Wind power prediction based on PCA and SOFTS fusion model

doi:10.11930/j.issn.1004-9649.202510044

Abstract

Abstract:

In order to improve the prediction accuracy and robustness of non-stationary wind power series, a wind power prediction method based on principal component analysis (PCA) and series-core fused time series forecaster (SOFTS) is proposed in this paper. Firstly, PCA is used to calculate the principal components of wind power variables to construct model feature variables, which are input into the SOFTS multi-layer perceptron for wind power related variables sequence encoding. The core representation of each input sequence is obtained based on the spatiotemporal aggregation and redistribution module. Secondly, complex correlations and global feature information between channels are captured effectively through horizontal and vertical intersections. Finally, by training the SOFTS network parameters, a wind power prediction model based on PCA and SOFTS fusion is established. The actual operation data of a wind farm in a certain area is used for verification. The prediction accuracy of the proposed wind power prediction model is 98.38%. Compared with other models, it has higher prediction accuracy and stronger robustness to non-stationary sequences.

Key words: wind power prediction, feature selection, PCA

CHEN Zhongzhong, GENG Xiaofei, DONG Xiangming, LI Lianghao, HU Jiawei, WU Congwen, KANG Fuquan. Wind power prediction based on PCA and SOFTS fusion model[J]. Electric Power, 2026, 59(6): 125-132.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202510044

