发电技术 ›› 2024, Vol. 45 ›› Issue (2): 323-330.DOI: 10.12096/j.2096-4528.pgt.22038
邵宜祥, 刘剑, 胡丽萍, 过亮, 方渊, 李睿
收稿日期:
2023-03-15
出版日期:
2024-04-30
发布日期:
2024-04-29
作者简介:
基金资助:
Yixiang SHAO, Jian LIU, Liping HU, Liang GUO, Yuan FANG, Rui LI
Received:
2023-03-15
Published:
2024-04-30
Online:
2024-04-29
Supported by:
摘要:
超短期风速预测是保障风电机组桨距角前馈控制实施效果的关键,对提高风电机组环境适应性具有重要影响。为了提高预测精度,提出了一种改进组合神经网络的超短期风速预测方法。该方法选择适合时间序列预测且具有较强非线性学习能力的BP神经网络和长短期记忆(long short-term memory,LSTM)神经网络进行加权组合,以消除单个神经网络可能存在的较大误差;同时,为了提高组合效果,采用差分进化算法对组合权重进行优化。将该方法应用于某风场超短期风速预测中,通过与单神经网络预测、等权重组合神经网络预测的结果对比,验证了所提方法在提高预测精度上的有效性。
中图分类号:
邵宜祥, 刘剑, 胡丽萍, 过亮, 方渊, 李睿. 一种改进组合神经网络的超短期风速预测方法研究[J]. 发电技术, 2024, 45(2): 323-330.
Yixiang SHAO, Jian LIU, Liping HU, Liang GUO, Yuan FANG, Rui LI. Research on an Ultra-Short-Term Wind Speed Prediction Method Based on Improved Combined Neural Networks[J]. Power Generation Technology, 2024, 45(2): 323-330.
a个输入 | b个输出 |
---|---|
x1,x2,…,xa | xa+1,xa+2,…,xa+b |
x2,x3,…,xa+1 | xa+2,xa+3,…,xa+b+1 |
… | … |
xK,xK+1,…,xK+a-1 | xK+a,xK+a+2,…,xK+a+b-1 |
表1 风速样本映射结构
Tab. 1 Wind speed sample mapping structure
a个输入 | b个输出 |
---|---|
x1,x2,…,xa | xa+1,xa+2,…,xa+b |
x2,x3,…,xa+1 | xa+2,xa+3,…,xa+b+1 |
… | … |
xK,xK+1,…,xK+a-1 | xK+a,xK+a+2,…,xK+a+b-1 |
图6 2种模型风速预测结果误差分布频数直方图及其高斯拟合曲线
Fig. 6 Frequency histogram of the error distribution of the wind speed prediction results of the two models and its Gauss fitting curve
误差 | 等权重组合预测模型 | DE优化组合预测模型 |
---|---|---|
EMAE/(m/s) | 0.087 7 | 0.086 1 |
ERMSE/(m/s) | 0.120 1 | 0.117 8 |
EMAPE/% | 1.619 3 | 1.591 1 |
EME/(m/s) | -0.025 2 | -0.025 1 |
表2 2种模型风速预测结果的评价指标
Tab. 2 Evaluation metrics for the wind speed prediction results of the two models
误差 | 等权重组合预测模型 | DE优化组合预测模型 |
---|---|---|
EMAE/(m/s) | 0.087 7 | 0.086 1 |
ERMSE/(m/s) | 0.120 1 | 0.117 8 |
EMAPE/% | 1.619 3 | 1.591 1 |
EME/(m/s) | -0.025 2 | -0.025 1 |
图8 不同模型风速预测结果误差分布频数直方图及其高斯拟合曲线
Fig. 8 Frequency histogram of the error distribution of the wind speed prediction results of the different models and its Gauss fitting curve
误差 | BP 神经网络预测模型 | LSTM神经网络预测模型 | DE优化组合预测模型 |
---|---|---|---|
EMAE/(m/s) | 0.096 5 | 0.089 6 | 0.086 1 |
ERMSE/(m/s) | 0.129 5 | 0.122 0 | 0.117 8 |
EMAPE/% | 1.772 3 | 1.652 0 | 1.591 1 |
EME/(m/s) | -0.025 5 | -0.025 3 | -0.025 1 |
表3 不同模型风速预测结果的评价指标
Tab. 3 Evaluation metrics for the wind speed prediction results of the different models
误差 | BP 神经网络预测模型 | LSTM神经网络预测模型 | DE优化组合预测模型 |
