[1]刘旭丽,莫毓昌,吴哲,等.超短期风电功率预测的混合深度学习模型[J].华侨大学学报(自然科学版),2022,43(5):668-676.[doi:10.11830/ISSN.1000-5013.202108028]
　LIU Xuli,MO Yuchang,WU Zhe,et al.Hybrid Deep Learning Model Based on Super-Short-Term Wind Power Forecasting[J].Journal of Huaqiao University(Natural Science),2022,43(5):668-676.[doi:10.11830/ISSN.1000-5013.202108028]
点击复制

超短期风电功率预测的混合深度学习模型()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第43卷
期数:
2022年第5期
页码:
668-676
栏目:
出版日期:
2022-09-13

文章信息/Info

Title:
Hybrid Deep Learning Model Based on Super-Short-Term Wind Power Forecasting
文章编号:
1000-5013(2022)05-0668-09
作者:
刘旭丽1;  莫毓昌1;  吴哲1;  严珂2
1. 华侨大学 计算科学福建省高校重点实验室, 福建 泉州 362021;2.中国计量大学 信息工程学院, 浙江 杭州 310018
Author(s):
LIU Xuli1;  MO Yuchang1;  WU Zhe1;  YAN Ke2
1. Fujian Provincial Key Laboratory of Computational Science, Huaqiao University, Quanzhou 362021, China; 2. College of Information Engineering, China Jiliang University, Hangzhou 310018, China
关键词:
风力发电;  超短期预测;  离散小波变换;  时间卷积网络;  长短期记忆神经网络
Keywords:
wind power generation;  super-short-term prediction;  discrete wavelet transform;  time convolutional network;  long and short-term memory neural network
分类号:
O24
DOI:
10.11830/ISSN.1000-5013.202108028
文献标志码:
A
摘要:
针对风电功率预测(WPF)问题,提出一种基于离散小波变换(DWT)、时间卷积网络(TCN)和长短期记忆(LSTM)神经网络的混合深度学习模型(DWT-TCN-LSTM),对超短期风电功率进行预测.将DWT-TCN-LSTM模型分别与差分整合移动平均自回归(ARIMA)模型,支持向量回归(SVR)模型,长短期记忆神经网络模型和卷积长短期记忆(TCN-LSTM)混合模型进行对比实验,通过对称平均绝对百分比误差(SMAPE),均方根误差(RMSE)和平均绝对误差(MAE)3种评价指标值对各个模型进行评价.实验结果表明:DWT-TCN-LSTM模型具有较好的预测性能.
Abstract:
Aiming at the problem of wind power forecasting(WPF), a hybrid deep learning model(DWT-TCN-LSTM)based on discrete wavelet transform(DWT), time convolutional network(TCN)and long and short-term memory(LSTM)neural network is proposed to predict the super-short-term wind power. The DWT-TCN-LSTM model is compared experimentally with the differential integrated moving average autoregressive model(ARIMA), support vector regression(SVR)model, long and short-term memory neural network model and convolutional long and short-term memory(TCN-LSTM)mixed model. The each model is evaluated through three evaluation metrics of symmetric mean absolute percent error(SMAPE), root mean square error(RMSE)and mean absolute error(MAE). The experimental results show that: the DWT-TCN-LSTM model has better prediction performance.

参考文献/References:

[1] WU Yuankang,CHANG S M,MANDAL P.Grid-connected wind power plants: A survey on the integration requirements in modern grid codes[C]//IEEE/IAS 55th Industrial and Commercial Power Systems Technical Conference.Calgary:IEEE Press,2019:1-9.DOI:10.1109/ICPS.2019.8733382.
[2] LU Xiaoxing,LI Kangping,XU Hanchen,et al.Fundamentals and business model for resource aggregator of demand response in electricity markets[J].Energy,2020,204:117885.DOI:10.1016/j.energy.2020.117885.
[3] WANG Fei,XIANG Biao,LI Kangping,et al.Smart households’ aggregated capacity forecasting for load aggregators under incentive-based demand response programs[J].IEEE Transactions on Industry Applications,2020,56(2):1086-1097.DOI:10.1109/TIA.2020.2966426.
[4] WANG Fei,LI Kangping,DUIC N,et al.Association rule mining based quantitative analysis approach of household characteristics impacts on residential electricity consumption patterns[J].Energy Conversion and Management,2018,171:839-854.DOI:10.1016/j.enconman.2018.06.017.
[5] WEN Yuxin,ALHAKEEM D,MANDAL P,et al.Performance evaluation of probabilistic methods based on bootstrap and quantile regression to quantify PV power point forecast uncertainty[J].IEEE Transactions on Neural Networks and Learning Systems,2020,31(4):1134-1144.DOI:10.1109/TNNLS.2019.2918795.
[6] WU Yuankang,SU Poen,WU Tingyi,et al. Probabilistic wind power forecasting using weather ensemble models[C]//IEEE/IAS 54th Industrial and Commercial Power Systems Technical Conference.Niagara Falls:IEEE Press,2018:1-8.DOI:10.1109/ICPS.2018.8369963.
[7] WU Yuankang,HONG Jingshan,SU Poen.Stratification-based wind power forecasting in a high penetration wind power system using a hybrid model with charged system search algorithm[C]//IEEE Industry Applications Society Annual Meeting.Addison:IEEE Press,2015:1-9.DOI:10.1109/IAS.2015.7356793.
[8] LIU Meng,QUILUMBA F L,LEE W J.Dispatch scheduling for a wind farm with hybrid energy storage based on wind and LMP forecasting[J].IEEE Transactions on Industry Applications,2015,51(3):1970-1977.DOI:10.1109/TIA.2014.2372043.
[9] SHI Jie,DING Zhaohao,LEE W J,et al.Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features[J].IEEE Transactions on Smart Grid,2014,5(1):521-526.DOI:10.1109/TSG.2013.2283269.
[10] WANG Fei,XUAN Zhiming,ZHEN Zhao,et al.A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework[J].Energy Conversion and Management,2020,212:112766.DOI:10.1016/j.enconman.2020.112766.
[11] WANG Fei,XUAN Zhiming,ZHEN Zhao,et al.A minutely solar irradiance forecasting method based on real-time sky image-irradiance mapping model[J].Energy Conversion and Management,2020,220:113075.DOI:10.1016/j.enconman.2020.113075.
[12] ZHEN Zhao,LIU Jiaming,ZHANG Zhanyao,et al.Deep learning based surface irradiance mapping model for solar PV power forecasting using sky image[J].IEEE Transactions on Industry Applications,2020,56(4):3385-3396.DOI:10.1109/TIA.2020.2984617.
[13] COSTA A,CRESPO A,NAVARRO J,et al.A review on the young history of the wind power short-term prediction[J].Renewable and Sustainable Energy Reviews,2008,12(6):1725-1744.DOI:10.1016/j.rser.2007.01.015.
[14] ALENCAR D B,AFFONSO C,OLIVEIRA R C L,et al.Different models for forecasting wind power generation: Case study[J].Energies,2017,10(12):1976.DOI:10.3390/en10121976.
[15] FOLEY A M,LEAHY P G,MCKEOGH E J.Wind power forecasting & prediction methods[C]//9th International Conference on Environment and Electrical Engineering.Prague:IEEE Press,2010:61-64.DOI:10.1109/EEEIC.2010.5490016.
[16] CHANG G W, LU H J, HSU L Y,et al.A hybrid model for forecasting wind speed and wind power generation[C]//IEEE Power and Energy Society General Meeting.Boston:IEEE Press,2016:1-5.DOI:10.1109/PESGM.2016.7742039.
[17] YU Ruiguo,GAO Jie,YU Mei,et al.LSTM-EFG for wind power forecasting based on sequential correlation features[J].Future Generation Computer Systems,2019,93:33-42.DOI:10.1016/j.future.2018.09.054.
[18] CAO Yukun,GUI Liai.Multi-step wind power forecasting model using LSTM networks, similar time series and LightGBM[C]//5th International Conference on Systems and Informatics.Nanjing:IEEE Press,2018:192-197.DOI:10.1109/icsai.2018.8599498.
[19] LIU Yao,GUAN Lin,HOU Chen,et al.Wind power short-term prediction based on LSTM and discrete wavelet transform[J].Applied Sciences,2019,9(6):1108.DOI:10.3390/app9061108.
[20] LEA C,VIDAL R,REITER A,et al.Temporal convolutional networks: A unified approach to action segmentation[C]//European Conference on Computer Vision 2016 Workshops.Amsterdam:Springer,2016:47-54.DOI:10.1007/978-3-319-49409-8_7.

备注/Memo

备注/Memo:
收稿日期: 2021-08-27
通信作者: 莫毓昌(1980-),男,教授,博士,主要从事数据科学的研究.E-mail:yuchangmo@sina.com.
基金项目: 国家自然科学基金资助项目(61972165); 福建省科技重大专项资助项目(2020HZ02014); 数据科学福建省高校科技创新团队项目(MJK-2018-49); 大数据分析与安全泉州市高层次人才团队项目(2017ZT012)
更新日期/Last Update: 2022-09-20