风电输出功率预测技术研究综述

doi:10.3778/j.issn.1673-9418.2205028

计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (12): 2653-2677.DOI: 10.3778/j.issn.1673-9418.2205028

风电输出功率预测技术研究综述

武煜昊¹^,², 王永生¹^,²^,⁺(), 徐昊¹^,², 陈振¹^,², 张哲¹^,², 关世杰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

收稿日期:2022-05-07 修回日期:2022-08-08 出版日期:2022-12-01 发布日期:2022-08-12
通讯作者: +E-mail: wangys@imut.edu.cn
作者简介:武煜昊（1999—），男，河北邢台人，硕士研究生，主要研究方向为云计算与大数据分析等。
王永生（1976—），男，内蒙古呼和浩特人，博士，副教授，高级工程师，硕士生导师，主要研究方向为云计算与大数据分析、新能源应用等。
徐昊（1998—），男，江苏南京人，硕士研究生，主要研究方向为云计算与大数据分析等。
陈振（1994—），男，河南商丘人，硕士研究生，主要研究方向为云计算与大数据分析等。
张哲（1998—），男，河南郑州人，硕士研究生，主要研究方向为云计算与大数据分析等。
关世杰（1999—），男，河北张家口人，硕士研究生，主要研究方向为云计算与大数据分析等。
基金资助:
内蒙古自治区自然科学基金(2021LHMS06001);内蒙古自治区高等学校科学研究项目(NJZY21321);内蒙古自治区科技重大专项项目(2020GG0094)

Survey of Wind Power Output Power Forecasting Technology

WU Yuhao¹^,², WANG Yongsheng¹^,²^,⁺(), XU Hao¹^,², CHEN Zhen¹^,², ZHANG Zhe¹^,², GUAN Shijie¹^,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

Received:2022-05-07 Revised:2022-08-08 Online:2022-12-01 Published:2022-08-12
About author:WU Yuhao, born in 1999, M.S. candidate. His research interests include cloud computing and big data analysis, etc.
WANG Yongsheng, born in 1976, Ph.D., associate professor, senior engineer, M.S. supervisor. His research interests include cloud computing and big data analysis, new energy application, etc.
XU Hao, born in 1998, M.S. candidate. His research interests include cloud computing and big data analysis, etc.
CHEN Zhen, born in 1994, M.S. candidate. His research interests include cloud computing and big data analysis, etc.
ZHANG Zhe, born in 1998, M.S. candidate. His research interests include cloud computing and big data analysis, etc.
GUAN Shijie, born in 1999, M.S. candidate. His research interests include cloud computing and big data analysis, etc.
Supported by:
Natural Science Foundation of Inner Mongolia Autonomous Region(2021LHMS06001);Research Program of Science and Technology at Universities of Inner Mongolia Autonomous Region(NJZY21321);Key Technologies Research and Development Program of Inner Mongolia Autonomous Region(2020GG0094)

摘要/Abstract

摘要：

风电具有的波动性、间歇性等特点对并网造成一定程度的影响，提前进行风电功率预测是解决上述问题的一个重要途径。但传感器传输、网络通信等不可控因素的存在，导致采集到用于风电功率预测的数据存在异常值和缺失值，因此在进行风电功率预测前应当进行相应的异常值检测和缺失值插补操作。为进一步促进风电数据清洗及预测技术的发展，对当前现有模型及方法进行分析与总结，并对现有技术进行划分、对比。从时序数据出发，首先，对风电预测领域的异常值检测方法的研究现状进行分类、分析与总结，对现有异常检测方法所存不足与缺陷进行概述，并对未来发展中或将成为重点的研究方向进行展望；其次，将现有的缺失值处理方法的评价指标进行描述，根据处理方式的不同将处理技术按照常规处理方法、辨别式的插补方法、生成式的插补方法及物理特性方法进行分析与总结，并对现有研究中所存问题进行分析；最后，对现有研究中的预测方法、多层级预测及自适应预测系统的研究现状进行分析总结，并对现有预测存在的挑战及未来发展方向进行了总结与展望。

关键词: 深度学习, 风电功率预测, 异常值检测, 缺失值插补, 时间序列数据

Abstract:

Uncertainty and volatility of wind power generation, bring some serious challenges for the grid-connected wind power system. Prediction of wind power in advance is an important way to solve the above problems. Due to the existence of uncontrollable factors such as sensor transmission and network communication, the data collected for wind power prediction have abnormal values and missing values. Therefore, corresponding outlier detection and missing value interpolation operations should be performed before wind power prediction. To further promote the development of wind power data cleaning and prediction technology, current existing models and methods are analyzed and summarized, and the existing technologies are divided and compared. Starting from time series data, this paper first classifies, analyzes and summarizes the research status of outlier detection methods in the field of wind power prediction, summarizes the deficiencies and defects of existing anomaly detection methods, and prospects the research directions that may become the focus in the future development. Secondly, the evaluation indices of the existing missing value treatment methods are described. According to the different treatment methods, the processing techniques are analyzed and summarized according to the conventional treatment methods, discriminative interpolation methods, generative interpolation methods and physical characteristics methods, and the existing problems in the existing research are analyzed. Finally, the current research status of forecasting methods, multi-level forecasting and adaptive forecasting systems in existing research are analyzed and summarized, and the existing challenges and future development directions of existing forecasting are summarized and prospected.

Key words: deep learning, wind power forecasting, outlier detection, missing value imputation, time series data

中图分类号:

TP391

武煜昊, 王永生, 徐昊, 陈振, 张哲, 关世杰. 风电输出功率预测技术研究综述[J]. 计算机科学与探索, 2022, 16(12): 2653-2677.

WU Yuhao, WANG Yongsheng, XU Hao, CHEN Zhen, ZHANG Zhe, GUAN Shijie. Survey of Wind Power Output Power Forecasting Technology[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(12): 2653-2677.

图/表 13

参考文献 182

[1]	World Wind Energy Association. World market for wind power saw another record year in 2021: 97, 3 Gigawatt of new capacity added[EB/OL]. [2022-03-18]. https://wwindea.org/world-market-for-wind-power-saw-another-record-year-in-2021-973-gigawatt-of-new-capacity-added/.
[2]	WU Z, LUO G, YANG Z L, et al. A comprehensive review on deep learning approaches in wind forecasting applications[J]. CAAI Transactions on Intelligence Technology, 2022, 7(2): 129-143. DOI URL
[3]	吴布托. 风电机组运行数据中异常值的检测方法[D]. 兰州: 兰州理工大学, 2017.
	WU B T. Detection method of abnormal value in operating data of wind turbine[D]. Lanzhou: Lanzhou University of Technology, 2017.
[4]	AFANASYEV D O, FEDOROVA E A. On the impact of outlier filtering on the electricity price forecasting accuracy[J]. Applied Energy, 2019, 236: 196-210. DOI URL
[5]	CHANDOLA V, BANERJEE A, KUMAR V. Anomaly detection: a survey[J]. ACM Computing Surveys, 2009, 41(3): 1-58.
[6]	封焯文, 朱世平, 赵志华, 等. 风功率异常数据检测方法对比研究[J]. 电工电能新技术, 2021, 40(7): 55-61.
	FENG Z W, ZHU S P, ZHAO Z H, et al. Comparative study on detection methods of wind power abnormal data[J]. Advanced Technology of Electrical Engineering and Energy, 2021, 40(7): 55-61.
[7]	LIN W Y, CHEN M C, LIAO S K. Wall cladding anomaly detection by supervised machine learning on drone thermograph[C]// Proceedings of the 2019 International Workshop on Future Technology, 2019: 21-22.
[8]	DENKENA B, DITTRICH M A, NOSKE H, et al. Statistical approaches for semi-supervised anomaly detection in machining[J]. Production Engineering, 2020, 14: 385-393. DOI URL
[9]	CHEUNG C, VALDÉS J J, CHAVEZ R S, et al. Failure modeling of a propulsion subsystem: unsupervised and semi- supervised approaches to anomaly detection[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2019, 33(11): 1940019. DOI URL
[10]	柳青秀, 马红占, 褚学宁, 等. 基于长短时记忆-自编码神经网络的风电机组性能评估及异常检测[J]. 计算机集成制造系统, 2019, 25(12): 3209-3219. DOI
	LIU Q X, MA H Z, CHU X N, et al. Performance assessment and anomaly detection of wind turbine based on long short time memory-auto encoder neural network[J]. Computer Integrated Manufacturing Systems, 2019, 25(12): 3209-3219.
[11]	杭梦鑫, 陈伟, 张仁杰. 基于改进的一维卷积神经网络的异常流量检测[J]. 计算机应用, 2021, 41(2): 433-440. DOI
	HANG M X, CHEN W, ZHANG R J. Abnormal flow detection based on improved one-dimensional convolutional neural network[J]. Journal of Computer Applications, 2021, 41(2): 433-440. DOI
[12]	霍文君, 王伟, 李文. AnomalyDetect: 一种基于欧式距离的在线异常检测算法[J]. 中国科学技术大学学报, 2019, 49(7): 555-563.
	HUO W J, WANG W, LI W. AnomalyDetect: an online distance-based anomaly detection algorithm[J]. Journal of University of Science and Technology of China, 2019, 49(7): 555-563.
[13]	GOLDSTEIN M, DENGEL A. Histogram-based outlier score (HBOS): a fast unsupervised anomaly detection algorithm[C]// Proceedings of the Poster and Demo Track of the 35th German Conference on Artificial Intelligence, 2012: 59-63.
[14]	彭虎. 风电分布模式及概率预测方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2010.
	PENG H. Wind power distribution pattern and probabilistic prediction method[D]. Harbin: Harbin Institute of Technology, 2010.
[15]	武佳卉, 邵振国, 杨少华, 等. 数据清洗在新能源功率预测中的研究综述和展望[J]. 电气技术, 2020, 21(11): 1-6.
	WU J H, SHAO Z G, YANG S H, et al. Review and prospect of data cleaning in renewable energy power prediction[J]. Electrical Engineering, 2020, 21(11): 1-6.
[16]	HONG Y Y, YU T H, LIU C Y. Hour-ahead wind speed and power forecasting using empirical mode decomposition[J]. Energies, 2013, 6(12): 6137-6152. DOI URL
[17]	MAO Y, JUN C D. Wind data anomaly detection and interpolation of missing data[J]. Applied Mechanics and Materials, 2014, 672-674: 302-305.
[18]	陈运文, 吴飞, 吴庐山, 等. 基于异常检测的时间序列研究[J]. 计算机技术与发展, 2015, 25(4): 166-170.
	CHEN Y W, WU F, WU L S, et al. Research on time series based on anomaly detection[J]. Computer Technology and Development, 2015, 25(4): 166-170.
[19]	胡珉, 白雪, 徐伟, 等. 多维时间序列异常检测算法综述[J]. 计算机应用, 2020, 40(6): 1553-1564. DOI
	HU M, BAI X, XU W, et al. Review of anomaly detection algorithms for multidimensional time series[J]. Journal of Computer Applications, 2020, 40(6): 1553-1564. DOI
[20]	KUSIAK A, VERMA A. Monitoring wind farms with performance curves[J]. IEEE Transactions on Sustainable Energy, 2012, 4(1): 192-199. DOI URL
[21]	RODRIGUEZ A, LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496. DOI URL
[22]	雷萌, 郭鹏, 刘博嵩. 基于自适应DBSCAN算法的风电机组异常数据识别研究[J]. 动力工程学报, 2021, 41(10): 859-865.
	LEI M, GUO P, LIU B S. Study on abnormal data recognition of wind turbines based on adaptive DBSCAN algorithm[J]. Journal of Chinese Society of Power Engineering, 2021, 41(10): 859-865.
[23]	钟世红. 风电功率异常数据甄别及其预测研究[D]. 北京: 北京林业大学, 2017.
	ZHONG S H. Abnormal data discrimination and forecasting for wind power time series[D]. Beijing: Beijing Forestry University, 2017.
[24]	ZHANG Z P, LIANG Y X. A data stream outlier detection algorithm based on reverse k nearest neighbors[J]. Advanced Materials Research, 2011, 225: 1032-1035.
[25]	胡晓东. 基于SCADA数据的风电机组故障预警[D]. 北京: 华北电力大学, 2021.
	HU X D. Wind turbine fault early warning based on SCADA data[D]. Beijing: North China Electric Power University, 2021.
[26]	李洋, 方滨兴, 郭莉, 等. 基于TCM-KNN和遗传算法的网络异常检测技术[J]. 通信学报, 2007, 28(12): 48-52. DOI
	LI Y, FANG B X, GUO L, et al. Network anomaly detection based on TCM-KNN and genetic algorithm[J]. Journal on Communications, 2007, 28(12): 48-52. DOI
[27]	陈彬杰. 隐私保护的区块链异常交易检测研究[D]. 郑州: 信息工程大学, 2021.
	CHEN B J. Research on privacy-preserving anomaly detection for blockchain[D]. Zhengzhou: Information Engineering University, 2021.
[28]	BREUNIG M M, KRIEGEL H P, NG R T, et al. LOF: identifying density-based local outliers[C]// Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, Dallas, May 16-18, 2000. New York: ACM, 2000: 93-104.
[29]	JIN W, TUNG A K H, HAN J W, et al. Ranking outliers using symmetric neighborhood relationship[C]// LNCS 3918:Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining,Singapore, Apr 9-12, 2006. Berlin, Heidelberg: Springer, 2006: 577-593.
[30]	KRIEGEL H P, KRÖGER P, SCHUBERT E, et al. LoOP: local outlier probabilities[C]// Proceedings of the 18th ACM Conference on Information and Knowledge Management, Hong Kong, China, Nov 2-6, 2009. New York: ACM, 2009: 1649-1652.
[31]	姚添和. 基于自编码器和循环神经网络的短期风电功率预测研究[D]. 泉州: 华侨大学, 2019.
	YAO T H. Research on short-term wind power prediction based on auto-encoder and recurrent neural network[D]. Quanzhou: Huaqiao University, 2019.
[32]	XU X, LEI Y, ZHOU X. A lof-based method for abnormal segment detection in machinery condition monitoring[C]// Proceedings of the 2018 Prognostics and System Health Management Conference, Chongqing, Oct 26-28, 2018. Piscataway: IEEE, 2018: 125-128.
[33]	ZHANG J, YU X, LI Y, et al. A relevant subspace based contextual outlier mining algorithm[J]. Knowledge-Based Systems, 2016, 99: 1-9. DOI URL
[34]	BAI M, WANG X, XIN J, et al. An efficient algorithm for distributed density-based outlier detection on big data[J]. Neurocomputing, 2016, 181: 19-28. DOI URL
[35]	SONG S X, ZHANG A Q, WANG J M, et al. SCREEN: stream data cleaning under speed constraints[C]// Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, May 31-Jun 4, 2015. New York: ACM, 2015: 827-841.
[36]	MUNIR M, SIDDIQUI S A, DENGEL A, et al. DeepAnT: a deep learning approach for unsupervised anomaly detection in time series[J]. IEEE Access, 2018, 7: 1991-2005. DOI URL
[37]	LOSING V, HAMMER B, WERSING H. Incremental on-line learning: a review and comparison of state of the art algorithms[J]. Neurocomputing, 2018, 275: 1261-1274. DOI URL
[38]	张为金. 基于机器学习的电力异常数据检测[D]. 成都: 电子科技大学, 2018.
	ZHANG W J. Power data outlier detection based on machine learning[D]. Chengdu: University of Electronic Science and Technology of China, 2018.
