基于自适应核密度估计算法的风电功率超短期区间预测

郭恒宽; 田建艳; 刘竖威; 蒋莹莹; 杨立志

doi:10.19725/j.cnki.1007-2322.2024.0048

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于自适应核密度估计算法的风电功率超短期区间预测

新能源电力系统 | 更新时间：2026-06-02

- 基于自适应核密度估计算法的风电功率超短期区间预测
- Wind Power Ultra-short-term Interval Prediction Based on an Adaptive Kernel Density Estimation Algorithm
- 现代电力 2026年43卷第3期页码：499-508
- 作者机构：
  
  太原理工大学电气与动力工程学院,山西省,太原市,030024
- 作者简介：
  
  郭恒宽(1996)，男，硕士研究生，研究方向为风电功率预测，E-mail：1525558537@qq.com
  田建艳(1966)，女，博士，教授，通信作者，研究方向为复杂系统建模、综合能源系统管控等，E-mail：tut_tianjy@163.com
  刘竖威(1994)，男，硕士研究生，研究方向为数字孪生系统设计、综合能源管控，E-mail：2549120912@qq.com
  蒋莹莹(1998)，女，硕士研究生，研究方向为光伏出力预测，E-mail：630451226@qq.com
  杨立志(2000)，男，硕士研究生，研究方向为数字孪生系统设计、综合能源管控，E-mail：2042784576@qq.com
- 基金信息：
  
  山西省自然科学基金项目(202303021221026)。
- DOI：10.19725/j.cnki.1007-2322.2024.0048
  中图分类号： 3
- 纸质出版：2026
- 稿件说明：
移动端阅览
郭恒宽, 田建艳, 刘竖威, 等. 基于自适应核密度估计算法的风电功率超短期区间预测[J]. 现代电力, 2026,43(3):499-508.

GUO Hengkuan, TIAN Jianyan, LIU Shuwei, et al. Wind Power Ultra-short-term Interval Prediction Based on an Adaptive Kernel Density Estimation Algorithm[J]. 2026, 43(3): 499-508.
郭恒宽, 田建艳, 刘竖威, 等. 基于自适应核密度估计算法的风电功率超短期区间预测[J]. 现代电力, 2026,43(3):499-508. DOI： 10.19725/j.cnki.1007-2322.2024.0048.

GUO Hengkuan, TIAN Jianyan, LIU Shuwei, et al. Wind Power Ultra-short-term Interval Prediction Based on an Adaptive Kernel Density Estimation Algorithm[J]. 2026, 43(3): 499-508. DOI： 10.19725/j.cnki.1007-2322.2024.0048.

摘要

针对风电功率区间预测中核密度估计算法局部适应性不强的问题，提出一种自适应核密度估计算法，实现风电功率超短期区间预测。首先，构建基于双重注意力机制改进序列到序列(sequence to sequence

Seq2Seq)架构的长短期记忆神经网络风电功率超短期预测模型，对风电功率进行确定性预测。然后，利用提出的一种自适应核密度估计算法，对风电功率预测误差数据集进行核密度估计，得到误差数据集的概率密度函数。最后，通过对概率密度函数进行积分，得到误差数据集的分布函数，并根据分布函数求得不同置信度下的上侧和下侧分位数，将分位数和风电功率确定性预测值求和，实现相应置信度下的风电功率超短期区间预测。基于中国西北某风电场的数据进行仿真预测分析，结果表明该自适应核密度估计算法对风电功率预测误差数据具有更强的适应能力，验证了该风电功率区间预测模型的有效性。

Abstract

Aiming at the issue of insufficient local adaptability in kernel density estimation algorithm for wind power interval prediction

we propose an adaptive kernel density estimation algorithm for wind power ultra-short-term interval prediction. Firstly

a long short term-memory wind power ultra-short-term prediction model is constructed based on the improved sequence to sequence (Seq2Seq) architecture with a dual-stage attention mechanism for wind power deterministic prediction. Subsequently

an proposed adaptive kernel density estimation algorithm is utilized to estimate the kernel density of the historical wind power prediction error. The proposed algorithm is capable of adaptively adjusting the bandwidth according to the kernel density estimation of the prediction error. Finally

the cumulative distribution function of the prediction error is obtained by integrating the kernel density estimation results. In addition

the upper and lower quantiles under different confidence coefficients are calculated

and the ultra-short-term prediction intervals of wind power under the corresponding confidence coefficients are obtained by adding the quantiles and the deterministic prediction values. Simulation analysis based on the data from a wind farm in Northwest China demonstrate that the proposed adaptive kernel density estimation algorithm exhibits superior adaptive ability to wind power prediction error data. Moreover

the effectiveness of this wind power interval prediction model is validated through these experiments.

