基于多目标优化和深度学习的短期风功率组合预测

胡甲秋; 卓毅鑫; 唐健; 蒙文川; 戚焕兴; 刘鲁宁

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

PDF(7156 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (2) : 615-623. DOI: 10.19912/j.0254-0096.tynxb.2023-1644

基于多目标优化和深度学习的短期风功率组合预测

胡甲秋¹, 卓毅鑫¹, 唐健¹, 蒙文川², 戚焕兴³, 刘鲁宁⁴

作者信息 +

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

Hu Jiaqiu¹, Zhuo Yixin¹, Tang Jian¹, Meng Wenchuan², Qi Huanxing³, Liu Luning⁴

Author information +

文章历史 +

摘要

针对风功率时间序列的非线性和波动性等特征,提出一种基于多目标优化和深度学习的风功率组合预测的方法。该方法基于完全自适应噪声集合经验模态分解,得到原始风功率序列的子序列集合,分别使用极限学习机、长短期记忆和时间卷积网络建立子序列预测模型并重构。基于此建立组合预测模型,应用多目标哈里斯鹰优化算法和深度确定性梯度策略求解最优组合权值。使用广西某风电场的实测资料进行实验,结果表明：所提出的组合预测模型在4组数据集中均表现最优,与集合平均相比均方根误差分别降低了12.93%、13.91%、12.38%和9.71%,预测精度得到有效提升。

Abstract

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.

导出引用

胡甲秋, 卓毅鑫, 唐健, 蒙文川, 戚焕兴, 刘鲁宁. 基于多目标优化和深度学习的短期风功率组合预测[J]. 太阳能学报. 2025, 46(2): 615-623 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1644

Hu Jiaqiu, Zhuo Yixin, Tang Jian, Meng Wenchuan, Qi Huanxing, Liu Luning. SHORT-TERM WIND POWER COMBINATION FORECAST BASED ON MULTI-OBJECTIVE OPTIMIZATION AND DEEP LEARNING[J]. Acta Energiae Solaris Sinica. 2025, 46(2): 615-623 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1644

中图分类号： TM614

参考文献

[1] 栗然, 马涛, 张潇, 等. 基于卷积长短期记忆神经网络的短期风功率预测[J]. 太阳能学报, 2021, 42(6): 304-311.
LI R, MA T, ZHANG X, et al.Short-term wind power prediction based on convolutional long-short-term memory neural networks[J]. Acta energiae solaris sinica, 2021, 42(6): 304-311.
[2] 张立栋, 李继影, 吴颖, 等. 不同时间分辨率的风功率时间序列ARIMA模型预测[J]. 中国电力, 2016, 49(6): 176-180.
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, 2016, 49(6): 176-180.
[3] 刘晓楠, 王胜辉, 金月新, 等. 基于BP神经网络的风电场发电功率短期预测[J]. 沈阳工程学院学报(自然科学版), 2015, 11(1): 10-13, 24.
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), 2015, 11(1): 10-13, 24.
[4] 刘代刚, 周峥, 杨楠, 等. 基于最小二乘支持向量机的风功率短期预测[J]. 陕西电力, 2014, 42(10): 18-21.
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, 2014, 42(10): 18-21.
[5] 朱昶胜, 赵奎鹏. 改进灰狼算法的核极限学习机的风功率预测[J]. 计算机应用与软件, 2022, 39(5): 291-298.
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, 2022, 39(5): 291-298.
[6] 谭敏戈, 蒋勃, 王建渊, 等. 基于双向长短期记忆深度学习模型的短期风功率预测方法研究[J]. 电网与清洁能源, 2020, 36(6): 85-91.
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, 2020, 36(6): 85-91.
[7] 牛哲文, 余泽远, 李波, 等. 基于深度门控循环单元神经网络的短期风功率预测模型[J]. 电力自动化设备, 2018, 38(5): 36-42.
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, 2018, 38(5): 36-42.
[8] 苏连成, 朱娇娇, 李英伟. 基于时间卷积网络残差校正的短期风电功率预测[J]. 太阳能学报, 2023, 44(7): 427-435.
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, 2023, 44(7): 427-435.
[9] TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague, Czech Republic, 2011: 4144-4147.
[10] BATES J M, GRANGER C W J. The combination of forecasts[J]. Journal of the operational research society, 1969, 20(4): 451-468.
[11] 陈华友. 基于相关系数的优性组合预测模型研究[J]. 系统工程学报, 2006, 21(4): 353-360.
CHEN H Y.Research on properties of superior combined forecasting models based on correlation coefficients[J]. Journal of systems engineering, 2006, 21(4): 353-360.
[12] XIAO L, WANG J Z, DONG Y, et al.Combined forecasting models for wind energy forecasting: a case study in China[J]. Renewable and sustainable energy reviews, 2015, 44: 271-288.
[13] 叶家豪, 魏霞, 黄德启, 等. 基于灰色关联分析的BSO-ELM-AdaBoost风电功率短期预测[J]. 太阳能学报, 2022, 43(3): 426-432.
YE J H, WEI X, HUANG D Q, et al.Short-term forecast of wind power based on BSO-ELM-AdaBoost with grey correlation analysis[J]. Acta energiae solaris sinica, 2022, 43(3): 426-432.
[14] 赵欣, 王爽心, 刘如九. 基于灰色关联和协整理论的风功率组合预测研究[J]. 太阳能学报, 2017, 38(5): 1299-1306.
ZHAO X, WANG S X, LIU R J.Research on combination wind power forecasting based on gray correlation and cointegration theory[J]. Acta energiae solaris sinica, 2017, 38(5): 1299-1306.
[15] MI X W, YU C Q, LIU X W, et al.A dynamic ensemble deep deterministic policy gradient recursive network for spatiotemporal traffic speed forecasting in an urban road network[J]. Digital signal processing, 2022, 129: 103643.
[16] CHEN C, LIU H.Dynamic ensemble wind speed prediction model based on hybrid deep reinforcement learning[J]. Advanced engineering informatics, 2021, 48: 101290.
[17] HE Y D, ZHAO J B.Temporal convolutional networks for anomaly detection in time series[J]. Journal of physics: conference series, 2019, 1213(4): 042050.
[18] HEIDARI A A, MIRJALILI S, FARIS H, et al.Harris Hawks optimization: algorithm and applications[J]. Future generation computer systems, 2019, 97: 849-872.
[19] 展广涵, 王雨虹, 刘昊. 混合策略改进的哈里斯鹰优化算法及其应用[J]. 传感技术学报, 2022, 35(10): 1394-1403.
ZHAN G H, WANG Y H, LIU H.Improved Harris hawks optimization algorithm with hybrid strategy and its application[J]. Chinese journal of sensors and actuators, 2022, 35(10): 1394-1403.
[20] 李嘉文, 盛德仁, 李蔚, 等. 基于多目标优化和误差修正的短期风速预测[J]. 太阳能学报, 2022, 43(8): 273-280.
LI J W, SHENG D R, LI W, et al.Short-term wind speed prediction based on multi-objective optimization and error correction[J]. Acta energiae solaris sinica, 2022, 43(8): 273-280.
[21] LIAN R Z, PENG J K, WU Y K, et al.Rule-interposing deep reinforcement learning based energy management strategy for power-split hybrid electric vehicle[J]. Energy, 2020, 197: 117297.
[22] SHI X T, LI Y G, SUN B, et al.Optimizing zinc electrowinning processes with current switching via deep deterministic policy gradient learning[J]. Neurocomputing, 2020, 380: 190-200.