Login Register Cart 0
Generic placeholder image

Recent Advances in Electrical & Electronic Engineering

Editor-in-Chief

ISSN (Print): 2352-0965
ISSN (Online): 2352-0973

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Decentralized Wind Power Forecasting using Average Output Model and Improved Stacking Ensemble Learning

Author(s): Jiaquan Yang, Wei Li*, Yuting Yan, Zhiyong Yuan, Shi Su, Hao Bai, Shuhui Pan, Jun Chen and Qindao Zhao

Volume 16, Issue 3, 2023

Published on: 25 October, 2022

Page: [239 - 247] Pages: 9

DOI: 10.2174/2352096515666221004112548

Price: $65

Abstract

Background: Distributed wind farms cover a wide area, the internal units are far apart, and the output correlation is low. With the gradual expansion of its development scale, accurate prediction of distributed wind power has become an important means to ensure the smooth operation of the power system.

Objective: This paper proposes a decentralized wind power forecasting method based on cluster analysis and multi-model stacking ensemble learning.

Methods: Firstly, the average output model of multiple units is established through cluster analysis to eliminate redundant and repetitive features; secondly, a feature complex model is established to construct multi-dimensional combined features to fully extract feature information; then, an improved Stacking integrated learning model is proposed. Sets and model sets, while reducing the amount of model calculation, give full play to the feature adaptability of different models.

Results: The results of the proposed model are analyzed by comparison with traditional machine learning models such as SVM. Root Mean Square Error (RMSE) can be reduced by up to 6.3%.

Conclusion: The results show that, compared with traditional single-model forecasting, the decentralized wind power forecasting method based on cluster analysis and multi-model stacking ensemble learning has higher forecasting accuracy.

Keywords: Kmeans clustering, stacking ensemble learning, decentralized wind power, power forecasting

« Previous Next »
Graphical Abstract

[1]
H. Huang, Y. Du, S. Song, and Y. Guo, "Key technologies and economic analysis of decentralized wind power consumption: A case study in b city, China", Energies, vol. 13, no. 16, p. 4147, 2020.
[2]
Z. Han, Q. Jing, Y. Zhang, R. Bai, K. Guo, and Y. Zhang, “Review of wind power forecasting methods and new trends,” Power system protection and control, vol. 47, no. 24, pp. 178-187, 2019.
[3]
A. Khotanzad, R. Afkhami-Rohani, and D. Maratukulam, "ANNSTLF-Artificial Neural Network Short-Term Load Forecaster generation three," IEEE Transactions on Power Systems, vol. 13, no. 4, pp. 1413-1422, 1998.
Available: [http://dx.doi.org/10.1109/59.736285]
[4]
M. Xie, J. Deng, X. Ji, and M. Liu, "Support vector machine cooling load forecasting method based on information entropy and variable precision rough set optimization", Power System Technology, vol. 41, no. 1, pp. 210-214, 2017.
[5]
X. Yang, W. Guan, Y. Liu, and Y. Xiao, "Prediction intervals forecasts of wind power based on PSO-KELM", Proc. CSEE,, vol. 35, no. S1, pp. 146-153, 2015.
[6]
Q. Zhu, H. Li, Z. Wang, J. Chen, and B. Wang, "Short-term wind power forecasting based on LSTM", Power System Technology,, vol. 41, no. 12, pp. 3797-3802.
[7]
L. Zeng, S. Lei, S. Wang, and Y. Chang, "Ultra-short-term wind power prediction based on OVMD-SSA-DELM-GM model", Power System Technology, vol. 45, no. 12, pp. 4701-4712, 2021.
[8]
J. Shi, and J. Zhang, "Load forecasting based on multi-model by stacking ensemble learning", Proceedings of the CSEE, , vol. 39, no. 14, pp. 4032-4041, 2019.
[9]
C. Chen, X. Zhao, G. Bi, S. Chen, and X. Xie, "Short-term wind speed prediction based on Kmeans-VMD-LSTM", Electric Machines and Control Application, vol. 48, no. 12, pp. 85-93, 2021.
[10]
L. Kewen, P. Tianjiao, and Z. Haiming, "A short term wind power forecasting model based on combination algorithms," Proceedings of the CSEE,, vol. 33. 2013, pp. 130-135.
[11]
G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.Y. Liu, “Lightgbm: A highly efficient gradient boosting decision tree,” In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, Eds., vol. 30. Curran Associates, Inc., 2017. [Online]. Available: https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa- Paper.pdf
[12]
Y. Zhang, L. Yang, S. Ge, and H. Zhou, "Short-term photovoltaic power forecasting based on kmeans algorithm and support vector ma-chine", Power System Protection and Control, vol. 46, no. 21, pp. 118-125, 2018.
[13]
M.J. Sanjari, H.B. Gooi, and N.C. Nair, "Power Generation Forecast of Hybrid PV-Wind System," in IEEE Transactions on Sustainable Energy, vol. 11, no. 2, pp. 703-712, April 2020.
[http://dx.doi.org/10.1109/TSTE.2019.2903900]

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy