A Framework of Using Machine Learning Approaches for Short-Term Solar Power Forecasting

  • Usman Munawar
  • Zhanle WangEmail author
Original Article


Various machine learning approaches are widely applied for short-term solar power forecasting, which is highly demanded for renewable energy integration and power system planning. However, appropriate selection of machine learning models and data features is a significant challenge. In this study, a framework is developed to quantitatively evaluate various models and feature selection methods, and the best combination for short-term solar power forecasting is discovered. More specifically, the machine learning methods include the random forest, artificial neural network and extreme gradient boosting (XGBoost), and the feature selection techniques include the feature importance and principle component analysis (PCA). All possible combinations of these machine learning and feature selection methods are developed and evaluated for solar power forecasting. The best ensemble of machine learning methods and feature selection techniques is identified for solar power forecasting in Hawaii, US. Simulation results show that the XGBoost method with features selected by the PCA method outperforms the other approaches. In addition, the random forest and XGBoost models have rarely been used for short-term solar forecasting. This framework can be used to select appropriate machine learning approaches for short-term solar power forecasting and the simulation results can be used as a baseline for comparison.


Short-term solar power forecasting Machine learning Feature selection 



This research was funded by University of Regina, Grant No: [FGSR Scholarship Base Fund Grant].


  1. 1.
    Treasury Board of Canada Secretariat (2017) Government of Canada sets ambitious GHG reduction targets for federal operationGoogle Scholar
  2. 2.
    Zhang X, Li Y, Lu S, Hamann HF, Hodge B-M, Lehman B (2018) A solar time based analog ensemble method for regional solar power forecasting. IEEE Trans Sustain Energy 10:268–279CrossRefGoogle Scholar
  3. 3.
    Nalina U, Prema V, Smitha K, Rao KU (2014) Multivariate regression for prediction of solar irradiance. In: 2014 International Conference on Data Science and Engineering, 2014, pp. 177–181Google Scholar
  4. 4.
    Prakash A, Singh SK (2014) Towards an efficient regression model for solar energy prediction. In: Innovative Applications of Computational Intelligence on Power, Energy and Controls with their impact on Humanity, 2014, pp. 18–23Google Scholar
  5. 5.
    Bessa RJ, Trindade A, Silva CS, Miranda V (2015) Probabilistic solar power forecasting in smart grids using distributed information. Int J Electr Power 72:16–23CrossRefGoogle Scholar
  6. 6.
    Zhang Y, Beaudin M, Taheri R, Zareipour H, Wood D (2015) Day-ahead power output forecasting for small-scale solar photovoltaic electricity generators. IEEE Trans Smart Grid 6:2253–2262CrossRefGoogle Scholar
  7. 7.
    Yesilbudak M, Çolak M, Bayindir R (2016) A review of data mining and solar power prediction. In: IEEE International Conference on Renewable Energy Research and Applications, 2016, pp. 1117–1121Google Scholar
  8. 8.
    Marzouq M, El Fadili H, Lakhliai Z, Zenkouar K (2017) A review of solar radiation prediction using artificial neural networks. In: Interantional Conference on Wireless Technologies, Embedded and Intelligent Systems, 2017, pp. 1–6.Google Scholar
  9. 9.
    Ak R, Fink O, Zio E (2015) Two machine learning approaches for short-term wind speed time-series prediction. IEEE Trans Neural Netw Learn Syst. 27:1734–1747MathSciNetCrossRefGoogle Scholar
  10. 10.
    Hernández-Travieso JG, Travieso CM, Alonso JB, Dutta MK (2014) Solar radiation modelling for the estimation of the solar energy generation. In: Interantional Conference on Contemporary Computing, 2014, pp. 536–541Google Scholar
