SHORT-TERM WIND POWER COMBINATION FORECAST BASED ON MULTI-OBJECTIVE OPTIMIZATION AND DEEP LEARNING

被引：0

作者：

Hu, Jiaqiu ^{[1
]}

Zhuo, Yixin ^{[1
]}

Tang, Jian ^{[1
]}

Meng, Wenchuan ^{[2
]}

Qi, Huanxing ^{[3
]}

Liu, Luning ^{[4
]}

机构：

[1] Dispatching Control Center of Guangxi Power Grid, Nanning

[2] Energy Development Research Institute, China Southern Power Grid, Guangzhou

[3] Beihai Power Supply Bureau of Guangxi Power Grid, Beihai

[4] Eastern E-Energy（Beijing）Co.，Ltd., Beijing

来源：

Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2025年 / 46卷 / 02期

关键词：

combination forecasting; deep learning; forecast; multi-objective optimization; neural network; wind power;

D O I：

10.19912/j.0254-0096.tynxb.2023-1644

中图分类号：

学科分类号：

摘要：

Aiming at the characteristics of nonlinearity and volatility of wind power time series，this article proposes a wind power combination forecasting method based on multi-objective optimization and deep learning. The proposed method applies complete ensemble empirical mode decomposition with adaptive noise（CEEMDAN）to decompose the original wind power time series，and uses extreme learning machine（ELM），long short-term memory（LSTM），and time convolutional network（TCN）to train forecasting models and make forecasts on subsequences of CEEMDAN. Based on this，a combination forecasting model is established，where multi-objective Harris Hawks optimization（MOHHO）and deep deterministic policy gradient（DDPG）are combined to dynamically calculate the optimal weights. Using measured wind power data from an actual wind farm in Guangxi province for model testing and comparison，results show that the developed model performs best over all four datasets，with root mean squared error reduced by 12.93%，13.91%，12.38% and 9.71% compared to the simple average combination method，respectively，which verifies the effectiveness of the developed method. © 2025 Science Press. All rights reserved.

引用

页码：615 / 623

页数：8

共 22 条

[1]

LI R, ZHANG X, Et al., Short-term wind power prediction based on convolutional long-short-term memory neural networks［J］, Acta energiae solaris sinica, 42, 6, pp. 304-311, (2021)

[2]

ZHANG L D, LI J Y，, WU Y，, Et al., ARIMA model forecast for wind power time series with different temporal resolutions［J］, Electric power, 49, 6, pp. 176-180, (2016)

[3]

LIU X N, WANG S H，, JIN Y X，, Et al., Wind power short term prediction based on back propagation neural network ［J］, Journal of Shenyang Institute of Engineering（natural science）, 11, 1, pp. 10-13, (2015)

[4]

LIU D G，, ZHOU Z，, YANG N，, Et al., Short-term prediction of wind power based on least squares support vector machine［J］, Shaanxi electric power, 42, 10, pp. 18-21, (2014)

[5]

ZHU C S, ZHAO K P., Wind power prediction of kernel extreme learning machine based on improved grey wolf algorithm［J］, Computer applications and software, 39, 5, pp. 291-298, (2022)

[6]

TAN M G，, JIANG B, WANG J Y，, Et al., Research on short-term wind power prediction method based on deep learning model with bidirectional long short-term memory ［J］, Power system and clean energy, 36, 6, pp. 85-91, (2020)

[7]

NIU Z W, YU Z Y，, LI B, Et al., Short-term wind power forecasting model based on deep gated recurrent unit neural network［J］, Electric power automation equipment, 38, 5, pp. 36-42, (2018)

[8]

SU L C, ZHU J J, LI Y W., Short-term wind power prediction based on temporal convolutional network residual correction model［J］, Acta energiae solaris sinica, 44, 7, pp. 427-435, (2023)

[9]

SCHLOTTHAUER G，, Et al., A complete ensemble empirical mode decomposition with adaptive noise, 2011 IEEE International Conference on Acoustics，Speech and Signal Processing （ICASSP）, pp. 4144-4147, (2011)

[10]

BATES J M，, GRANGER C W J., The combination of forecasts［J］, Journal of the operational research society, 20, 4, pp. 451-468, (1969)

← 1 2 3 →