基于长短期记忆神经网络超短期风功率预测的风储联合系统一次调频策略

魏乐; 季雯雯; 刘渝斌; 周鑫

doi:10.19725/j.cnki.1007-2322.2024.0057

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 >

基于长短期记忆神经网络超短期风功率预测的风储联合系统一次调频策略

新能源电力系统 | 更新时间：2026-06-02

- 基于长短期记忆神经网络超短期风功率预测的风储联合系统一次调频策略
- Primary Frequency Regulation Strategy for a Wind-storage-joint System Based on LSTM Ultra-short-term Power Generation Prediction
- 现代电力 2026年43卷第3期页码：518-529
- 作者机构：
  
  华北电力大学控制与计算机工程学院, 北京市昌平区,102206
- 作者简介：
  
  魏乐(1976)，女，博士，教授，硕士生导师，通信作者，研究方向为大机组建模与优化控制、电力大数据分析，E-mail：weile@ncepu.edu.cn
  季雯雯(1997)，女，硕士研究生，研究方向为风力发电预测及应用，E-mail：17863363820@163.com
  刘渝斌(1999)，男，硕士研究生，研究方向为储能在电力系统中的应用，E-mail：lyb221904@163.com
  周鑫(2001)，男，硕士研究生，研究方向为风力发电调频，E-mail：2221043518@qq.com
- 基金信息：
  
  国家自然科学基金项目 (52176005)。
- DOI：10.19725/j.cnki.1007-2322.2024.0057
  中图分类号： 3
- 纸质出版：2026
- 稿件说明：
移动端阅览
魏乐, 季雯雯, 刘渝斌, 等. 基于长短期记忆神经网络超短期风功率预测的风储联合系统一次调频策略[J]. 现代电力, 2026,43(3):518-529.

WEI Le, JI Wenwen, LIU Yubin, et al. Primary Frequency Regulation Strategy for a Wind-storage-joint System Based on LSTM Ultra-short-term Power Generation Prediction[J]. 2026, 43(3): 518-529.
魏乐, 季雯雯, 刘渝斌, 等. 基于长短期记忆神经网络超短期风功率预测的风储联合系统一次调频策略[J]. 现代电力, 2026,43(3):518-529. DOI： 10.19725/j.cnki.1007-2322.2024.0057.

WEI Le, JI Wenwen, LIU Yubin, et al. Primary Frequency Regulation Strategy for a Wind-storage-joint System Based on LSTM Ultra-short-term Power Generation Prediction[J]. 2026, 43(3): 518-529. DOI： 10.19725/j.cnki.1007-2322.2024.0057.

摘要

针对高比例不确定性风力发电并网所引起的频率波动、以及电力系统惯性降低导致的电网调频能力减弱的问题，提出基于长短期记忆网络风功率预测的风储联合系统一次调频策略。首先，通过对历史数据的空间聚类和相关性分析进行风电场等值建模，并在此模型上基于长短期记忆网络进行风功率超短期预测；其次，根据风速区间选择风机变速或变桨调频的协调控制策略；最后，根据风功率预测偏差、电网频率偏差及其变化率调整功率型飞轮储能和能量型锂离子电池储能的辅助调频深度。在风储联合系统一次调频频率响应模型上进行仿真分析，结果显示风功率预测的准确率平均高达97.62%，所提风储联合一次调频策略相对于固定比例策略和单独风电调频策略，最大频率偏差分别减小了11.3%、28.6%，调节时间分别减小了27.1%和35.2%，有效地提升了风电调频性能，改善了电力系统频率特性。

Abstract

Aiming to address the instability caused by the high proportion of uncertain wind turbines connected to the grid

as well as the weakened frequency modulation ability due to the inertia reduction of the power system

a wind power prediction and primary frequency modulation strategy is proposed for integrated wind turbines and energy storage systems based on long and short term memory networks. Firstly

based on the spatial clustering algorithm and correlation analysis method

the equivalent modeling for a wind farm is conduced by employing historical data. With this model

the ultra-short term power prediction of wind power output is carried out based on long and short term memory networks. Secondly

the coordination control strategy of variable speed or variable pitch frequency modulation is selected according to the wind speed range. Finally

the auxiliary frequency modulation depth of power type flywheel storage and energy type battery storage is adjusted according to the predicted output deviation

frequency deviation and change rate of the wind turbines. Simulation experiments are carried out on a primary frequency modulation response model for integrated wind turbines and energy storage systems

which is built on Matlab/Simulink. The results demonstrate that the average prediction accuracy of wind power LSTM model reaches 97.62%

while the maximum frequency deviation of the proposed strategy is reduced by 11.3% and 28.6% respectively

compared with the fixed proportion strategy and the single wind power frequency modulation. In addition

the stabilization time is reduced by 27.1% and 35.2% respectively

thereby significantly improving both the frequency modulation performance of wind power and frequency characteristics of the power system.

关键词

Keywords

references

TANG Xinzi, GU Nengwei, HUANG Xuanqing, et al . Research progress of short-term prediction technology of wind power[J ] . Journal of Mechanical Engineering, 2022, 58(12): 213−236(in Chinese).

YONG S, ZHENYUAN L, XINNAN Y, et al . Research on ultra-short-term wind power prediction considering source relevance[J ] . IEEE ACCESS, 2020, 8147703−147710.

JANG Guimin, CHEN Zhijun, LI Xiaozhu, et al . Short-term wind power prediction based on EEMD-ACS-LSSVM[J ] . Acta Energiae Solaris Sinica , 2020, 41(05): 77−84(in Chinese).

HU Yang, LI Qian, FANG Fang, et al . Ultra-short term output dynamic interval modeling for wind power plants based on finite difference operating domain[J ] . Power System Technology, 2022, 46(04): 1346−1357(in Chinese).

MU Gang, CAI Tingting, YAN Gangui, et al . Bidirectional power constraints and their effects on doubly-fed wind turbines participating in continuous frequency modulation[J ] . Transactions of China Electrotechnical Society, 2019, 34(08): 1750−1759(in Chinese).

HAMOODI S, HAMEED F, HAMOODI A. Pitch angle control of wind turbine using adaptive fuzzy-PID controller[J]. EAI Endorsed Transactions on Energy Web, 2018, 0(0): 165500.

RASHMI P, PRASAD N P. Synergistic frequency regulation control mechanism for DFIG wind turbines with optimal pitch dynamics[J]. IEEE Transactions on Power Systems, 2020, 35(4): 3181−3191.

DONG Tianxiang, QU Baoyu, LI Xing, et al . The optimal control strategy of frequency response of combined wind storage system[J ] . Power System Technology, 2022, 46(10): 3980−3989(in Chinese).

ZHANG S, MISHRA Y, SHAHIDEHPOUR M. Fuzzy-logic based frequency controller for wind farms augmented with energy storage systems[J]. IEEE Transactions on Power Systems: A Publication of the Power Engineering Society, 2016, 31(2): 1595−1603.

MIAO Fufeng, TANG Xisheng, QI Zhiping. Frequency characteristic analysis of power system under combined frequency modulation of air storage[J]. High Voltage Engineering, 2015, 41(07): 2209−2216(in Chinese).

ZHAO Yongning, YE Lin, ZHU Qianwen. Characteristics and processing methods of abnormal data clusters of wind curtailment in wind farms[J]. Automation of Electric Power Systems, 2014, 38(21): 39−46(in Chinese).

SHEN Xiaojun, FU Xuejiao, ZHOU Chongcheng, et al . Wind turbine wind speed-power abnormal operation data characteristics and cleaning methods[J ] . Transactions of China Electrotechnical Society, 2018, 33(14): 3353−3361(in Chinese).

ARTI A, SINGH D S, BILAS R P. Mitigating the curse of dimensionality using feature projection techniques on electroencephalography datasets: an empirical review[J]. Artificial Intelligence Review, 2024, 57(3): 6−11.

XIE Luofeng, XU Huining, HUANG Qinyuan, et al . The double-tree complex wavelet packet and NCA-LSS VM are used to detect the internal defects of magnetic tiles[J ] . Journal of Zhejiang University(Engineering Science), 2017, 51(01): 184−191(in Chinese).

ZHANG Li, WANG Zong. Multi-label feature selection algorithm based on maximum correlation minimum redundancy joint mutual information[J]. Journal on Communications, 2018, 39(05): 111−122(in Chinese).

CUI Minyong, DONG Wentao, LU Zhigang. Convolution neural networks and long short-term memory networks based on density clustering mode decomposition for short term wind power prediction[J]. Modern Electric Power, 2024, 41(04): 631−641(in Chinese).

YANG Li, WU Yuxi, WANG Junli, et al . Review of recurrent neural networks[J ] . Journal of Computer Applications, 2018, 38(S2): 1−6+26(in Chinese).

JIANG Tao, CHANG Wenwen, LIU Xianchao, et al . A practical frequency response model and parameter identification method for large-scale wind power grid-connected systems considering information privacy[J ] . Power System Technology, 2024, 48(12): 4876−4885(in Chinese).

LI Junhui, LI Jing, ZHU Xingxu, et al . Prime frequency modulation cooperative control strategy of wind speed in combined wind storage system[J ] . Jilin Electric Power, 2023, 51(06): 7−12(in Chine se).

CHEN Jianghong, YUAN Teng, TONG Xin, et al . Coordinated control strategy of wind storage system based on fuzzy control[J ] . Modern Electric Power, 2025, 42(03): 592−600(in Chinese).

SU Jiantao, FENG Hao, ZHENG Zeming, et al . High voltage crossing control strategy of doubly-fed wind turbine considering pitch angle control[J ] . Electrical Automation, 2024, 46(01): 115−118(in Chinese).

FANG Fang, LIU Yubin, WANG Bingyu, et al . Optimal load distribution strategy of flywheel-thermal power combined secondary frequency modulation based on NSGA-Ⅱ[J ] . Automation of Electric Power Systems, 2024, 48(12): 79−88(in Chinese).

JIAN Xuehui, CHEN Chunlong, ZHAO Fei, et al . A multi-energy power system operation strategy that takes into account the operational flexibility of heat storage devices[J ] . Modern Electric Power, 2023, 40(04): 562−569(in Chinese).

GUO Dongze, ZHANG Jihong, WANG Qinyu, et al . Hybrid energy storage power distribution strategy to smooth out wind power output fluctuation[J ] . Energy Storage Science and Technology, 2024, 13(05): 1564-1573(in Chinese).

YAN Quanchun, GU Wen, FAN Lixin, et al . Energy storage helps wind turbines participate in the study of frequency modulation control strategy of power grid[J ] . Modern Electric Power, 2022, 39(05): 537−546(in Chinese).

浏览量

177

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于层次分析法AHP和TOPSIS的储能参与新能源一次调频选型方案

考虑荷电状态约束的储能参与电网一次调频综合控制策略

含风光火储的电力系统频率模糊自适应控制策略

基于改进海鸥–粒子群算法的火电机组一次调频参数辨识

高比例新能源电力系统惯量响应与一次调频功能的匹配关系研究