https://www.electricpower.com.cn/EN/Y2026/V59/I6/125

Figures/Tables 8

References 35

1	闫朝阳, 李杰, 刘韶峰, 等. 计及多资源投运占比的电力系统惯量量化评估方法[J]. 中国电力, 2026, 59 (4): 59- 69.
	YAN Zhaoyang, LI Jie, LIU Shaofeng, et al. A quantitative evaluation method for power system inertia considering the proportion of multiple resources in operation[J]. Electric Power, 2026, 59 (4): 59- 69.
2	徐涛, 李互刚, 杨龙雨. 基于交叉支路增强VSG控制的谐波抑制策略[J]. 中国电力, 2026, 59 (4): 70- 78.
	XU Tao, LI Hugang, YANG Longyu. Harmonic suppression strategy based on cross-branch enhanced VSG control[J]. Electric Power, 2026, 59 (4): 70- 78.
3	周洋, 黄德志, 李培栋, 等. 考虑平衡端点相位不对称及光伏接入的低压配电网三相潮流模型[J]. 中国电力, 2024, 57 (10): 190- 198.
	ZHOU Yang, HUANG Dezhi, LI Peidong, et al. A three-phase power flow model for low-voltage distribution networks considering balanced bus phase asymmetry and photovoltaic access[J]. Electric Power, 2024, 57 (10): 190- 198.
4	丁杨, 唐培全, 张文奎, 等. 考虑涉网一次调频考核要求面向风储联合系统收益优化的储能容量配置[J]. 山东电力技术, 2025, 52 (2): 46- 54.
	DING Yang, TANG Peiquan, ZHANG Wenkui, et al. Optimal allocation of energy storage for profit optimization in wind-storage systems considering primary frequency regulation examinations[J]. Shandong Electric Power, 2025, 52 (2): 46- 54.
5	孙怡文, 邢海军, 梅丘梅, 等. 计及风电-光伏出力相关性的新型电力系统可靠性评估[J]. 浙江电力, 2025, 44 (9): 13- 20.
	SUN Yiwen, XING Haijun, MEI Qiumei, et al. Reliability assessment of modern power systems accounting for the correlation of wind-PV output correlation[J]. Zhejiang Electric Power, 2025, 44 (9): 13- 20.
6	吴龙腾, 郭乾, 吴杰康, 等. 台风灾害中配电网故障抢修策略[J]. 山东电力技术, 2025, 52 (3): 49- 58.
	WU Longteng, GUO Qian, WU Jiekang, et al. Fault repair strategy for distribution network in typhoon disaster[J]. Shandong Electric Power, 2025, 52 (3): 49- 58.
7	周涛, 姚嘉辰, 倪俊, 等. 基于改进模糊自适应控制的风电机组逐步惯性最优控制策略[J]. 浙江电力, 2025, 44 (11): 35- 47.
	ZHOU Tao, YAO Jiachen, NI Jun, et al. An optimal stepwise inertial control strategy for wind turbines based on improved fuzzy adaptive control[J]. Zhejiang Electric Power, 2025, 44 (11): 35- 47.
8	邓祥力, 陈聪颖. 频率时空差异下考虑功率波动的新能源主动调频优化方法[J]. 浙江电力, 2025, 44 (12): 22- 34.
	DENG Xiangli, CHEN Congying. An optimization method for active frequency regulation of renewable energy accounting for power fluctuations under spatiotemporal differences[J]. Zhejiang Electric Power, 2025, 44 (12): 22- 34.
9	白留星, 吴飞宇, 叶露阳, 等. 考虑风电不确定性的电力现货市场联合出清模型[J]. 综合智慧能源, 2025, 47 (5): 73- 83.
	BAI Liuxing, WU Feiyu, YE Luyang, et al. A joint clearing model of electricity spot market considering wind power uncertainty[J]. Integrated Intelligent Energy, 2025, 47 (5): 73- 83.
10	王芊瑞, 阮景昕, 王跃社. 考虑风、光出力时空相关性的电-氢协同储能系统经济性优化调度研究[J]. 综合智慧能源, 2025, 47 (12): 34- 45.
	WANG Qianrui, RUAN Jingxin, WANG Yueshe. Economic optimal scheduling of electricity-hydrogen coordinated energy storage system considering spatiotemporal correlation of wind and photovoltaic power outputs[J]. Integrated Intelligent Energy, 2025, 47 (12): 34- 45.
11	杨彪, 刘素蔚, 高洪达, 等. 数字经济下的能源新基建[M]. 北京: 经济科学出版社, 2024.
12	杨国华, 祁鑫, 贾睿, 等. 基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测[J]. 中国电力, 2024, 57 (2): 55- 61.
	YANG Guohua, QI Xin, JIA Rui, et al. Short-term wind power forecast based on CNN & LSTM-GRU model integrated with CEEMD-SE algorithm[J]. Electric Power, 2024, 57 (2): 55- 61.
13	程先龙, 张杰, 李思莹, 等. 基于VMD-BP-BiLSTM的短期风电功率预测[J]. 综合智慧能源, 2025, 47 (6): 20- 29.
	CHENG Xianlong, ZHANG Jie, LI Siying, et al. Short-term wind power prediction based on VMD-BP-BiLSTM[J]. Integrated Intelligent Energy, 2025, 47 (6): 20- 29.
14	郝露茜, 刘琳, 刘白杨, 等. 基于变分模态分解和麻雀搜索算法的双向长短期记忆网络的风电短期功率预测方法研究[J]. 湖南电力, 2024, 44 (3): 89- 95.
	HAO Luxi, LIU Lin, LIU Baiyang, et al. Research on short-term wind power prediction method of bidirectional long short-term memory based on variational mode decomposition and sparrow search algorithm[J]. Hunan Electric Power, 2024, 44 (3): 89- 95.
15	李振海, 李钰炎, 易志高, 等. 基于长短时记忆网络和轻梯度增强机的风电功率多步预测[J]. 湖南电力, 2023, 43 (6): 68- 75.
	LI Zhenhai, LI Yuyan, YI Zhigao, et al. Multi-step prediction of wind power based on long short-term memory network and light gradient boosting machine[J]. Hunan Electric Power, 2023, 43 (6): 68- 75.
16	苏向敬, 宇海波, 符杨, 等. 基于DALSTM和联合分位数损失的海上风电功率概率预测[J]. 中国电力, 2023, 56 (11): 10- 19.
	SU Xiangjing, YU Haibo, FU Yang, et al. Probabilistic forecasting of offshore wind power based on dual-stage attentional LSTM and joint quantile loss function[J]. Electric Power, 2023, 56 (11): 10- 19.
