Skip to main content
SpringerLink
Log in

Online probabilistic forecasting method for trapezoidal photovoltaic stream data

  • Original Article
  • Published:
Journal of Power Electronics Aims and scope Submit manuscript

Abstract

For the probabilistic forecasting of photovoltaic generation, the design of a feasible online predictive framework is a challenging problem. To deal with this issue, an ensemble dynamic OS-ELM based on quantile estimation has been proposed. Considering inherent intermittent and random variations of the photovoltaic sequence, the weights of the forecasting model are updated according to the loss suffered. At the same time, the accommodative feature threshold can be calculated on the basis of increasing characteristics space, which builds the optimal network architecture for point forecast. A two-dimensional kernel density estimation algorithm based on a fuzzy inference method is exploited. This method breaks through the assumptive limit of error distribution. The changeable parameters help the model to be suitable for power fluctuations. Both the arriving data sample and the increasing feature space are tackled. Numerical experiments are conducted on two practical applications for solar power systems. The results show that the proposed algorithm not only has lower generalization error, but also provides higher confidence coefficient.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Elnozahy, A., Yousef, A.M., Abo-Elyousr, F.K., et al.: Performance improvement of hybrid renewable energy sources connected to the grid using artificial neural network and sliding mode control. J. Power Electron. 3, 1–14 (2021)

    Google Scholar 

  2. Shi, J.Y., Xue, F., Ling, L.T., et al.: Combining model-based and heuristic techniques for fast tracking the global maximum power point of a photovoltaic string. J. Power Electron. 17(2), 476–489 (2017)

    Article  Google Scholar 

  3. Dong, Y., Dong, Z., Zhao, T., et al.: Short term load forecasting with markovian switching distributed deep belief networks. Int. J. Electr. Power Energy Syst. 130, 106942 (2021)

    Article  Google Scholar 

  4. Yang, Y., Che, J., Deng, C., et al.: Sequential grid approach based support vector regression for short-term electric load forecasting. Appl. Energy 238, 1010–1021 (2019)

    Article  Google Scholar 

  5. Wang, S., Minku, L., Yao, X.: Resampling-based ensemble methods for online class imbalance learning. IEEE Trans. Knowl. Data Eng. 27(5), 1356–1368 (2015)

    Article  Google Scholar 

  6. Zhang, Q., Zhang, P., Long, G., et al.: Online learning from trapezoidal data streams. IEEE Trans. Knowl. Data Eng. 28(10), 2709–2723 (2016)

    Article  Google Scholar 

  7. Sobri, S., Sam, K., Nasrudin, A.: Solar photovoltaic generation forecasting methods: a review. Energy Convers. Manag. 156, 459–497 (2018)

    Article  Google Scholar 

  8. Ouyang, T.: Feature learning for stacked ELM via low-rank matrix factorization. Neurocomputing 448, 7553 (2021)

    Article  Google Scholar 

  9. Huang, G., Huang, G.B., Song, S., et al.: Trends in extreme learning machines: a review. Neural Netw. 61, 32–48 (2015)

    Article  Google Scholar 

  10. Xiao, C., Sutanto, D., Muttaqi, K.M., et al.: Online sequential extreme learning machine algorithm for better predispatch electricity price forecasting grids. IEEE Trans. Ind. Appl. 57, 1860–1871 (2021)

    Article  Google Scholar 

  11. Tang, P., Chen, D., Hou, Y.: Entropy method combined with extreme learning machine method for the short-term photovoltaic power generation forecasting. Chaos Solitons Fractals 89, 243–248 (2016)

    Article  Google Scholar 

  12. Wang, J., Ran, R., Zhou, Y.: A Short-term photovoltaic power prediction model based on an FOS-ELM algorithm. Appl. Sci. 7(4), 423 (2017)

    Article  Google Scholar 

  13. Gneiting, T., Matthias, K.: Probabilistic forecasting. Ann. Rev. Stat. Appl. 1, 125–151 (2014)

    Article  Google Scholar 

  14. Liu, W., Xu, Y.: Randomized learning-based hybrid ensemble model for probabilistic forecasting of PV Power Generation[J]. IET Gener. Transm. Distrib. 14(24), 5909–5917 (2020)

    Article  Google Scholar 

  15. Lauret, P., David, M., Pedro, H.: Probabilistic solar forecasting using quantile regression models. Energies 10(10), 1591 (2017)

    Article  Google Scholar 

  16. Fatemi, S., Kuh, A., Fripp, M.: Parametric methods for probabilistic forecasting of solar irradiance. Renew. Energy 129, 666–676 (2018)

