access icon free Randomised learning-based hybrid ensemble model for probabilistic forecasting of PV power generation

© The Institution of Engineering and Technology
Received 02/04/2020, Accepted 24/08/2020, Revised 08/07/2020, Published 09/09/2020

Probabilistic forecasting of solar photovoltaic (PV) generation is critical for stochastic or robust optimisation-based power system dispatch. This study proposes a randomised learning-based hybrid ensemble (RLHE) model to construct the prediction intervals of probabilistic PV forecasting. Three different randomised learning algorithms, namely extreme learning machine, randomised vector functional link, and stochastic configuration network, are ensembled as a hybrid forecasting model. Besides, bootstrap is used as the ensemble learning framework to increase the diversity of training samples. For each algorithm, a decision-making rule is designed to evaluate the credibility of the individual outputs and the incredible ones are discarded at the output aggregation step. The weight coefficients of the aggregated outputs of the three algorithms are then optimised to compute the final point forecast results. Based on the point forecast results, the prediction intervals are constructed considering both model misspecification uncertainty and data noise uncertainty. The variance in model misspecification uncertainty is directly calculated with the individual outputs and the variance in data noise uncertainty is separately trained with an RLHE model. The proposed method is tested with an open dataset and compared with several benchmarking approaches.

Inspec keywords: decision making; probability; optimisation; stochastic processes; photovoltaic power systems; neural nets; learning (artificial intelligence)

Other keywords: randomised vector functional link; aggregated outputs; model misspecification uncertainty; RLHE model; extreme learning machine; stochastic optimisation-based power system dispatch; randomised learning-based hybrid ensemble model; stochastic configuration network; probabilistic forecasting; robust optimisation-based power system dispatch; final point forecast results; PV power generation; individual outputs; probabilistic PV forecasting; prediction intervals; solar photovoltaic generation; hybrid forecasting model; data noise uncertainty

Subjects: Other topics in statistics; Solar power stations and photovoltaic power systems; Optimisation techniques; Optimisation techniques; Other topics in statistics; Knowledge engineering techniques; Neural computing techniques

