基于EN-SKPCA降维和FPA优化LSTMNN期风电功率预测

张淑清; 杨振宁; 姜安琦; 李君; 刘海涛; 穆勇

doi:10.19912/j.0254-0096.tynxb.2020-1025

PDF(6207 KB)

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

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

作者信息 +

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

Author information +

文章历史 +

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。

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.

导出引用

张淑清, 杨振宁, 姜安琦, 李君, 刘海涛, 穆勇. 基于EN-SKPCA降维和FPA优化LSTMNN期风电功率预测[J]. 太阳能学报. 2022, 43(6): 204-211 https://doi.org/10.19912/j.0254-0096.tynxb.2020-1025

Zhang Shuqing, Yang Zhenning, Jiang Anqi, Li Jun, Liu Haitao, Mu Yong. SHORT TERM WIND POWER PREDICTION BASED ON EN-SKPCA DIMENSIONALITY REDUCTION AND FPA OPTIMIZING LSTMNN[J]. Acta Energiae Solaris Sinica. 2022, 43(6): 204-211 https://doi.org/10.19912/j.0254-0096.tynxb.2020-1025

中图分类号： TH17

参考文献

[1] HUA H, QIN Y, HAO C, et al.Optimal energy management strategies for energy Internet via deep reinforcement learning approach[J]. Applied energy, 2019, 239: 598-609.
[2] 孙泽贤, 孙鹤旭. 计及误差反馈的短期风电功率预测[J]. 太阳能学报, 2020, 41(8): 281-287.
SUN Z X, SUN H X.Short-term wind power forecast considering error feedback[J]. Acta energiae solaris sinica, 2020, 41(8): 281-287.
[3] 王金甲, 彭汝佳. 在线自适应LASSO罚向量自回归模型的风电功率预测[J]. 燕山大学学报, 2018, 42(6): 532-538,551.
WANG J J, PENG R J.An online adaptive LASSO penalty vector autoregressive model for wind power prediction[J]. Journal of Yanshan University, 2018, 42(6): 532-538, 551.
[4] QURESHI A S, KHAN A, ZAMEER A, et al.Wind power prediction using deep neural network based meta regression and transfer learning[J]. Applied soft computing, 2017, 58: 742-755.
[5] WAN X, ZHANG M, TAN Y.The determination of kernel function parameter initial value of the KPCA based on adaptive contribution rate[J]. IOP conference series earth and environmental science, 2017, 94(1): 012097.
[6] XIE L, TAO J, ZHANG Q, et al.CNN and KPCA-based automated feature extraction for real time driving pattern recognition[J]. IEEE access, 2019, 7: 123765-123775.
[7] 张淑清, 杨振宁, 张立国, 等. 基于弹性网降维及花授粉算法优化BP神经网络的短期电力负荷预测[J]. 仪器仪表学报, 2019, 40(7): 47-54.
ZHANG S Q, YANG Z N, ZHANG L G, et al.Short-term power load forecast based on dimension reduction by elastic network and flower pollination algorithm optimized BP neural network[J]. Chinese journal of scientific instrument, 2019, 40(7): 47-54.
[8] WANG D, TANAKA T.Sparse kernel principal component analysis based on elastic net regularization[C]// 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada, IEEE, 2016.
[9] 姜万录, 李振宝, 雷亚飞, 等. 基于深度学习的滚动轴承故障诊断与性能退化程度识别方法[J]. 燕山大学学报, 2020, 44(6): 526-536.
JIANG W L, LI Z B, LEI Y F, et al.Deep learning based rolling bearing fault diagnosis and performance degradation degree recognition method[J]. Journal of Yanshan University, 2020, 44(6): 526-536.
[10] KNOLL F, HAMMERNIK K, ZHANG C, et al.Deep-learning methods for parallel magnetic resonance imaging reconstruction: A survey of the current approaches, trends and issues[J]. IEEE signal processing magazine, 2020, 37(1): 128-140.
[11] FAN C, WANG J, GANG W, et al.Assessment of deep recurrent neural network-based strategies for short-term building energy predictions[J]. Applied energy, 2019, 236: 700-710.
[12] 刘云鹏, 许自强, 董王英, 等. 基于经验模态分解和长短期记忆神经网络的变压器油中溶解气体浓度预测方法[J]. 中国电机工程学报, 2019, 39(13): 3998-4007.
LIU Y P, XU Z Q, DONG W Y, et al, Concentration prediction of dissolved gases in transformer oil based on empirical mode decomposition and long short-term memory neural networks[J]. Proceedings of the CSEE, 2019, 39(13): 3998-4007.
[13] 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017(12): 3797-3802.
ZHU Q M, LI H Y, WANG Z Q, et al.Short-term wind power forecasting based on LSTM[J]. Power system technology, 2017(12): 3797-3802.
[14] 李万, 冯芬玲, 蒋琦玮. 改进粒子群算法优化LSTM神经网络的铁路客运量预测[J]. 铁道科学与工程学报, 2018, 15(12): 260-266.
LI W, FENG F L, JIANG Q W.Prediction for railway passenger volume based on modified PSO optimized LSTM neural network[J]. Journal of railway science and engineering, 2018, 15(12): 260-266.
[15] ABDEL-BASSET M, SHAWKYL A.Flower pollination algorithm: A comprehensive review[J]. Artificial intelligence review, 2019, 50(4): 2533-2557.
[16] LIANG X B, LIANG W, XIONG J Y.Intelligent diagnosis of natural gas pipeline defects using improved flower pollination algorithm and artificial neural network[J]. Journal of cleaner production, 2020, 264: 121655.