banner
Home > Open Journal Systems

Models for estimation of solar irradiance in Zimbabwe: A statistical and machine learning approach

Kudzanayi Chiteka, Rejoice Mwarazi, Rajesh Arora, Christopher Enweremadu

Abstract


The present study focused on the statistical development of solar irradiance predictive models for locations with limited solar irradiance measuring equipment. Multiple linear regression models were developed using both measured and satellite corrected meteorological data. The study chose easy to measure and access meteorological data for analysis and modelling. Multicollinearity and correlation analysis were performed to analyse the relationships among the independent and dependent variables. Statistical predictive models were developed, and the prediction accuracy of the developed models was analysed using the coefficient of determination (R2) and the Mean Absolute Percentage Error (MAPE). The results revealed a higher performance of the developed models compared to generic empirical models. The prediction MAPE for the three models developed were respectively 0.117 kWh/m2, 0.132 kWh/m2 and 0.044 kWh/m2 for Hg, Hb and Hd. The models also had R2 values of 0.895, 0.972 and 0.993 respectively for global horizontal irradiance (Hg), direct normal irradiance (Hb) and diffuse irradiance (Hd). The developed models outperformed the generic models by a minimum of 5.74%. The study showed that it is more accurate to predict Global Horizontal Irradiance by summing the predicted component of Hb and Hd.


Keywords


solar irradiance; irradiance prediction; predictive modelling; meteorological parameters; regression analysis

Full Text:

PDF

References


1. Eitan A. Promoting renewable energy to cope with climate change—Policy discourse in Israel. Sustainability 2021; 13(6): 3170. doi: 10.3390/su13063170

2. Jamil B, Bellos E. Development of empirical models for estimation of global solar radiation exergy in India. Journal of Cleaner Production 2019; 207: 1–16. doi: 10.1016/j.jclepro.2018.09.246

3. Li D, Heimeriks G, Alkemade F. The emergence of renewable energy technologies at country level: Relatedness, international knowledge spillovers and domestic energy markets. Industry and Innovation 2020; 27(9): 991–1013. doi: 10.1080/13662716.2020.1713734

4. Müller R, Pfeifroth U. Remote Sensing of solar surface radiation—A reflection of concepts, applications and input data based on experience with the effective cloud albedo. Atmospheric Measurement Techniques 2022; 15(5): 1537–1561. doi: 10.5194/amt-15-1537-2022

5. Liu P, Tong X, Zhang J, et al. Estimation of half-hourly diffuse solar radiation over a mixed plantation in north China. Renewable Energy 2020; 149: 1360–1369. doi: 10.1016/j.renene.2019.10.136

6. Nunez Munoz M, Ballantyne EEF, Stone DA. Development and evaluation of empirical models for the estimation of hourly horizontal diffuse solar irradiance in the United Kingdom. Energy 2022; 241: 122820. doi: 10.1016/j.energy.2021.122820

7. El Mghouchi Y, El Bouardi A, Choulli Z, Ajzoul T. Models for obtaining the daily direct, diffuse and global solar radiations. Renewable and Sustainable Energy Reviews 2016; 56: 87–99. doi: 10.1016/j.rser.2015.11.044

8. Ye H, Yang B, Han Y, Chen N. State-of-the-art solar energy forecasting approaches: Critical potentials and challenges. Frontiers in Energy Research 2022; 10: 875790. doi: 10.3389/fenrg.2022.875790

9. Liu BYH, Jordan RC. The interrelationship and characteristic distribution of direct, diffuse and total solar radiation. Solar Energy 1960; 4(3): 1–19. doi: 10.1016/0038-092X(60)90062-1

10. Collares-Pereira M, Rabl A. The average distribution of solar radiation-correlations between diffuse and hemispherical and between daily and hourly insolation values. Solar Energy 1979; 22(2): 155–164. doi: 10.1016/0038-092X(79)90100-2

11. Mecibah MS, Boukelia TE, Tahtah R, Gairaa K. Introducing the best model for estimation the monthly mean daily global solar radiation on a horizontal surface (Case study: Algeria). Renewable and Sustainable Energy Reviews 2014; 36: 194–202. doi: 10.1016/j.rser.2014.04.054

12. Dal Pai A, Escobedo JF, Dal Pai E, dos Santos CM. Estimation of hourly, daily and monthly mean diffuse radiation based on MEO shadowring correction. Energy Procedia 2014; 57: 1150–1159. doi: 10.1016/j.egypro.2014.10.102

13. Feng Y, Cui N, Zhang Q, et al. Comparison of artificial intelligence and empirical models for estimation of daily diffuse solar radiation in North China Plain. International Journal of Hydrogen Energy 2017; 42(21): 14418–14428. doi: 10.1016/j.ijhydene.2017.04.084

14. Iqbal M. An Introduction to Solar Radiation. Academic Press; 1983.

15. Roderick ML. Estimating the diffuse component from daily and monthly measurements of global radiation. Agricultural and Forest Meteorology 1999; 95(3): 169–185. doi: 10.1016/S0168-1923(99)00028-3

16. Hove T, Manyumbu E, Rukweza G. Developing an improved global solar radiation map for Zimbabwe through correlating long-term ground- and satellite-based monthly clearness index values. Renewable Energy 2014; 63: 687–697. doi: 10.1016/j.renene.2013.10.032