References

    1. 1)
      • 27. Wang, D., Li, M.: ‘Stochastic configuration networks: fundamentals and algorithms’, IEEE Trans. Cybern., 2017, 47, (10), pp. 3466–3479.
    2. 2)
      • 18. Sanjari, M.J., Gooi, H.B.: ‘Probabilistic forecast of PV power generation based on higher order Markov chain’, IEEE Trans. Power Syst., 2017, 32, (4), pp. 2942–2952.
    3. 3)
      • 13. David, M., Ramahatana, F., Trombe, P.J., et al: ‘Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models’, Sol. Energy, 2016, 133, pp. 55–72.
    4. 4)
      • 4. Song, J., Krishnamurthy, V., Kwasinski, A., et al: ‘Development of a Markov-chain-based energy storage model for power supply availability assessment of photovoltaic generation plants’, IEEE Trans. Sustain. Energy, 2013, 4, (2), pp. 491–500.
    5. 5)
      • 5. Shi, J., Lee, W.-J., Liu, Y., et al: ‘Forecasting power output of photovoltaic systems based on weather classification and support vector machines’, IEEE Trans. Ind. Appl., 2012, 48, (3), pp. 1064–1069.
    6. 6)
      • 24. Cao, Z., Wan, C., Zhang, Z., et al: ‘Hybrid ensemble deep learning for deterministic and probabilistic low-voltage load forecasting’, IEEE Trans. Power Syst., 2020, 35, (3), pp. 1881–1897.
    7. 7)
      • 7. Alfadda, A., Rahman, S., Pipattanasomporn, M.: ‘Solar irradiance forecast using aerosols measurements: a data driven approach’, Sol. Energy, 2018, 170, pp. 924–939.
    8. 8)
      • 21. Lee, H., Kim, N.-W., Lee, J.-G., et al: ‘Uncertainty-aware forecast interval for hourly PV power output’, IET Renew. Power Gener., 2019, 13, (14), pp. 2656–2664.
    9. 9)
      • 33. Wan, C., Xu, Z., Pinson, P., et al: ‘Probabilistic forecasting of wind power generation using extreme learning machine’, IEEE Trans. Power Syst., 2014, 29, (3), pp. 1033–1044.
    10. 10)
      • 29. Xu, Y., Dong, Z.Y., Zhao, J.H., et al: ‘A reliable intelligent system for real-time dynamic security assessment of power systems’, IEEE Trans. Power Syst., 2012, 27, (3), pp. 1253–1263.
    11. 11)
      • 6. Long, H., Zhang, Z., Su, Y.: ‘Analysis of daily solar power prediction with data-driven approaches’, Appl. Energy, 2014, 126, pp. 29–37.
    12. 12)
      • 10. Zhang, C., Xu, Y., Dong, Z.Y., et al: ‘Robust coordination of distributed generation and price-based demand response in microgrids’, IEEE Trans. Smart Grid, 2018, 9, (5), pp. 4236–4247.
    13. 13)
      • 32. ‘PV power generation, ambient temperature and solar irradiance data’. Available at: http://solar.uq.edu.au/user/reportPower.php.
    14. 14)
      • 2. Xu, Y., Dong, Z.Y., Zhang, R., et al: ‘Multi-timescale coordinated voltage/var control of high renewable-penetrated distribution systems’, IEEE Trans. Power Syst., 2017, 32, (6), pp. 4398–4408.
    15. 15)
      • 30. Wan, C., Xu, Z., Pinson, P.: ‘Direct interval forecasting of wind power’, IEEE Trans. Power Syst., 2013, 28, (4), pp. 4877–4878.
    16. 16)
      • 20. Chen, B., Li, J.: ‘Combined probabilistic forecasting method for photovoltaic power using an improved Markov chain’, IET Gener. Transm. Distrib., 2019, 13, (19), pp. 4364–4373.
    17. 17)
      • 19. Golestaneh, F., Pinson, P., Gooi, H.B.: ‘Very short-term nonparametric probabilistic forecasting of renewable energy generation – with application to solar energy’, IEEE Trans. Power Syst., 2016, 31, (5), pp. 3850–3863.
    18. 18)
      • 22. Webb, G.I., Zheng, Z.: ‘Multistrategy ensemble learning: reducing error by combining ensemble learning techniques’, IEEE Trans. Knowl. Data Eng., 2004, 16, (8), pp. 980–991.
    19. 19)
      • 15. Fonseca Junior, J.G. da S., Oozeki, T., Ohtake, H., et al: ‘On the use of maximum likelihood and input data similarity to obtain prediction intervals for forecasts of photovoltaic power generation’, J. Electr. Eng. Technol., 2015, 10, (3), pp. 1342–1348.
    20. 20)
      • 25. Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: ‘Extreme learning machine: theory and applications’, Neurocomputing, 2006, 70, (1-3), pp. 489–501.
    21. 21)
      • 11. van der Meer, D.W., Widén, J., Munkhammar, J.: ‘Review on probabilistic forecasting of photovoltaic power production and electricity consumption’, Renew. Sustain. Energy Rev., 2018, 81, pp. 1484–1512.
    22. 22)
      • 9. Li, Z., Xu, Y.: ‘Temporally-coordinated optimal operation of a multi-energy microgrid under diverse uncertainties’, Appl. Energy, 2019, 240, pp. 719–729.
    23. 23)
      • 1. Birol, F.: ‘Renewables 2019: analysis and forecasts to 2024’ (International Energy Agency, France, 2019).
    24. 24)
      • 23. Zhang, R., Dong, Z.Y., Xu, Y., et al: ‘Short-term load forecasting of Australian national electricity market by an ensemble model of extreme learning machine’, IET Gener. Transm. Distrib., 2013, 7, (4), pp. 391–397.
    25. 25)
      • 3. Liu, J., Fang, W., Zhang, X., et al: ‘An improved photovoltaic power forecasting model with the assistance of aerosol Index data’, IEEE Trans. Sustain. Energy, 2015, 6, (2), pp. 434–442.
    26. 26)
      • 26. Zhang, L., Suganthan, P.N.: ‘A comprehensive evaluation of random vector functional link networks’, Inf. Sci., 2016, 367–368, pp. 1094–1105.
    27. 27)
      • 16. Wu, W., Wang, K., Han, B., et al: ‘A Versatile probability model of photovoltaic generation using pair copula construction’, IEEE Trans. Sustain. Energy, 2015, 6, (4), pp. 1337–1345.
    28. 28)
      • 28. Dietterich, T.G.: ‘Ensemble methods in machine learning’, in ‘Multiple classifier systems’ (Springer, Berlin Heidelberg, 2000), pp. 1–15, https://link.springer.com/chapter/10.1007/3-540-45014-9_1.
    29. 29)
      • 8. Yang, H.-T., Huang, C.-M., Huang, Y.-C., et al: ‘A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output’, IEEE Trans. Sustain. Energy, 2014, 5, (3), pp. 917–926.
    30. 30)
      • 31. Cramér, H.: ‘Mathematical methods of statistics’ (Princeton University Press, USA, 1999), 19 Printing.
    31. 31)
      • 14. Tabone, M.D., Callaway, D.S.: ‘Modeling variability and uncertainty of photovoltaic generation: a hidden state spatial statistical approach’, IEEE Trans. Power Syst., 2015, 30, (6), pp. 2965–2973.
    32. 32)
      • 34. Qing, X., Niu, Y.: ‘Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM’, Energy, 2018, 148, pp. 461–468.
    33. 33)
      • 17. Ren, Z., Yan, W., Zhao, X., et al: ‘Chronological probability model of photovoltaic generation’, IEEE Trans. Power Syst., 2014, 29, (3), pp. 1077–1088.
    34. 34)
      • 12. Chu, Y., Li, M., Pedro, H.T.C., et al: ‘Real-time prediction intervals for intra-hour DNI forecasts’, Renew. Energy, 2015, 83, pp. 234–244.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-gtd.2020.0625
Loading

Related content

content/journals/10.1049/iet-gtd.2020.0625
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading