[1]朱希,林俊德,施翔宇,等.基于VMD-SSA及误差补偿的风电功率超短期预测[J].福建理工大学学报,2023,21(06):573-579.[doi:10.3969/j.issn.1672-4348.2023.06.010]
　ZHU Xi,LIN Junde,SHI Xiangyu,et al.Ultra-short-term prediction of wind powerbased on VMD-SSA and error compensation[J].Journal of Fujian University of Technology;,2023,21(06):573-579.[doi:10.3969/j.issn.1672-4348.2023.06.010]
点击复制

基于VMD-SSA及误差补偿的风电功率超短期预测()
分享到：

《福建理工大学学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第21卷
期数:
2023年06期
页码:
573-579
栏目:
出版日期:
2023-12-25

文章信息/Info

Title:
Ultra-short-term prediction of wind powerbased on VMD-SSA and error compensation
作者:
朱希; 林俊德; 施翔宇; 林金阳
福建理工大学微电子技术研究中心
Author(s):
ZHU Xi;  LIN Junde;  SHI Xiangyu;  LIN Jinyang
Research Center for Microelectronics Technology, Fujian University of Technology
关键词:
风电功率短期预测; 变分模态分解; 奇异谱分析; 误差补偿
Keywords:
short-term prediction of wind power; variational mode decomposition; singular spectrum analysis; error compensation
分类号:
TM614
DOI:
10.3969/j.issn.1672-4348.2023.06.010
文献标志码:
A
摘要:
风电功率随机性强、规律性差等非线性特征导致风电功率难以被准确预测,为了解决这一问题,提出一种结合变分模态分解、奇异谱分析、长短期记忆网络和高斯过程回归的风电功率超短期预测方法。利用奇异谱分析算法优化变分模态分解后的模态分量,提取了数据中的趋势性,降低了风电数据的随机波动性。引入高斯过程回归算法,可对长短期记忆网络的预测结果进行误差补偿,进一步提高预测的精度。以西北某风电场的实测数据为例进行仿真分析,结果表明,该模型能提取风电序列的非线性特征,有效表征风电功率的时序性,增强了预测的效果,提高了预测的精度。
Abstract:
In order to solve the problem that wind power is difficult to be predicted accurately due to nonlinear characteristics such as high randomness and poor regularity of wind power, a method of ultra-short-term prediction of wind power combining variational modal decomposition (VMD), singular spectrum analysis (SSA), long and short-term memory network (LSTM) and Gaussian process regression (GPR) was proposed. The singular spectrum analysis algorithm was used to optimize the modal components after the variational modal decomposition, extract the trend in the data, and reduce the random volatility of wind power data. The Gaussian process regression algorithm was introduced to compensate the error of the prediction results of the long and short-term memory network to further improve the accuracy of the prediction. The measured data of a wind farm in Northwest China was taken as an example for simulation and analysis, and the results show that the model is able to extract the nonlinear features of wind power sequences, effectively characterize the temporal sequence of wind power, enhance the effect of prediction, and improve the accuracy of prediction.

参考文献/References:

［1］ 秦海岩. 加快发展新能源，支撑落实“双碳”目标［J］. 可持续发展经济导刊，2021（S2）：23-25.［2］ 孙荣富，张涛，和青，等. 风电功率预测关键技术及应用综述［J］. 高电压技术，2021，47（4）：1129-1143.［3］ 杨茂，张罗宾. 基于数据驱动的超短期风电功率预测综述［J］. 电力系统保护与控制，2019，47（13）：171-186.［4］ 韩自奋，景乾明，张彦凯，等. 风电预测方法与新趋势综述［J］. 电力系统保护与控制，2019，47（24）：178-187.［5］ HU Q H，ZHANG S G，XIE Z X，et al. Noise model based ν-support vector regression with its application to short-term wind speed forecasting［J］. Neural Networks，2014，57：1-11.［6］ 姜贵敏，陈志军，李笑竹，等. 基于EEMD-ACSLSSVM的短期风电功率预测［J］. 太阳能学报，2020，41（5）：77-84.［7］ KRISHNA RAYI V，MISHRA S P，NAIK J，et al. Adaptive VMD based optimized deep learning mixed kernel ELM autoencoder for single and multistep wind power forecasting［J］. Energy，2022，244：122585. ［8］ CHE J X, YE Y, WANG H P, et al. A sample entropy parsimonious model using decompositionensemble with SSA and CEEMDAN for shortterm wind speed prediction［J］. Engineering Letters,2023,31(1):34.［9］ 苗长新，王霞，李昊，等. 基于数值天气预报风速误差修正的风电功率日前预测［J］. 电网技术，2022，46（9）：3455-3464.［10］ HUANG Y S，YANG L，LIU S J，et al. Multi-step wind speed forecasting based on ensemble empirical mode decomposition，long short term memory network and error correction strategy［J］. Energies，2019，12（10）：1822.［11］ 盛四清，金航，刘长荣. 基于VMD-WSGRU的风电场发电功率中短期及短期预测［J］. 电网技术，2022，46（3）：897-904.［12］ 李青，张新燕，马天娇，等. 基于SSA-CNN-BiGRU-Attention的超短期风电功率预测模型［J］. 电机与控制应用，2023，50（5）：61-71.［13］ WANG S L，WU F，TAKYI-ANINAKWA P，et al. Improved singular filteringGaussian process regressionlong shortterm memory model for wholelifecycle remaining capacity estimation of lithium-ion batteries adaptive to fast aging and multi-current variations［J］. Energy，2023，284：128677.［14］ YANG H，GAO L P，LI G H. Underwater acoustic signal prediction based on correlation variational mode decomposition and error compensation［J］. IEEE Access，2020，8：103941-103955.

相似文献/References:

[1]刘丽桑,郭凯琪,陈健,等.基于VMD-MWOA-ELM的日前光伏功率预测[J].福建理工大学学报,2023,21(03):269.[doi:10.3969/j.issn.1672-4348.2023.03.011]
　LIU Lisang,GUO Kaiqi,CHEN Jian,et al.Prediction of day-ahead photovoltaic power generation based on VMD-MWOA-ELM[J].Journal of Fujian University of Technology;,2023,21(06):269.[doi:10.3969/j.issn.1672-4348.2023.03.011]
[2]董志文,苏晶晶.基于VMD-MTF-CNN的故障电弧检测方法[J].福建理工大学学报,2024,22(04):371.[doi:10.3969/j.issn.2097-3853.2024.04.010]
　DONG Zhiwen,SU Jingjing.Arc fault detection method based on VMD-MTF-CNN[J].Journal of Fujian University of Technology;,2024,22(06):371.[doi:10.3969/j.issn.2097-3853.2024.04.010]

更新日期/Last Update: 2023-12-25