17. Boriratrit S, Fuangfoo P, Srithapon C, Chatthaworn R. Adaptive meta-learning extreme learning machine with golden eagle optimization and logistic map for forecasting the incomplete data of solar irradiance. Energy and AI 2023; 13: 100243. doi: 10.1016/j.egyai.2023.100243

18. Tahir ZUR, Hafeez S, Asim M, et al. Estimation of daily diffuse solar radiation from clearness index, sunshine duration and meteorological parameters for different climatic conditions. Sustainable Energy Technologies and Assessments 2021; 47: 101544. doi: 10.1016/j.seta.2021.101544

19. Chen JL, He L, Chen Q, et al. Study of monthly mean daily diffuse and direct beam radiation estimation with MODIS atmospheric product. Renewable Energy 2019; 132: 221–232. doi: 10.1016/j.renene.2018.07.151

20. van Kuijk K. Solar PV Potential in Rural Zimbabwe: Analysing Natural and Economical Potential [Master’s thesis]. Vrije Universiteit Amsterdam; 2012.

21. Maps of World. Available online: https://www.mapsofworld.com/lat_long/zimbabwe-lat-long.html/ (accessed on 9 November 2022).

22. Khan W, Walker S, Zeiler W. A bottom-up framework for analysing city-scale energy data using high dimension reduction techniques. Sustainable Cities and Society 2023; 89: 104323. doi: 10.1016/j.scs.2022.104323

23. Velliangiri S, Alagumuthukrishnan S, Thankumar joseph SI. A review of dimensionality reduction techniques for efficient computation. Procedia Computer Science 2019; 165: 104–111. doi: 10.1016/j.procs.2020.01.079

24. Chen RC, Dewi C, Huang SW, Caraka RE. Selecting critical features for data classification based on machine learning methods. Journal of Big Data 2020; 7(1): 52. doi: 10.1186/s40537-020-00327-4

25. Farhana N, Firdaus A, Darmawan MF, Ab Razak MF. Evaluation of Boruta algorithm in DDoS detection. Egyptian Informatics Journal 2023; 24(1): 27–42. doi: 10.1016/j.eij.2022.10.005

26. Kursa MB. Boruta for those in a hurry. Available online: https://cran.r-project.org/web/packages/Boruta/vignettes/inahurry.pdf (accessed on 10 December 2022).

27. Kursa MB, Rudnicki WR. Feature selection with the Boruta package. Journal of Statistical Software 2010; 36(11): 1–13. doi: 10.18637/jss.v036.i11

28. Kursa MB, Jankowski A, Rudnicki WR. Boruta—A system for feature selection. Fundamenta Informaticae 2010; 101(4): 271–285. doi: 10.3233/FI-2010-288

29. Veusz—A scientific plotting package. Available online: https://veusz.github.io/ (accessed on 12 March 2023).

30. Allen MP. The problem of multicollinearity. In: Understanding Regression Analysis. Springer; 1997. pp. 176–180.

31. Asadi Shamsabadi E, Salehpour M, Zandifaez P, Dias-da-Costa D. Data-driven multicollinearity-aware multi-objective optimisation of green concrete mixes. Journal of Cleaner Production 2023; 390: 136103. doi: 10.1016/j.jclepro.2023.136103

32. Voss DS. Multicollinearity. In: Kempf-Leonard K (editor). Encyclopedia of Social Measurement. Elsevier; 2005. pp. 759–770

33. Page JK. The estimation of monthly mean values of daily total short wave radiation on vertical and inclined surfaces from sunshine records for latitudes 40°N–40°S. Available online: https://digitallibrary.un.org/record/3827996 (accessed on 1 December 2022).

34. Smith G. Step away from stepwise. Journal of Big Data 2018; 5(1): 32. doi: 10.1186/s40537-018-0143-6

35. Brahma B, Wadhvani R. Solar irradiance forecasting based on deep learning methodologies and multi-site data. Symmetry 2020; 12(11): 1830. doi: 10.3390/sym12111830

36. Singla P, Duhan M, Saroha S. An ensemble method to forecast 24-h ahead solar irradiance using wavelet decomposition and BiLSTM deep learning network. Earth Science Informatics 2022; 15(1): 291–306. doi: 10.1007/s12145-021-00723-1

37. Bamigbola OM, Atolagbe SE. Empirical models for predicting global solar radiation on the African continent based on factors of location and season. Open Journal of Modelling and Simulation 2021; 9(1): 59–73. doi: 10.4236/ojmsi.2021.91004

38. Bamisile O, Cai D, Oluwasanmi A, et al. Comprehensive assessment, review, and comparison of AI models for solar irradiance prediction based on different time/estimation intervals. Scientific Reports 2022; 12(1):9644. doi: 10.1038/s41598-022-13652-w

39. Benatiallah D, Bouchouicha K, Benatiallah A, et al. Forecasting of solar radiation using an empirical model. Algerian Journal of Renewable Energy and Sustainable Development 2019; 1(2): 212–219. doi: 10.46657/ajresd.2019.1.2.11




DOI: https://doi.org/10.32629/jai.v7i2.1032

Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Kudzanayi Chiteka, Rejoice Mwarazi, Rajesh Arora, Christopher Enweremadu

License URL: https://creativecommons.org/licenses/by-nc/4.0/