  11. 11.
    Huang C-J, Kuo P-H (2019) Multiple-input deep convolutional neural network model for short-term photovoltaic power forecasting. IEEE Access 7:74822–74834CrossRefGoogle Scholar
  12. 12.
    Valencia F, Collado J, Sáez D, Marín LG (2015) Robust energy management system for a microgrid based on a fuzzy prediction interval model. IEEE Trans Smart Grid 7:1486–1494CrossRefGoogle Scholar
  13. 13.
    Percy SD, Aldeen M, Berry A (2018) Residential demand forecasting with solar-battery systems: a survey-less approach. IEEE Trans Sustain Energy 9:1499–1507CrossRefGoogle Scholar
  14. 14.
    Abedinia O, Raisz D, Amjady N (2017) Effective prediction model for Hungarian small-scale solar power output. IET Renew Power Gener 11:1648–1658CrossRefGoogle Scholar
  15. 15.
    A. Lahouar, A. Mejri, and J. B. H. Slama, “Importance based selection method for day-ahead photovoltaic power forecast using random forests,” in Int. Conf.Green Energy Conversion System, 2017, pp. 1-7Google Scholar
  16. 16.
    Pirbazari AM, Chakravorty A, Rong C (2019) Evaluating feature selection methods for short-term load forecasting. In IEEE Intenational Conference on Big Data and Smart Computing, 2019, pp. 1–8Google Scholar
  17. 17.
    Shaker H, Zareipour H, Wood D (2015) A data-driven approach for estimating the power generation of invisible solar sites. IEEE Trans Smart Grid 7:2466–2476CrossRefGoogle Scholar
  18. 18.
    Tuohy A, Zack J, Haupt SE, Sharp J, Ahlstrom M, Dise S et al (2015) Solar forecasting: methods, challenges, and performance. IEEE Power Energ Mag 13:50–59CrossRefGoogle Scholar
  19. 19.
    Martinez-Anido CB, Botor B, Florita AR, Draxl C, Lu S, Hamann HF et al (2016) The value of day-ahead solar power forecasting improvement. Sol Energy 129:192–203CrossRefGoogle Scholar
  20. 20.
    Fonseca JGDS, Oozeki T, Ohtake H, Takashima T, Ogimoto K (2015) Regional forecasts of photovoltaic power generation according to different data availability scenarios: a study of four methods. Progress Photovolt 23:1203–12185CrossRefGoogle Scholar
  21. 21.
    Junior JGDSF, Oozeki T, Ohtake H, Shimose KI, Takashima T, Ogimoto K (2014) Regional forecasts and smoothing effect of photovoltaic power generation in Japan: An approach with principal component analysis. Renew Energy 68:403–413CrossRefGoogle Scholar
  22. 22.
    Kumar N, Akella A (2014) Prediction and efficiency evaluation of solar energy resources by using mixed ANN and DEA approaches. In 2014 IEEE PES General Meeting Conference and Exposition, 2014, pp 1–5.Google Scholar
  23. 23.
    Alobaidi MH, Chebana F, Meguid MA (2018) Robust ensemble learning framework for day-ahead forecasting of household based energy consumption. Appl Energy 212:997–1012CrossRefGoogle Scholar
  24. 24.
    Hackathon N (2017) Solar radiation predictionGoogle Scholar
  25. 25.
    Denil M, Matheson D, De Freitas N (2014) Narrowing the gap: Random forests in theory and in practice. In: International Conference on machine learning, 2014, pp 665–673Google Scholar
  26. 26.
    Arce-Medina E, Paz-Paredes JI (2009) Artificial neural network modeling techniques applied to the hydrodesulfurization process. Math Comput Model 49:207–214MathSciNetCrossRefGoogle Scholar
  27. 27.
    Sundaram RB (2018) An end-to-end guide to understand the math behind XGBoostGoogle Scholar
  28. 28.
    Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794Google Scholar
  29. 29.
    Riffonneau Y, Bacha S, Barruel F, Ploix S (2011) Optimal power flow management for grid connected PV systems with batteries. IEEE Trans Sustain Energy 2:309–320CrossRefGoogle Scholar

Copyright information

© The Korean Institute of Electrical Engineers 2020

Authors and Affiliations

  1. 1.University of ReginaReginaCanada
  2. 2.University of Engineering and TechnologyLahorePakistan

Personalised recommendations