Ultra-short-term Wind Power Forecasting Based on Invariant Learning

LI Yuhao; YAN Jie; WANG Han; HAN Shuang; LIU Yongqian

doi:10.19805/j.cnki.jcspe.2025.250296

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Ultra-short-term Wind Power Forecasting Based on Invariant Learning

更新时间：2026-10-10

- Ultra-short-term Wind Power Forecasting Based on Invariant Learning
- Chinese Journal of Power Engineering Vol. 45, Issue 10, Pages: 1696-1703(2025)
- 作者机构：
  
  华北电力大学新能源学院,北京,102206
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2025.250296
  CLC：
- Online First：08 June 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
李玉浩,阎洁,王函,韩爽,刘永前. 基于不变学习的超短期风电功率预测动力工程学报, 2025, 45(10): 1696-1703 https://doi.

org/10.19805/j.cnki.jcspe.2025.250296
李玉浩,阎洁,王函,韩爽,刘永前. 基于不变学习的超短期风电功率预测动力工程学报, 2025, 45(10): 1696-1703 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.250296.

org/10.19805/j.cnki.jcspe.2025.250296 DOI：

摘要

由于天气状况、机组控制策略等外部因素的复杂性

未来预测数据常常偏离训练数据分布

从而导致超短期风电功率预测模型精度显著下降。为解决该问题

提出了基于不变学习的超短期风电功率预测方法

该方法通过联合优化环境推理模块与不变特征学习模块

学习不变特征与功率间映射关系

实现鲁棒性建模。结果表明:与2个基准模型相比

所提方法的归一化均方根误差和归一化平均绝对误差分别降低1.19~1.30百分点和0.41~0.68百分点。

Abstract

Due to the complexity of external factors such as weather conditions and wind turbine control strategies

future forecasting data often deviates from the training data distribution

leading to a significant decline in the accuracy of ultra-short-term wind power prediction models. To address this issue

an ultra-short-term wind power forecasting method based on invariant learning was proposed. The method learned the mapping relationship between invariant features and power by jointly optimizeing the environment inference module and the invariant feature learning module

achieving robust modeling. The results show that compared with two benchmark models

the proposed method reduces forecasting error of the normalized root mean square error and normalized mean absolute error by an average of 1.19-1.30 and 0.41-0.68 percentage points respectively.

关键词

Keywords

references

付炳喆, 王玮, 任国瑞, 等. 考虑增强特征选择的深度卷积-时序网络短期风功率预测[J]. 动力工程学报, 2024, 44(10): 1565-1573. FU Bingzhe, WANG Wei, REN Guorui, et al. Short-term wind power prediction with deep convolutional-temporal networks considering enhanced feature selection[J]. Journal of Chinese Society of Power Engineering, 2024, 44(10): 1565-1573.

魏乐, 戴泽, 陈远野, 等. 考虑多对一时空特征的短期风功率组合预测模型[J]. 动力工程学报, 2024, 44(12): 1869-1877. WEI Le, DAI Ze, CHEN Yuanye, et al. Combined prediction model of short-term wind power by considering many-to-one spatial-temporal features[J]. Journal of Chinese Society of Power Engineering, 2024, 44(12): 1869-1877.

LI Yuhao, WANG Han, YAN Jie, et al. Ultra-short-term wind power forecasting based on the strategy of "dynamic matching and online modeling"[J]. IEEE Transactions on Sustainable Energy, 2025, 16(1): 107-123.

崔杨, 王议坚, 黄彦浩, 等. 基于多元注意力框架与引导式监督学习的闭环风电功率超短期预测策略[J]. 中国电机工程学报, 2023, 43(4): 1334-1346. CUI Yang, WANG Yijian, HUANG Yanhao, et al. Closed-loop wind power ultra-short-term forecasting strategy based on multi-attention framework and guided supervised learning[J]. Proceedings of the CSEE, 2023, 43(4): 1334-1346.

WEI Junqiang, WU Xuejie, YANG Tianming, et al. Ultra-short-term forecasting of wind power based on multi-task learning and LSTM[J]. International Journal of Electrical Power & Energy Systems, 2023, 149: 109073.

LIU Lei, LIU Jicheng, YE Yu, et al. Ultra-short-term wind power forecasting based on deep Bayesian model with uncertainty[J]. Renewable Energy, 2023, 205: 598-607.

YANG Mao, GUO Yunfeng, HUANG Yutong. Wind power ultra-short-term prediction method based on NWP wind speed correction and double clustering division of transitional weather process[J]. Energy, 2023, 282: 128947.

YU Guangzheng, LU Liu, TANG Bo, et al. Ultra-short-term wind power subsection forecasting method based on extreme weather[J]. IEEE Transactions on Power Systems, 2023, 38(6): 5045-5056.

韩丽, 程颖洁, 王施琪, 等. 基于扩散模型和爬坡趋势分类的风电功率自适应区间预测[J]. 电网技术, 2024, 48(6): 2448-2457. HAN Li, CHENG Yingjie, WANG Shiqi, et al. Adaptive interval forecasting of wind power based on diffusion model and ramping trend classification[J]. Power System Technology, 2024, 48(6): 2448-2457.

潘春阳, 文书礼, 朱淼, 等. 基于概念漂移监测与增量更新机制的超短期风电功率在线预测[J]. 中国电机工程学报, 2025, 45(6): 2133-2144. PAN Chunyang, WEN Shuli, ZHU Miao, et al. Online ultra-short-term wind power forecasting based on concept drift detection and incremental updating mechanism[J]. Proceedings of the CSEE, 2025, 45(6): 2133-2144.

PAN Chunyang, WEN Shuli, ZHU Miao, et al. Hedge backpropagation based online LSTM architecture for ultra-short-term wind power forecasting[J]. IEEE Transactions on Power Systems, 2024, 39(2): 4179-4192.

LIU Haoxin, KAMARTHI H, KONG Lingkai, et al. Time-series forecasting for out-of-distribution generalization using invariant learning[C]//41st International Conference on Machine Learning. Vienna: OpenReview.net, 2024.

SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal: MIT Press, 2014: 3104-3112.

XU Shiwei, WANG Yongjun, XU Xinglei, et al. A multi-step wind power group forecasting seq2seq architecture with spatial-temporal feature fusion and numerical weather prediction correction[J]. Energy, 2024, 291: 130352.

MAEDA T N, SHIMIZU S. Causal additive models with unobserved variables[C]//Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence.Cambridge, MA, USA: PMLR, 2021: 97-106.

LIU Jiashuo, HU Zheyuan, CUI Peng, et al. Heterogeneous risk minimization[C]//Proceedings of the 38th International Conference on Machine Learning. [S.l.]:PMLR, 2021: 6804-6814.

WANG Han, ZHANG Ning, DU Ershun, et al. An adaptive identification method of abnormal data in wind and solar power stations[J]. Renewable Energy, 2023, 208: 76-93.

KAUFMAN L, ROUSSEEUW P J. Finding groups in data: an introduction to cluster analysis[M]. Hoboken: Wiley, 2005.

KIM T, KIM J, TAE Y, et al. Reversible instance normalization for accurate time-series forecasting against distribution shift[C]//The 10th International Conference on Learning Representations. Massachusetts, USA:OpenReview.net, 2022.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dual-channel Short-term Wind Power Forecasting Fusing Long- and Short-term Dependencies

Research on Multiaixal Creep Behavior and Failure Criteria of TP321 Stainless Steel at 650 ℃

Dynamic Modeling of SNCR Denitrification System for Waste Incinerators Based on BKA-Transformer-BiGRU

Double-layer Coordination Economic and Real-time Dispatching Strategy for Large-scale Energy Base

Research on the Thermoelectric Performance of a PVT System Based on a Full-flow Channel Cooling Collector

Related Author

GUO Lijin

LIANG Xiaolong

CAI Haoxiang

Related Institution

School of Control Science and Engineering, Tiangong University

Tianjin Key Laboratory of Intelligent Control of Electrical Equipment

AI问答

⁰