    Article  Google Scholar 

  17. Golestaneh, F., Pinson, P., Gooi, H.: Very short-term nonparametric probabilistic forecasting of renewable energy generation-with application to solar energy. IEEE Trans. Power Syst. 31(5), 3850–3863 (2016)

    Article  Google Scholar 

  18. Yu, Y., Han, X., Yang, M., et al.: Probabilistic prediction of regional wind power based on spatiotemporal quantile regression. IEEE Trans. Ind. Appl. 56, 6117–6127 (2020)

    Article  Google Scholar 

  19. Manjhi, D., Chaturvedi, A.: Reuse estimate and interval prediction using MOGA-NN and RBF-NN in the functional paradigm. Sci. Comput. Program. 208, 102643 (2021)

    Article  Google Scholar 

  20. Wan, C., et al.: Direct quantile regression for nonparametric probabilistic forecasting of wind power generation. IEEE Trans. Power Syst. 32(4), 2767–2778 (2017)

    Article  Google Scholar 

  21. Xu, Q., Zhang, J., Jiang, C., et al.: Weighted quantile regression via support vector machine. Expert Syst. Appl. 42(13), 5441–5451 (2015)

    Article  Google Scholar 

  22. Fliess, M., Join, C., Voyant, C.: Prediction bands for solar energy: new short-term time series forecasting techniques. Sol. Energy 166, 519–528 (2018)

    Article  Google Scholar 

  23. Mahmoud, T., Dong, Z., Ma, J.: An advanced approach for optimal wind power generation prediction intervals by using self-adaptive evolutionary extreme learning machine. Renew. Energy 126, 254–269 (2018)

    Article  Google Scholar 

  24. Verbois, H., Rusydi, A., Thiery, A.: Probabilistic forecasting of day-ahead solar irradiance using quantile gradient boosting. Sol. Energy 173, 313–327 (2018)

    Article  Google Scholar 

  25. Gao, D., Huang, M.: Prediction of remaining useful life of lithium-ion battery based on multi-kernel support vector machine with particle swarm optimization. J. Power Electron. 17(5), 1288–1297 (2017)

    Google Scholar 

  26. Abuogo, J.O.: Machine learning approach for sorting SiC MOSFET devices for paralleling. J. Power Electron 20(1), 329–340 (2020)

    Article  Google Scholar 

  27. UQ SOLAR Photovoltaic Data. 2020. The University of Queensland. http://solar.uq.edu.au/user/reportPower.php.

  28. Bai, Z., Huang, G.B., Wang, D., et al.: Sparse extreme learning machine for classification. IEEE Trans. Cybern. 44(10), 1858–1870 (2014)

    Article  Google Scholar 

  29. Ma, C., Ouyang, J., Chen, H., Ji, J.: A novel kernel extreme learning machine algorithm based on self-adaptive artificial bee colony optimisation strategy. Int. J. Syst. Sci. 47(6), 1342–1357 (2016)

    Article  Google Scholar 

  30. Karaboga, D., Akay, B.: A comparative study of artificial bee colony algorithm. Appl. Math. Comput. 214(1), 108–132 (2009)

    MathSciNet  MATH  Google Scholar 

  31. Zhou, J., Foster, D., Stine, R., et al.: Streamwise feature selection. J. Mach. Learn. Res. 7(9), 1861–1885 (2006)

    MathSciNet  MATH  Google Scholar 

  32. Zhao, W., Li, Z., Xu, J., et al.: Novel fuzzy direct torque control based on constructed functional transformed grey model. J. Power Electron. 21(6), 1–10 (2021)

    Article  Google Scholar 

  33. Tahmasebifar, R., Sheikh-El-Eslami, M.K., Kheirollahi, R.: Point and interval forecasting of real-time and day-ahead electricity prices by a novel hybrid approach[J]. IET Gener. Transm. Distrib. 11(9), 2173–2183 (2017)

    Article  Google Scholar 

Download references

Acknowledgements

The work received the support of the National Natural Science Foundation of China under Grant 61775022 and U19A2063, the Science and Technology Research Program of Education Department of Jilin Province of China (No.JJKH20210844KJ), and the Development Program of Science and Technology of Jilin Province of China (No.YDZJ202101ZYTS151, 2020122351JC). The authors gratefully acknowledge support from the Key Laboratory of Optical Control and Optical Information Transmission Technology, Ministry of Education.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, Jilin, China

    Haiyang Yu, Chunyi Chen & Huamin Yang

Authors
  1. Haiyang Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chunyi Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Huamin Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Haiyang Yu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yu, H., Chen, C. & Yang, H. Online probabilistic forecasting method for trapezoidal photovoltaic stream data. J. Power Electron. 21, 1701–1711 (2021). https://doi.org/10.1007/s43236-021-00302-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s43236-021-00302-z

Keywords

Search

Navigation