欢迎访问《太阳能学报》官方网站,今天是 分享到:
ISSN 0254-0096 CN 11-2082/K

太阳能学报 ›› 2022, Vol. 43 ›› Issue (6): 204-211.DOI: 10.19912/j.0254-0096.tynxb.2020-1025

• • 上一篇    下一篇

基于EN-SKPCA降维和FPA优化LSTMNN期风电功率预测

张淑清1, 杨振宁1, 姜安琦1, 李君1, 刘海涛1, 穆勇2   

  1. 1.燕山大学电气工程学院,秦皇岛 066004;
    2.国网冀北电力有限公司 唐山供电公司,唐山 063000
  • 收稿日期:2020-09-24 出版日期:2022-06-28 发布日期:2022-12-28
  • 通讯作者: 杨振宁(1996—),男,硕士研究生,主要从事大数据处理、时序预测方面的研究。1015357236@qq.com
  • 基金资助:
    国家重点研发计划(2021YFB3201600); 河北省自然科学基金(F2020203058); 国家自然科学基金(51875498)

SHORT TERM WIND POWER PREDICTION BASED ON EN-SKPCA DIMENSIONALITY REDUCTION AND FPA OPTIMIZING LSTMNN

Zhang Shuqing1, Yang Zhenning1, Jiang Anqi1, Li Jun1, Liu Haitao1, Mu Yong2   

  1. 1. Institute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China;
    2. Tangshan Power Supply Company of North Hebei Electric Power Co., Ltd., Tanshan 063000, China
  • Received:2020-09-24 Online:2022-06-28 Published:2022-12-28

摘要: 综合考虑风电功率序列及气象数据的多维特征,提出一种弹性网稀疏核主成分分析(EN-SKPCA)降维方法,对气象因素降维并表述为回归优化型问题,添加的弹性网惩罚解决了KPCA重构主成分难以解释构成的问题;提出花授粉算法(FPA)优化长短时记忆神经网络(LSTMNN)预测模型,可自动筛选出最佳超参数,降低了参数经验设置所带来的随机性。该方法解决了突变天气的影响,提高了预测精度。对2017年宁夏麻黄山第一风电场实测数据实验,证明了该方法的优越性。

关键词: 风电, 功率预测, 气象, 降维, 弹性网稀疏核主成分分析, 花授粉算法优化, 长短时记忆神经网络

Abstract: Comprehensively considering the characteristics of wind power series and the multi-dimensional meteorological data, a dimensionality reduction method of elastic net improved kernel principal component analysis (EN-SKPCA) is proposed. The dimensionality of meteorological factors is reduced and expressed as a regression optimization problem. The added elastic network penalty solve the problem that the KPCA reconstruction principal component is difficult to explain. The flower pollination algorithm (FPA) is proposed to optimize the long-short-term memory neural network (LSTMNN) prediction. The model can automatically select the best super parameters and reduce the randomness caused by the empirical setting of parameters. The method solves the influence of abrupt weather and improves the prediction accuracy. The superiority of this method is proved by the experiment on the measured data of Mahuangshan No.1 wind farm in Ningxia in 2017.

Key words: wind power, power predication, meteorology, dimensionality reduction, elastic net sparse kernel principal component analysis, flower pollination algorithm optimizing, long short-term memory neural network

中图分类号: