities of Queensland Australia , 2019, Journal of Cleaner Production.

[54]  Indira Karakoti,et al.  Evaluation of different diffuse radiation models for Indian stations and predicting the best fit model , 2011 .

[55]  Wei Gong,et al.  Evaluation of sunshine-based models for predicting diffuse solar radiation in China , 2018, Renewable and Sustainable Energy Reviews.

[56]  C. G. Ozoegwu,et al.  Artificial neural network forecast of monthly mean daily global solar radiation of selected locations based on time series and month number , 2019, Journal of Cleaner Production.

[57]  Shengjun Wu,et al.  Assessing the transferability of support vector machine model for estimation of global solar radiation from air temperature , 2015 .

[58]  Benjamin Y. H. Liu,et al.  The interrelationship and characteristic distribution of direct, diffuse and total solar radiation , 1960 .

[59]  Yu Feng,et al.  Comparison of artificial intelligence and empirical models for estimation of daily diffuse solar radiation in North China Plain , 2017 .

[60]  Shahaboddin Shamshirband,et al.  Determining the most important variables for diffuse solar radiation prediction using adaptive neuro-fuzzy methodology; case study: City of Kerman, Iran , 2016 .

[61]  Ningbo Cui,et al.  Development of data-driven models for prediction of daily global horizontal irradiance in Northwest China , 2019, Journal of Cleaner Production.

[62]  Hamdy K. Elminir,et al.  Prediction of hourly and daily diffuse fraction using neural network, as compared to linear regression models , 2007 .

[63]  Ram Gopal Raj,et al.  The artificial neural network for solar radiation prediction and designing solar systems: a systematic literature review , 2015 .

[64]  Hongbin Liu,et al.  General models for estimating daily global solar radiation for different solar radiation zones in mainland China , 2013 .

[65]  Jianping Yang,et al.  Estimation of horizontal diffuse solar radiation with measured daily data in China , 2004 .

[66]  Basharat Jamil,et al.  Comparison of empirical models to estimate monthly mean diffuse solar radiation from measured data: Case study for humid-subtropical climatic region of India , 2017 .

[67]  Yusuf Al-Turki,et al.  Investigating the performance of support vector machine and artificial neural networks in predicting solar radiation on a tilted surface: Saudi Arabia case study , 2015 .