---|---|---|---|
EMAE/(m/s) | 0.096 5 | 0.089 6 | 0.086 1 |
ERMSE/(m/s) | 0.129 5 | 0.122 0 | 0.117 8 |
EMAPE/% | 1.772 3 | 1.652 0 | 1.591 1 |
EME/(m/s) | -0.025 5 | -0.025 3 | -0.025 1 |
1 | 颜湘武,王德胜,隗小雪,等 .风电机组故障穿越与频率调节风储联合控制策略研究[J].中国电机工程学报,2021,41(17):5911-5923. doi:10.13334/j.0258-8013.pcsee.201129 |
YAN X W, WANG D S, WEI X X,et al .Research on the wind power-storage joint control based on fault ride-through and frequency regulation of wind turbine[J].Proceedings of the CSEE,2021,41(17):5911-5923. doi:10.13334/j.0258-8013.pcsee.201129 | |
2 | 王诗超,孙仕达,郝为瀚,等 .基于VSC与DRU的混合级联型海上风电直流外送系统控制与阻抗建模[J].电力建设,2022,43(4):38-48. doi:10.12204/j.issn.1000-7229.2022.04.005 |
WANG S C, SUN S D, HAO W H,et al .Control and impedance modeling of offshore wind power hybrid cascaded DC transmission system based on of VSC and DRU[J].Electric Power Construction,2022,43(4):38-48. doi:10.12204/j.issn.1000-7229.2022.04.005 | |
3 | 李铮,郭小江,申旭辉,等 .我国海上风电发展关键技术综述[J].发电技术,2022,43(2):186-197. doi:10.12096/j.2096-4528.pgt.22028 |
LI Z, GUO X J, SHEN X H,et al .Summary of technologies for the development of offshore wind power industry in China[J].Power Generation Technology,2022,43(2):186-197. doi:10.12096/j.2096-4528.pgt.22028 | |
4 | 房方,梁栋炀,刘亚娟,等 .海上风电智能控制与运维关键技术[J].发电技术,2022,43(2):175-185. doi:10.12096/j.2096-4528.pgt.22042 |
FANG F, LIANG D Y, LIU Y J,et al .Key technologies for intelligent control and operation and maintenance of offshore wind power[J].Power Generation Technology,2022,43(2):175-185. doi:10.12096/j.2096-4528.pgt.22042 | |
5 | 瞿晟珉,应飞祥,秦少茜,等 .“双碳”背景下海上风电维护策略研究现状与展望[J].智慧电力,2023,51(10):23-30. |
QU S M, YING F X, QIN S X,et al .Research status and prospects of offshore wind power maintenance strategy under background of carbon peak and carbon neutrality[J].Smart Power,2023,51(10):23-30. | |
6 | 李国庆,徐亚男,江守其,等 .海上风电经柔性直流联网系统受端交流故障穿越协调控制策略[J].电力系统保护与控制,2022,50(7):111-119. |
LI G Q, XU Y N, JIANG S Q,et al .Coordinated control strategy for receiving-end AC fault ride-through of an MMC-HVDC connecting offshore wind power[J].Power System Protection and Control,2022,50(7):111-119. | |
7 | 陈露洁,徐式蕴,孙华东,等 .高比例电力电子电力系统宽频带振荡研究综述[J].中国电机工程学报,2021,41(7):2297-2310. doi:10.13334/j.0258-8013.pcsee.191863 |
CHEN L J, XU S Y, SUN H D,et al .A survey on wide-frequency oscillation for power systems with high penetration of power electronics[J].Proceedings of the CSEE,2021,41(7):2297-2310. doi:10.13334/j.0258-8013.pcsee.191863 | |
8 | 胡姚刚,刘怀盛,时萍萍,等 .风电机组偏航系统故障诊断与寿命预测综述[J].中国电机工程学报,2022,42(13):4871-4883. |
HU Y G, LIU H S, SHI P P,et al .Overview of fault diagnosis and life prediction for wind turbine yaw system[J].Proceedings of the CSEE,2022,42(13):4871-4883. | |
9 | 王爽心,郭婷婷,李蒙 .风电机组变工况变桨系统异常状态在线识别[J].中国电机工程学报,2019,39(17):5144-5152. |
WANG S X, GUO T T, LI M .On-line abnormal state identification of pitch system based on transitional mode for wind turbine[J].Proceedings of the CSEE,2019,39(17):5144-5152. | |
10 | 陈子含,滕伟,胥学峰,等 .基于图卷积网络和风速差分拟合的中长期风功率预测[J].中国电力,2023,56(10):96-105. |
CHEN Z H, TENG W, XU X F,et al .Medium and long term wind power prediction based on graph convolutional network and wind velocity differential fitting[J].Electric Power System,2023,56(10):96-105. | |
11 | 丁藤,冯冬涵,林晓凡,等 .基于修正后ARIMA-GARCH模型的超短期风速预测[J].电网技术,2017,41(6):1808-1814. |
DING T, FENG D H, LIN X F,et al .Ultra-short-term wind speed forecasting based on improved ARIMA-GARCH model[J].Power System Technology,2017,41(6):1808-1814. | |
12 | 乔倜傥,谢丽蓉,叶家豪,等 .基于风速波动特性划分的短期风电功率预测[J/OL].电测与仪表:1-9[2023-02-17].. |
QIAO T T, XIE L R, YE J H,et al .Short-term wind power forecasting based on wind speed fluctuation characteristics[J/OL].Electrical Measurement and Instrumentation:1-9[2023-02-17].. | |
13 | 苏艳萍,田源 .变速恒频风力发电系统风速短期预测方法研究[J].电网与清洁能源,2022,38(2):88-93. doi:10.3969/j.issn.1674-3814.2022.02.013 |
SU Y P, TIAN Y .Research on short-term wind speed prediction method of variable speed constant frequency wind power generation system[J].Power System and Clean Energy,2022,38(2):88-93. doi:10.3969/j.issn.1674-3814.2022.02.013 | |
14 | 凡航,张雪敏,梅生伟,等 .基于时空神经网络的风电场超短期风速预测模型[J].电力系统自动化,2021,45(1):28-35. doi:10.7500/AEPS20190831001 |
FAN H, ZHANG X M, MEI S W,et al .Ultra-short-term wind speed prediction model for wind farms based on spatiotemporal neural network[J].Automation of Electric Power Systems,2021,45(1):28-35. doi:10.7500/AEPS20190831001 | |
15 | 薛禹胜,郁琛,赵俊华,等 .关于短期及超短期风电功率预测的评述[J].电力系统自动化,2015,39(6):141-151. doi:10.7500/AEPS20141218003 |
XUE Y S, YU C, ZHAO J H,et al .A review on ultra-short-term wind power prediction[J].Automation of Electric Power Systems,2015,39(6):141-151. doi:10.7500/AEPS20141218003 | |
16 | VILLANUEVA D, FEIJÓO A .Normal-based model for true power curves of wind turbines[J].IEEE Transactions on Sustainable Energy,2016,7(3):1005-1011. doi:10.1109/tste.2016.2515264 |