17	彭宇文, 杨之乐, 李冰, 等. 基于VMD-ISSA-LSTM的短期光伏发电功率预测[J]. 广东电力, 2024, 37 (1): 18- 26.
	PENG Yuwen, YANG Zhile, LI Bing, et al. Short term photovoltaic power generation prediction based on VMD-ISSA-LSTM[J]. Guangdong Electric Power, 2024, 37 (1): 18- 26.
18	马志光. 基于GWO-VMD-LSTM的超短期风电功率预测[J]. 自动化应用, 2025, 66 (23): 80- 83.
	MA Zhiguang. Ultra-short-term wind power prediction based on GWO-VMD-LSTM[J]. Automation Application, 2025, 66 (23): 80- 83.
19	滕云雷, 李桓. 基于WSO-LSTM的风电功率预测技术研究[J]. 电工电气, 2025 (12): 22- 28.
	TENG Yunlei, LI Huan. The research on wind power prediction technology based on WSO-LSTM[J]. Electrotechnics Electric, 2025 (12): 22- 28.
20	陈磊, 黄凯阳, 张怡, 等. 基于信息调控和MATCN的超短期风电功率多步预测[J]. 现代电子技术, 2024, 47 (18): 1- 7.
	CHEN Lei, HUANG Kaiyang, ZHANG Yi, et al. Ultra-short-term wind power multi-step forecasting based on information regulation and MATCN[J]. Modern Electronics Technique, 2024, 47 (18): 1- 7.
21	田书欣, 姜皓喆, 秦世耀, 等. 基于CKAN-IWTC-LSTM的海上风电功率预测方法[J]. 智慧电力, 2025, 53 (11): 91- 98.
	TIAN Shuxin, JIANG Haozhe, QIN Shiyao, et al. Offshore wind power forecasting method based on CKAN-IWTC-LSTM[J]. Smart Power, 2025, 53 (11): 91- 98.
22	宋江涛, 崔双喜, 樊小朝, 等. 基于SGMD-SE与优化TCN-BiLSTM/BiGRU的超短期风功率预测[J]. 太阳能学报, 2024, 45 (10): 588- 596.
	SONG Jiangtao, CUI Shuangxi, FAN Xiaochao, et al. Ultra-short-term wind power prediction based on sgmd-se and optimized tcn-BiLSTM/BiGRU[J]. Acta Energiae Solaris Sinica, 2024, 45 (10): 588- 596.
23	马志侠, 张林鍹, 巴音塔娜, 等. 基于自适应二次分解与CNN-BiLSTM的超短期风电功率预测[J]. 太阳能学报, 2024, 45 (6): 429- 435.
	MA Zhixia, ZHANG Linxuan, BA Yintana, et al. Ultra-short-term wind power prediction based on adaptive quadratic mode decomposition and cnn-BiLSTM[J]. Acta Energiae Solaris Sinica, 2024, 45 (6): 429- 435.
24	甘恒玉, 黄莉, 刘兴举, 等. 基于iInformer的超短期风电功率多步预测[J]. 河南大学学报(自然科学版), 2024, 54 (5): 576- 586.
	GAN Hengyu, HUANG Li, LIU Xingju, et al. Multi-step prediction of ultra-short-term wind power based on iInformer[J]. Journal of Henan University (Natural Science), 2024, 54 (5): 576- 586.
25	XIANG L, FU X, YAO Q T, et al. A novel model for ultra-short term wind power prediction based on Vision Transformer[J]. Energy, 2024, 294, 130854.
26	WEI H, WANG W, KAO X. A novel approach to ultra-short-term wind power prediction based on feature engineering and informer[J]. Energy Reports, 2023, 9, 1236- 1250.
27	DAI X R, LIU G P, HU W S. An online-learning-enabled self-attention-based model for ultra-short-term wind power forecasting[J]. Energy, 2023, 272, 127173.
28	李特, 黄孜滢. 机器学习在风力发电功率预测中应用综述[J]. 山东电力技术, 2025, 52 (8): 45- 55.
	LI Te, HUANG Ziying. Overview of application of machine learning in wind power forecasting[J]. Shandong Electric Power, 2025, 52 (8): 45- 55.
29	张海涛, 李文娟, 李雪峰, 等. 基于变分模态分解和时间注意力机制TCN网络的光伏发电功率预测[J]. 电测与仪表, 2024, 61 (12): 156- 163.
	ZHANG Haitao, LI Wenjuan, LI Xuefeng, et al. Photovoltaic power forecasting based on TPA-TCN model and variational modal decomposition[J]. Electrical Measurement & Instrumentation, 2024, 61 (12): 156- 163.
30	WANG Z, NIE Y, SUN P, et al. A cascaded spatio-temporal linear framework with channel-independence strategy for traffic forecasting[J]. arXiv: 2308.07496, 2023.
31	HAN L, CHEN X Y, YE H J, et al. Efficient multivariate time series forecasting with series-core fusion[C]//Advances in Neural Information Processing Systems (NeurIPS). Vancouver: NeurIPS Organizing Committee, 2024: 14521–14530.
32	李翔, 张涛, 张哲, 等. Transformer在计算机视觉领域的研究综述[J]. 计算机工程与应用, 2023, 59 (1): 1- 14.
	LI Xiang, ZHANG Tao, ZHANG Zhe, et al. Survey of transformer research in computer vision[J]. Computer Engineering and Applications, 2023, 59 (1): 1- 14.
33	朱东杰, 吕昆烨, 宋长虹, 等. 基于密度修正的风电功率曲线线性拟合模型[J]. 综合智慧能源, 2025, 47 (3): 84- 91.
	ZHU Dongjie, LYU Kunye, SONG Changhong, et al. Linear fitting model for wind power curves based on density correction[J]. Integrated Intelligent Energy, 2025, 47 (3): 84- 91.
34	臧海祥, 赵勇凯, 张越, 等. 基于低风速功率修正和损失函数改进的超短期风电功率预测[J]. 电力系统自动化, 2024, 48 (7): 248- 257.
	ZANG Haixiang, ZHAO Yongkai, ZHANG Yue, et al. Ultra-short-term wind power prediction based on power correction under low wind speed and improved loss function[J]. Automation of Electric Power Systems, 2024, 48 (7): 248- 257.
35	韩丽, 于晓娇, 喻洪波, 等. 基于波动趋势分段的风电功率区间预测[J]. 电力系统自动化, 2023, 47 (18): 206- 215.
	HAN Li, YU Xiaojiao, YU Hongbo, et al. Wind power interval prediction based on fluctuation trend segmentation[J]. Automation of Electric Power Systems, 2023, 47 (18): 206- 215.