关键词

Keywords

references

ZHU Qiaomu, LI Hongyi, WANG Ziqi, et al . Short-term wind power forecasting based on LSTM[J ] . Power System Technology, 2017, 41(12): 3797−3802(in Chinese).

MU Y, WANG M, ZHENG X, et al . An improved LSTM-Seq2Seq-based forecasting method for electricity load[J ] . Frontiers in Energy Research, 2023, 10(1): 1−13.

XIONG B, LOU L, MENG X, et al . Short-term wind power forecasting bas ed on attention mechanism and deep learning[J ] . Electric Power Systems Research, 2022, 206(5): 1−9.

YAO Yue, LIU Da. Short-term wind power forecasting based on attention mechanism of CNN-LSTM[J]. Modern Electric Power, 2022, 39(2): 212−218(in Chinese).

MENG A, CHEN S, OU Z. et al. A novel few-shot learning approach for wind power prediction applying secondary evolutionary generative adversarial network[J]. Energy, 2022, 261(10): 1−15.

SU Xiangjing, ZHOU Wenxin, LI Chaojie, et al . Interpretable offshore wind power output forecasting based on dual-stage attention long short-term memory[J ] . Automation of Electric Power Systems, 2022, 46(7): 141−151(in Chinese).

WU Wenzu, QIAO Ying, LU Zongxiang, et al . Methods and prospects for probability forecasting of wind power[J ] . Automation of Electric Power Systems, 2017, 41(18): 167−175(in Chinese).

CUI W, WAN C, SONG Y. Ensemble deep learning-based non-crossing quantile regression for nonparametric probabilistic forecasting of wind power generation[J]. IEEE Transactions on Power Systems, 2023, 38(4): 3163−3178.

CHOI J, EOM H, BAEK S M. A wind power probabilistic model using the reflection method and multi-kernel function kernel density estimation[J]. Energies, 2022, 15(24): 1−17.

YANG Xiyun, XING Guotong, MA Xue, et al . A model of quantile regression with kernel extreme learing machine and wind power interval prediction[J ] . Acta Energiae Solaris Sinica, 2020, 41(11): 300−306(in Chinese).

HAQUE A U, NEHRIR M H, MANDAL P. A hybrid intelligent model for deterministic and quantile regression approach for probabilistic wind power forecasting[J]. IEEE Transactions on Power Systems, 2014, 29(4): 1663−1672.

JUBAN J, FUGON L, KARINIOTAKIS G. Probabilistic short-term wind power forecasting based on kernel density estimators[C]// European Wind Power Conference and Exhibition. Milan, Italy: EWEA, 2007: 7−10.

ZHU Manting. Research on wind power prediction based on deep learning[D]. Beijing: North China Electric Power University (Beijing), 2021(in Chinese).

YANG Xiu, CHEN Binchao, ZHU Lan, et al . Short-term probability density prediction of public building load based on correlation analysis and quantile regression of long short-term memory networks[J ] . Power System Technology, 2019, 43(9): 3061−3071(i n Chinese).

WANG Sen, SUN Yonghui, HOU Dongchen, et al . Ultra-short-term adaptive probabilistic prediction of wind power based on multi-window wide kernel density estimation[J ] . High Voltage Engineering, 2024, 50(7): 3070−3079(in Chinese).

WAHBAH M, MOHANDES B, EL-FOULY T H M, et al . Unbiased cross-validation kernel density estimation for wind and PV probabilistic modelling[J ] . Energy Conversion and Management, 2022, 266(6): 1−10.

MA Xiangjin. Research on wind power forecasting method based on long short-term memory networks and nonparametric kernel density estimation[D]. Shenyang: Northeastern University, 2020(in Chinese).

DENG Qilin, QIU Tianyu, SHEN Furao, et al . Adaptive online kernel density estimation method[D ] . Journal of Software, 2020, 31 (4): 1173−1188(in Chinese).

SHI Tian. Probability forecasting of bus short-term net load considering renewable energy access[D]. Nanjing: Southeast University, 2021(in Chinese).

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于图卷积神经网络−双向门控循环单元及注意力机制的风电功率短期预测模型

基于数据增强和特征注意力机制的灰狼优化算法−优化残差神经网络变压器故障诊断方法

基于注意力机制的卷积神经网络-长短期记忆网络的短期风电功率预测

基于非对称纳什议价博弈的独立储能电量保险服务模型

基于数据驱动和负荷准线的储能与多类用户需求响应优化策略