17 | 丁华杰,宋永华,胡泽春,等 .基于风电场功率特性的日前风电预测误差概率分布研究[J].中国电机工程学报,2013,33(34):136-144. |
DING H J, SONG Y H, HU Z C,et al .Probability density function of day-ahead wind power forecast errors based on power curves of wind farms[J].Proceedings of the CSEE,2013,33(34):136-144. | |
18 | 肖永山,王维庆,霍晓萍 .基于神经网络的风电场风速时间序列预测研究[J].节能技术,2007(2):106-108. doi:10.3969/j.issn.1002-6339.2007.02.003 |
XIAO Y S, WANG W Q, HUO X P .Study on the time-series wind speed forecasting of the wind farm based on neural networks[J].Energy Conservation Technology,2007(2):106-108. doi:10.3969/j.issn.1002-6339.2007.02.003 | |
19 | 王一珺,贾嵘 .基于Elman和实测风速功率数据的短期风功率预测[J].高压电器,2017,53(9):125-129. |
WANG Y J, JIA R .Short-term wind power forecasting based on Elman neural network and measured wind speed power data[J].High Voltage Apparatus,2017,53(9):125-129. | |
20 | 段新会,李文鑫 .基于改进粒子群优化神经网络的超短期风速预测[J].自动化与仪表,2021,36(3):76-80. |
DUAN X H, LI W X .Ultra-short-term wind speed prediction based on improved particle swarm neural network algorithm[J].Automation & Instrumentation,2021,36(3):76-80. | |
21 | 李冰,张妍,刘石 .基于LSTM的短期风速预测研究[J].计算机仿真,2018,35(11):456-461. doi:10.3969/j.issn.1006-9348.2018.11.099 |
LI B, ZHANG Y, LIU S .Wind speed short term prediction study based on LSTM[J].Computer Simulation,2018,35(11):456-461. doi:10.3969/j.issn.1006-9348.2018.11.099 | |
22 | 朱丽娜 .风电场短期风速预测方法研究[D].兰州:兰州理工大学,2021. |
ZHU L N .Research on short-term wind speed prediction method for wind farm[D].Lanzhou :Lanzhou University of Technology,2021. | |
23 | WANG K, QI X, LIU H,et al .Deep belief network based k-means cluster approach for short-term wind power forecasting[J].Energy,2018,165:840-852. doi:10.1016/j.energy.2018.09.118 |
24 | 刘纯,范高锋,王伟胜,等 .风电场输出功率的组合预测模型[J].电网技术,2009,33(13):74-79. |
LIU C, FAN G F, WANG W S,et al .A combination forecasting model for wind farm output power[J].Power System Technology,2009,33(13):74-79. | |
25 | 张妍,王东风,韩璞 .一种风电场短期风速组合预测模型[J].太阳能学报,2017,38(6):1510-1516. |
ZHANG Y, WANG D F, HAN P .Combination forecasting model of short-term wind speed for wind farm[J].Acta Energiae Solaris Sinica,2017,38(6):1510-1516. | |
26 | 赵征,王晓亮,张亚刚 .基于ARMA-ARCH模型和BP模型的短期风速组合预测方法研究[J].电网与清洁能源,2018,34(11):45-51. doi:10.3969/j.issn.1674-3814.2018.11.008 |
ZHAO Z, WANG X L, ZHANG Y G .Short-term wind speed combined prediction based on ARMA-ARCH model and BP model[J].Power System and Clean Energy,2018,34(11):45-51. doi:10.3969/j.issn.1674-3814.2018.11.008 | |
27 | 刘辉,李岩,曹权 .基于小波分解的神经网络组合风速预测[J].电气自动化,2021,43(1):45-47. doi:10.3969/j.issn.1000-3886.2021.01.014 |
LIU H, LI Y, CAO Q .Wind speed prediction through neural network combination based on wavelet decomposition[J].Electrical Automation,2021,43(1):45-47. doi:10.3969/j.issn.1000-3886.2021.01.014 | |
28 | 王耀庆,孙建平,李冰,等 .基于小波变换和LSTM的短期风速预测研究[J].计算机仿真,2021,38(2):438-443. doi:10.3969/j.issn.1006-9348.2021.02.092 |
WANG Y Q, SUN J P, LI B,et al .Short-term wind speed forecasting study based on wavelet transform and LSTM[J].Computer Simulation,2021,38(2):438-443. doi:10.3969/j.issn.1006-9348.2021.02.092 | |
29 | 王俊,李霞,周昔东,等 .基于VMD和LSTM的超短期风速预测[J].电力系统保护与控制,2020,48(11):45-52. |
WANG J, LI X, ZHOU X D,et al .Ultra-short-term wind speed prediction based on VMD-LSTM[J].Power System Protection and Control,2020,48(11):45-52. | |
30 | 李相俊,许格健 .基于长短期记忆神经网络的风力发电功率预测方法[J].发电技术,2019,40(5):426-433. doi:10.12096/j.2096-4528.pgt.19108 |
LI X J, XU G J .Wind power prediction method based on long short-term memory neural network[J].Power Generation Technology,2019,40(5):426-433. doi:10.12096/j.2096-4528.pgt.19108 |
[1] | 陈昱, 丁鸿, 崔勇, 朱里, 陈士俊, 凌秋阳, 徐勇生, 郑建. 变电设备温度态势感知及辅助决策系统方案研究[J]. 发电技术, 2024, 45(4): 744-752. |
[2] | 周丹, 袁至, 李骥, 范玮. 考虑平抑未来时刻风电波动的混合储能系统超前模糊控制策略[J]. 发电技术, 2024, 45(3): 412-422. |
[3] | 刘洪波, 刘永发, 任阳, 孙黎, 刘珅诚. 高风电渗透率下考虑系统风电备用容量的储能配置[J]. 发电技术, 2024, 45(2): 260-272. |
[4] | 贾晓强, 杨永标, 杜姣, 甘海庆, 杨楠. 气候变化条件下基于智能预测模型的虚拟电厂不确定性运行优化研究[J]. 发电技术, 2023, 44(6): 790-799. |
[5] | 安吉振, 郑福豪, 刘一帆, 陈衡, 徐钢. 基于大数据分析的火电机组引风机故障预警研究[J]. 发电技术, 2023, 44(4): 557-564. |
[6] | 苏靖程, 王志强, 屈江江, 张凯. 基于BP神经网络和支持向量回归的燃煤电厂空气预热器压差预测[J]. 发电技术, 2023, 44(4): 550-556. |
[7] | 时浩, 肖海平, 刘彦鹏. 基于BP神经网络和最小二乘支持向量机的灰熔点预测和对比[J]. 发电技术, 2022, 43(1): 139-146. |
[8] | 黄树帮, 陈耀, 金宇清. 碳中和背景下多通道特征组合超短期风电功率预测[J]. 发电技术, 2021, 42(1): 60-68. |
[9] | 宋学伟, 刘玉瑶. 基于改进K-means聚类的风光发电场景划分[J]. 发电技术, 2020, 41(6): 625-630. |
[10] | 朱月,沙俊民,赵静. 含不同机组风电场低电压穿越能力仿真研究[J]. 发电技术, 2020, 41(3): 328-333. |
[11] | 匡生,王蓓蓓. 考虑储能寿命和参与调频服务的风储联合运行优化策略[J]. 发电技术, 2020, 41(1): 73-78. |
[12] | 李相俊,许格健. 基于长短期记忆神经网络的风力发电功率预测方法[J]. 发电技术, 2019, 40(5): 426-433. |
[13] | 唐诗洁,陆强,曲艳超,任翠涛,杨勇平. 基于遗传算法优化BP神经网络的SCR脱硝系统催化剂体积设计[J]. 发电技术, 2019, 40(3): 246-252. |
[14] | 仇梓峰,王爽心,李蒙. 基于无人机图像的风力发电机叶片缺陷识别[J]. 发电技术, 2018, 39(3): 277-285. |
[15] | 孔德同, 贾思远, 王天品, 刘庆超. 基于振动分析的风力发电机故障诊断方法[J]. 发电技术, 2017, 38(1): 54-58. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||