参数	设置
输入序列长度	4
预测序列长度	1
编码器层数	3
解码器层数	1
编码器的输入维度	21
解码器的输入维度	21
解码器的输出维度	21
模型的维度	512
全卷积网络的中间向量维度	512
学习率	0.000 3
神经元随机失活率	0.1
训练轮数	1 000
提前停止容忍次数	15
批次大小	256
主成分数	10

参数	设置
输入序列长度	4
预测序列长度	1
编码器层数	3
解码器层数	1
编码器的输入维度	21
解码器的输入维度	21
解码器的输出维度	21
模型的维度	512
全卷积网络的中间向量维度	512
学习率	0.000 3
神经元随机失活率	0.1
训练轮数	1 000
提前停止容忍次数	15
批次大小	256
主成分数	10

变量	重要性分数
云量	2.276 3
海平面气压	2.056 6
2 m相对湿度	1.885 2
大尺度降水	1.730 6
对流降水	1.621 8
动量通量	1.573 0
长波辐射通量	1.552 1
距地面100 m处风速	1.547 7
距地面10 m处风向	1.524 7
距地面70 m处风速	1.521 0
短波辐射通量	1.491 8
地表水压	1.468 9
感热通量	1.455 9
30 m温度	1.423 8
潜热通量	1.412 2
距地面100 m处风向	1.398 5
距地面30 m处风速	1.376 1
距地面70 m处风向	1.310 4
2 m温度	1.309 1
距地面10 m处风速	1.138 1
距地面30 m处风向	1.112 3
总降水	1.102 1

变量	重要性分数
云量	2.276 3
海平面气压	2.056 6
2 m相对湿度	1.885 2
大尺度降水	1.730 6
对流降水	1.621 8
动量通量	1.573 0
长波辐射通量	1.552 1
距地面100 m处风速	1.547 7
距地面10 m处风向	1.524 7
距地面70 m处风速	1.521 0
短波辐射通量	1.491 8
地表水压	1.468 9
感热通量	1.455 9
30 m温度	1.423 8
潜热通量	1.412 2
距地面100 m处风向	1.398 5
距地面30 m处风速	1.376 1
距地面70 m处风向	1.310 4
2 m温度	1.309 1
距地面10 m处风速	1.138 1
距地面30 m处风向	1.112 3
总降水	1.102 1

模型	E_ACC/%	E_MS/MW	E_MAP/%
SOFTS	95.77	17.510 9	23.83
PCA-LSTM	93.69	39.787 7	29.00
PCA-PatchTST	98.24	3.051 7	18.22
PCA-SOFTS	98.38	2.568 7	15.49