基于生成对抗网络多变量风电时间序列异常值处理

doi:10.19912/j.0254-0096.tynxb.2021-0685

太阳能学报 ›› 2022, Vol. 43 ›› Issue (12): 300-311.DOI: 10.19912/j.0254-0096.tynxb.2021-0685

基于生成对抗网络多变量风电时间序列异常值处理

徐昊^1,2, 王永生^1~3, 许志伟^1,2,4, 武煜昊^1,2, 陈振^1,2

1.内蒙古工业大学数据科学与应用学院,呼和浩特 010080;
2.内蒙古自治区基于大数据的软件服务工程技术研究中心,呼和浩特 010080;
3.内蒙古农业大学计算机与信息工程学院,呼和浩特 010080;
4.中国科学院计算机技术研究所,北京 100190

收稿日期:2021-06-18 出版日期:2022-12-28 发布日期:2023-06-28
通讯作者: 王永生（1976—）,男,博士、副教授,主要从事大数据分析云计算、新能源应用方面研究。wangys@imut.edu.cn
基金资助:
国家自然科学基金（61962045）; 内蒙古自治区高等学校科学研究项目（NJZY21321）; 内蒙古自治区关键技术攻关计划（2020GG0094）; 内蒙古自治区自然科学基金（2021LHMS06001）

OUTLIER PROCESSING OF MULTIVARIABLE WIND POWER TIME SERIES BASED ON GENERATIVE ADVERSARIAL NETWORK

Xu Hao^1,2, Wang Yongsheng^1-3, Xu Zhiwei^1,2,4, Wu Yuhao^1,2, Chen Zhen^1,2

1. College of Data Science and Application, Inner Mongolia University of Technology, Hohhot 010080, China;
2. Inner Mongolia Autonomous Region Engineering & Technology Research Center of Big Data Based Software Service, Hohhot 010080, China;
3. College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot 010080, China;
4. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China

Received:2021-06-18 Online:2022-12-28 Published:2023-06-28

摘要/Abstract

摘要： 将孤立森林算法应用于风电数据的异常值检测,利用改进的GRUI神经单元基于WGAN网络进行缺失值插补。在内蒙古风电场的真实数据集上验证了所提方法的有效性,并与KNN、GAN等方法进行对比,验证了模型的有效性,具有更好的插补精度。

关键词: 风力发电, 时间序列, 对抗生成网络, 异常检测, 缺失插补

Abstract: The rapid development and original data lack of wind power generation have brought difficulties and challenges to wind power prediction. Accurate and complete original data is the basis of wind power research. The isolated forest algorithm is applied to the outlier detection of wind power data. The improved GRUI neural unit is used to perform missing value interpolation based on the WGAN network. The effectiveness of the proposed method is verified on the real data set from the Inner Mongolia wind farm and compared with KNN, GAN and other methods. As the results, the model has better interpolation accuracy.

Key words: wind power, time series, generative adversarial network, outlier detection, missing interpolation

中图分类号:

TP391.1

徐昊, 王永生, 许志伟, 武煜昊, 陈振. 基于生成对抗网络多变量风电时间序列异常值处理[J]. 太阳能学报, 2022, 43(12): 300-311.

Xu Hao, Wang Yongsheng, Xu Zhiwei, Wu Yuhao, Chen Zhen. OUTLIER PROCESSING OF MULTIVARIABLE WIND POWER TIME SERIES BASED ON GENERATIVE ADVERSARIAL NETWORK[J]. Acta Energiae Solaris Sinica, 2022, 43(12): 300-311.

参考文献

[1] RAHBAR K, CHAI C C, ZHANG R.Energy cooperation optimization in microgrids with renewable energy integration[J]. IEEE transactions on smart grid, 2016, 9(2): 1482-1493.
[2] BLOESS A, SCHILL W P, ZERRAHN A.Power-to-heat for renewable energy integration: a review of technologies, modeling approaches, and flexibility potentials[J]. Applied energy, 2018, 212: 1611-1626.
[3] 刘怡彤. 考虑新能源不确定性的全清洁能源区域电网的主从博弈研究[D]. 西安: 西安理工大学, 2019.
LIU Y T.Master-slave game study of clean energy regional power grid considering the uncertainty of new energy sources[D]. Xi’an: Xi’an University of Technology, 2019.
[4] 马彦宏, 汪宁渤, 何世恩, 等. 酒泉千万千瓦级风电基地发展现状与展望[J]. 电网与清洁能源, 2009, 25(11): 76-79.
MA Y H, WANG N B, HE S E, et al.The current situation and prospect for Jiuquan 10 GW wind power base[J]. Power system and clean energy, 2009, 25(11): 76-79.
[5] 田英杰, 苏运, 郭乃网, 等 . 基于时间序列嵌入的电力负荷预测方法[J]. 计算机应用与软件, 2018, 35(11): 55-60, 73.
TIAN Y J, SU Y, GUO N W, et al.Electricity load forecasting method based on time series embedding[J]. Computer applications and software, 2018, 35(11): 55-60, 73.
[6] 赵永宁, 叶林, 朱倩雯. 风电场弃风异常数据簇的特征及处理方法[J]. 电力系统自动化, 2014, 38(21): 39-46.
ZHAO Y N, LIN Y, ZHU Q W.Characteristics and processing method of abnormal data clusters caused by wind curtailments in wind farms[J]. Automation of electric power systems, 2014, 38(21): 39-46.
[7] 陈伟, 吴布托, 裴喜平. 风电机组异常数据预处理的分类多模型算法[J].电力系统及其自动化学报, 2018, 30(4): 137-143.
CHEN W, WU B T, PEI X P.Classification multi-model algorithm for abnormal data preprocessing in wind turbines[J]. Proceedings of the CSU-EPSA, 2018, 30(4): 137-143.
[8] 沈小军, 付雪姣, 周冲成, 等. 风电机组风速-功率异常运行数据特征及清洗方法[J]. 电工技术学报, 2018, 33(14): 3353-3361.
SHEN X J, FU X J, ZHOU C C, et al.Characteristics of outliers in wind speed-power operation data of wind turbines and its cleaning method[J]. Transactions of China Electrotechnical Society, 2018, 33(14): 3353-3361.
[9] 金文进, 杨武. 异常检测技术研究综述[J]. 软件导刊, 2008(1): 10-13.
JIN W J, YANG W.A summary of anomaly detection for IDS[J]. Software guide, 2008(1): 10-13.
[10] KIRAN B R, THOMAS D M, PARAKKAL R.An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos[J]. Journal of imaging, 2018, 4(2): 36.
[11] SHARMA R, GULERIA A, SINGLA R K.An overview of flow-based anomaly detection[J]. International journal of communication networks and distributed systems, 2018, 21(2): 220-240.
[12] 沈小军, 周冲成, 吕洪. 基于运行数据的风电机组间风速相关性统计分析[J]. 电工技术学报, 2017, 32(16): 265-274.
SHEN X J, ZHOU C C, LYU H.Statistical analysis of wind speed correlation between wind turbines based on operating data[J]. Transactions of China Electrotechnical Society, 2017, 32(16): 265-274.
[13] KUSIAK A, ZHENG H Y, SONG Z.Models for monitoring wind farm power[J]. Renewable energy, 2009, 34(3): 583-590.
[14] LIU F T, TING K M, ZHOU Z H.Isolation forest[C]//Eighth IEEE International Conference on Data Mining, Pisa, Italy, 2008: 413-422.
[15] LIU F T, TING K M, ZHOU Z H.Isolation-based anomaly detection[J]. ACM transactions on knowledge discovery from data, 2012, 6(1): 1-39.
[16] QIN Y, LOU Y S.Hydrological time series anomaly pattern detection based on isolation forest[C]//IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference(ITNEC), Chengdu, China, IEEE, 2019: 1706-1710.
[17] LITTLE R J A, RUBIN D B. Statistical analysis with missing data[M]. New York: John Wiley & Sons, 2019.
[18] BATISTA G E, MONARD M C.An analysis of four missing data treatment methods for supervised learning[J]. Applied artificial intelligence, 2003, 17(5-6): 519-533.
[19] HASTIE T, MAZUMDER R, LEE J D, et al.Matrix completion and low-rank SVD via fast alternating least squares[J]. Journal of machine learning research, 2015, 16(1): 3367-3402.
[20] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al.Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[21] HUANG X, LI Y, POURSAEED O, et al.Stacked generative adversarial networks[C]//Computer Vision and Pattern Recognition(CVPR) Conference, Honolulu, Hawaii, USA, 2017.
[22] LEDIG C, THEIS L, HUSZAR F, et al.Photo-realistic single image super-resolution using a generative adversarial network[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Honolulu, HI, USA, 2017: 4681-4690.
[23] YU L T, ZHANG W N, WANG J, et al.Seqgan: sequence generative adversarial nets with policy gradient[C]//Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, California, USA, 2017.
[24] YOON J, JORDON J, SCHAAR M.Gain: missing data imputation using generative adversarial nets[C]//Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, 2018: 5689-5698.
[25] 朱倩雯, 叶林, 赵永宁, 等. 风电场输出功率异常数据识别与重构方法研究[J]. 电力系统保护与控制, 2015, 43(3): 38-45.
ZHU Q W, YE L, ZHAO Y N, et al.Methods for elimination and reconstruction of abnormal power data in wind farms[J]. Power system protection and control, 2015, 43(3): 38-45.
[26] AMMAD M, RAMLI A.Cubic B-Spline curve interpolation with arbitrary derivatives on its data points[C]//2019 23rd International Conference in Information Visualization—Part II, Adelaide, SA, Australia, 2019: 156-159.
[27] WANG J D, YANG F, DU X H.Microgrid harmonic and interharmonic analysis algorithm based on cubic spline interpolation signal reconstruction[C]//IEEE PES Innovative Smart Grid Technologies-Asia, Tianjin, 2012: 1-5.
[28] 杨茂, 翟冠强, 李大勇. 基于风速升降特性及支持向量机理论的异常数据重构算法[J]. 电力系统保护与控制, 2018, 46(16): 31-37.
YANG M, ZHAI G Q, LI D Y.An algorithm of abnormal data reconstruction based on RISE-FALL-feature of the wind speed and support vector machine[J]. Power system protection and control, 2018, 46(16): 31-37.
[29] LUO Y H, CAI X R, ZHANG Y, et al.Multivariate time series imputation with generative adversarial networks[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems, NeurIPS, Montréal, Canada, 2018: 1603-1614.
[30] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[31] CHO K, VAN MERRIËNBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP), Doha, Qatar, 2014: 1724-1734.
[32] LEE D Y, HORVITZ E.Predicting mortality of intensive care patients via learning about hazard[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, California, USA, 2017: 4953-4954.
[33] ARJOVSKY M, CHINTALA S, BOTTOU L.Wasserstein generative adversarial networks[C]//Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, 2017, 70: 214-223.
[34] SCHLEGL T, SEEBOCK P, WALDSTEIN S M, et al.Unsupervised anomaly detection with generative adversarial networks to guide marker discovery[C]//International Conference on Information Processing in Medical Imaging, Boone, NC, USA, Springer, 2017.

基于生成对抗网络多变量风电时间序列异常值处理

OUTLIER PROCESSING OF MULTIVARIABLE WIND POWER TIME SERIES BASED ON GENERATIVE ADVERSARIAL NETWORK

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王海旗, 晋涛, 刘星廷, 王欣伟, 郭瑞宙, 程胤璋. 基于转子动能控制的风电机组功率平滑控制结构及优化策略研究[J]. 太阳能学报, 2022, 43(9): 251-257.
[2]	李英量, 王康, 高兆迪, 王德明, 宋楠, 朱琦. 考虑风电接入的电压控制区域修正方法研究[J]. 太阳能学报, 2022, 43(9): 258-266.
[3]	张家安, 刘东, 刘辉, 宋鹏, 刘京波, 吴宇辉. 基于风速波动特征提取的超短期风速预测[J]. 太阳能学报, 2022, 43(9): 308-313.
[4]	周满国, 黄艳国, 段锦锋. 基于GRU-RF模型的太阳辐照度短时预测[J]. 太阳能学报, 2022, 43(7): 166-173.
[5]	刘明洋, 潘文霞, 李程昊, 高泽, 崔惟, 刘铜锤. 考虑撬棒和直流卸荷保护的双馈电机电磁暂态过程分析[J]. 太阳能学报, 2022, 43(7): 249-256.
[6]	韩平平, 孙浩然, 童青洋, 张炎, 陈忠, 杨为. 基于定关断面积的分层接入UHVDC系统换流器协调控制策略[J]. 太阳能学报, 2022, 43(7): 316-325.
[7]	杨明岱, 王宪, 赵前程, 胡芳, 阳雪兵. 永磁同步风电机组发电机定子温度建模方法[J]. 太阳能学报, 2022, 43(5): 319-326.
[8]	黄中华, 刘喆, 谢雅. 超大功率风力发电机组塔筒屈曲分析[J]. 太阳能学报, 2022, 43(4): 304-310.
[9]	邢法财, 徐政. 双馈感应风力发电机的负电阻效应研究[J]. 太阳能学报, 2022, 43(4): 324-332.
[10]	顾永强, 冯锦飞, 张哲玮, 田志昌, 宫云龙. 基于模态参数的在役风力发电机叶片损伤识别研究[J]. 太阳能学报, 2022, 43(3): 350-355.
[11]	罗园庆, 陈长征, 赵思雨. 基于增强形态滤波与三阶累积量对角切片谱的风力发电机滚动轴承故障诊断方法[J]. 太阳能学报, 2022, 43(3): 373-381.
[12]	杨旭, 李岚, 杨琦, 赵楠, 侯传羽. 电压不平衡下无权重系数FCS-MPC的DFIG控制[J]. 太阳能学报, 2022, 43(2): 389-393.
[13]	刘兆, 周慧珠. 风力发电机组塔架螺栓连接公差问题研究[J]. 太阳能学报, 2022, 43(2): 408-414.
[14]	姜明洋, 徐丽, 张开军, 马远兴. 基于季节指数调整的循环神经网络风速时间序列预测[J]. 太阳能学报, 2022, 43(2): 444-450.
[15]	刘微容, 杨帆, 刘婕, 米彦春, 宋昊文, 郭宏林. 基于双重速率QDMC的液压型风力发电机组变量马达转速控制[J]. 太阳能学报, 2022, 43(2): 471-478.