[39]	LU H, LIU Y, FEI Z, et al. An outlier detection algorithm based on cross-correlation analysis for time series dataset[J]. IEEE Access, 2018, 6: 53593-53610. DOI URL
[40]	SAKURADA M, YAIRI T. Anomaly detection using auto-encoders with nonlinear dimensionality reduction[C]// Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, Gold Coast, Dec 2, 2014. New York: ACM, 2014: 4-11.
[41]	KIEU T, YANG B, JENSEN C S. Outlier detection for multidimensional time series using deep neural networks[C]// Proceedings of the 19th IEEE International Conference on Mobile Data Management, Aalborg, Jun 25-28, 2018. Washington: IEEE Computer Society, 2018: 125-134.
[42]	SU Y, ZHAO Y J, NIU C H, et al. Robust anomaly detection for multivariate time series through stochastic recurrent neural network[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, Aug 4-8, 2019. New York: ACM, 2019: 2828-2837.
[43]	DE CARO F, VACCARO A, VILLACCI D. Adaptive wind generation modeling by fuzzy clustering of experimental data[J]. Electronics, 2018, 7(4): 47. DOI URL
[44]	WANG X, LIN J, PATEL N, et al. Exact variable-length anomaly detection algorithm for univariate and multivariate time series[J]. Data Mining and Knowledge Discovery, 2018, 32(6): 1806-1844. DOI URL
[45]	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.
[46]	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.
[47]	KIM D, LEE S, LEE J. An ensemble-based approach to anomaly detection in marine engine sensor streams for efficient condition monitoring and analysis[J]. Sensors, 2020, 20(24): 7285. DOI URL
[48]	CHEN X H, DENG L W, HUANG F T, et al. DAEMON: unsupervised anomaly detection and interpretation for multivariate time series[C]// Proceedings of the 37th IEEE International Conference on Data Engineering, Chania, Apr 19-22, 2021. Piscataway: IEEE, 2021: 2225-2230.
[49]	LI Z H, ZHAO Y J, HAN J Q, et al. Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding[C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Singapore, Aug 14-18, 2021. New York: ACM, 2021: 3220-3230.
[50]	LI J B, ZHENG L C, ZHU Y D, et al. Outlier impact characterization for time series data[C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Advances in Artificial Intelligence. Menlo Park: AAAI, 2021: 11595-11603.
[51]	李伟花. 考虑时空分布特性的区域风电功率预测方法[D]. 北京: 华北电力大学, 2015.
	LI W H. Regional wind power forecasting method based on temporal and spatial distribution characteristics[D]. Beijing: North China Electric Power University, 2015.
[52]	程万伟. 时间序列缺失值插补方法研究[D]. 长沙: 湖南大学, 2018.
	CHENG W W. Study on the interpolation method of time series missing value[D]. Changsha: Hunan University, 2018.
[53]	韦钢, 王飞, 张永健, 等. 负荷预测中历史数据缺损处理[J]. 电力科学与工程, 2004(1): 16-19.
	WEI G, WANG F, ZHANG Y J, et al. Methods of processing shortage and damage of historical data in load forecasting[J]. Electric Power Science and Engineering, 2004(1): 16-19.
[54]	张东英, 李伟花, 刘燕华, 等. 风电场有功功率异常运行数据重构方法[J]. 电力系统自动化, 2014, 38(5): 14-18.
	ZHANG D Y, LI W H, LIU Y H, et al. Reconstruction method of active power historical operating data for wind farm[J]. Automation of Electric Power Systems, 2014, 38(5): 14-18.
[55]	PARK J, MULLER J, ARORA B, et al. Long-term missing value imputation for time series data using deep neural networks[J]. arXiv:2202.12441, 2022.
[56]	BAEZA A, YÁÑEZ DIONISIO F. A note on some bounds between cubic spline interpolants depending on the boundary conditions: application to a monotonicity property[J]. Applied Numerical Mathematics, 2022, 181: 320-325.
[57]	DONGRE B, PATERIYA R K. Power curve model classification to estimate wind turbine power output[J]. Wind Engineering, 2019, 43(3): 213-224. DOI URL
[58]	纪德洋, 金锋, 冬雷, 等. 基于皮尔逊相关系数的光伏电站数据修复[J]. 中国电机工程学报, 2022, 42(4): 1514-1523.
	JI D Y, JIN F, DONG L, et al. Data repairing of photovoltaic power plant based on pearson correlation coefficient[J]. Journal of Chinese Electrical Engineering Science, 2022, 42(4): 1514-1523.
[59]	VAN BUUREN S, GROOTHUIS-OUDSHOORN K. mice: multivariate imputation by chained equations in R[J]. Journal of Statistical Software, 2011, 45: 1-67.
[60]	YU H F, RAO N, DHILLON I S. Temporal regularized matrix factorization for high-dimensional time series prediction[C]// Advances in Neural Information Processing Systems 29, Barcelona, Dec 5-10, 2016: 847-855.
[61]	陈华, 盛晟, 夏润亮, 等. 基于矩阵分解的降水时空插值方法[J]. 河海大学学报(自然科学版), 2021, 49(1): 35-41.
	CHEN H, SHENG S, XIA R L, et al. Spatiotemporal interpolation method of rainfall based on matrix decomposition[J]. Journal of Hohai University(Natural Sciences), 2021, 49(1): 35-41.
[62]	杨茂, 张强. 基于最大相关最小冗余相关向量机的风电功率缺失数据补齐研究[J]. 太阳能学报, 2017, 38(4): 938-944.
	YANG M, ZHANG Q. Polishing missing data for wind power based on MRMR of relevance vector machine[J]. Acta Energiae Solaris Sinica, 2017, 38(4): 938-944.
[63]	杨茂, 孙涌, 穆钢, 等. 基于自适应神经模糊推理系统的风功率缺失数据补齐[J]. 电力系统自动化, 2014, 38(19): 16-21.
	YANG M, SUN Y, MU G, et al. Data completing of missing wind power data based on adaptive neuro-fuzzy inference system[J]. Automation of Electric Power Systems, 2014, 38(19): 16-21.
[64]	LI W, YUE Q, TEQUAN T. Data modeling of calibration parameter measurement based on MLP model[C]// Proceedings of the 2019 14th IEEE International Conference on Electronic Measurement & Instruments, Changsha, Nov 1-3, 2019. Piscataway: IEEE, 2019: 1-7.
[65]	MOON T, HONG S, CHOI H Y, et al. Interpolation of greenhouse environment data using multilayer perceptron[J]. Computers and Electronics in Agriculture, 2019, 166: 105023. DOI URL
[66]	刘杨. 基于样本逼近的PM2.5预测算法研究[D]. 长春: 吉林大学, 2018.
	LIU Y. Research on PM2.5 prediction alogorithm based on sample approximation[D]. Changchun: Jilin University, 2018.
[67]	CHE Z, PURUSHOTHAM S, CHO K, et al. Recurrent neural networks for multivariate time series with missing values[J]. Scientific Reports, 2018, 8(1): 1-12.
[68]	YOON J, ZAME W R, VAN DER SCHAAR M. Multi-directional recurrent neural networks: a novel method for estimating missing data[C]// Proceedings of the 34th International Conference on Machine Learning, Sydney, 2017: 1-5.
[69]	CAO W, WANG D, LI J, et al. BRITS: bidirectional recurrent imputation for time series[C]// Proceedings of the Annual Conference on Neural Information Processing Systems 2018, Montréal, Dec 3-8, 2018: 6776-6786.
[70]	TANG X F, YAO H X, SUN Y W, et al. Joint modeling of local and global temporal dynamics for multivariate time series forecasting with missing values[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conference, the 10th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 7-12, 2020. Menlo Park: AAAI, 2020: 5956-5963.
[71]	ZHANG Y, ZHOU B, CAI X, et al. Missing value imputation in multivariate time series with end-to-end generative adversarial networks[J]. Information Sciences, 2021, 551: 67-82. DOI URL
[72]	GARCÍA-LAENCINA P J, SANCHO-GÓMEZ J L, FIGUEIRAS-VIDAL A R. Pattern classification with missing data: a review[J]. Neural Computing and Applications, 2010, 19(2): 263-282. DOI URL
[73]	NELWAMONDO F V, MOHAMED S, MARWALA T. Missing data: a comparison of neural network and expectation maximization techniques[J]. Current Science, 2007(11): 1514-1521.
[74]	LU C B, MEI Y. An imputation method for missing data based on an extreme learning machine auto-encoder[J]. IEEE Access, 2018, 6: 52930-52935. DOI URL
[75]	LAI X, WU X, ZHANG L, et al. Imputations of missing values using a tracking-removed autoencoder trained with incomplete data[J]. Neurocomputing, 2019, 366: 54-65. DOI URL
[76]	GONDARA L, WANG K. Multiple imputation using deep denoising autoencoders[J]. arXiv:1705.02737, 2017.
[77]	RYU S, KIM M, KIM H. Denoising autoencoder-based missing value imputation for smart meters[J]. IEEE Access, 2020, 8: 40656-40666. DOI URL
[78]	BOQUET G, VICARIO J L, MORELL A, et al. Missing data in traffic estimation: a variational autoencoder imputation method[C]// Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, May 12-17, 2019. Piscataway: IEEE, 2019: 2882-2886.
[79]	NAZABAL A, OLMOS P M, GHAHRAMANI Z, et al. Handling incomplete heterogeneous data using vaes[J]. Pattern Recognition, 2020, 107: 107501. DOI URL
[80]	YOON J, JORDON J, SCHAAR M. Gain: missing data imputation using generative adversarial nets[C]// Proceedings of the 35th International Conference on Machine Learning, Stockholmsmässan, Jul 10-15, 2018: 5689-5698.
[81]	SHANG C, PALMER A, SUN J, et al. VIGAN: missing view imputation with generative adversarial networks[C]// Proceedings of the 2017 IEEE International Conference on Big Data. Piscataway: IEEE, 2017: 766-775.
[82]	CHE T, LI Y, ZHANG R, et al. Maximum-likelihood augmented discrete generative adversarial networks[J]. arXiv: 1702.07983, 2017.
[83]	LUO Y H, CAI X R, ZHANG Y, et al. Multivariate time series imputation with generative adversarial networks[C]// Proceedings of the Annual Conference on Neural Information Processing Systems 2018, Montréal, Dec 3-8, 2018: 1-12.
[84]	金博斌. 基于生成模型的时序数据缺失值插补方案设计[D]. 南京: 南京邮电大学, 2021.
	JIN B B. Design for time series imputation scheme based on generative model[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2021.
[85]	FEDUS W, GOODFELLOW I, DAI A M. MaskGAN: better text generation via filling in the__[J]. arXiv:1801.07736, 2018.
[86]	YU L T, ZHANG W N, WANG J, et al. SeqGAN: sequence generative adversarial nets with policy gradient[C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, Feb 4-9, 2017. Menlo Park: AAAI, 2017: 2852-2858.
[87]	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.
[88]	AMMAD M, RAMLI A. Cubic B-Spline curve interpolation with arbitrary derivatives on its data points[C]// Proceedings of the 23rd International Conference in Information Visualization, Adelaide, Jul 16-19, 2019. Piscataway: IEEE, 2019: 156-159.
[89]	王俊橙. 计及风电功率预测的飞轮储能配合风电场并网的有功功率控制[D]. 成都: 西南交通大学, 2013.
	WANG J C. Active power control of wind farm integration to grid with flywheel energy storage system considering wind power prediction[D]. Chengdu: Southwest Jiaotong University, 2013.
[90]	LUJANO-ROJAS J M, OSÓRIO G J, MATIAS J C O, et al. A heuristic methodology to economic dispatch problem incorporating renewable power forecasting error and system reliability[J]. Renewable Energy, 2016, 87: 731-743. DOI URL
[91]	闫佳. 基于多维聚类及马尔可夫链组合模型的风电功率短期预测方法研究[D]. 银川: 北方民族大学, 2021.
	YAN J. Research on short-term wind power forecasting method based on multi-dimensional clustering and Markov chain combination model[D]. Yinchuan: North Minzu University, 2021.
[92]	陈妮亚. 短期风电功率预测方法研究[D]. 北京: 北京航空航天大学, 2014.
	CHEN N Y. Research on short-term wind power forecasting method[D]. Beijing: Beihang University, 2014.
[93]	ZHANG Y, HAN J, PAN G, et al. A multi-stage predicting methodology based on data decomposition and error correction for ultra-short-term wind energy prediction[J]. Journal of Cleaner Production, 2021, 292: 125981. DOI URL
[94]	钱政, 裴岩, 曹利宵, 等. 风电功率预测方法综述[J]. 高电压技术, 2016, 42(4): 1047-1060.
	QIAN Z, PEI Y, CAO L X, et al. Review of wind power forecasting method[J]. High Voltage Engineering, 2016, 42(4): 1047-1060.
[95]	风电功率预测功能规范: Q/GDW588—2011[S]. 北京: 国家电网有限公司, 2011.
	Function specification of wind power forecasting: Q/GDW 588—2011[S]. Beijing: State Grid Corporation of China, 2011.
[96]	PINSON P. Estimation of the uncertainty in wind power forecasting[D]. École Nationale Supérieure des Mines de Paris, 2006.
[97]	洪翠, 林维明, 温步瀛. 风电场风速及风电功率预测方法研究综述[J]. 电网与清洁能源, 2011, 27(1): 60-66.
	HONG C, LIN W M, WEN B Y. Overview on prediction methods of wind speed and wind power[J]. Power System and Clean Energy, 2011, 27(1): 60-66.
[98]	冯双磊, 王伟胜, 刘纯, 等. 风电场功率预测物理方法研究[J]. 中国电机工程学报, 2010, 30(2): 1-6.
	FENG S L, WANG W S, LIU C, et al. Study on the physical approach to wind power prediction[J]. Proceedings of the CSEE, 2010, 30(2): 1-6.
[99]	LI L, LIU Y, YANG Y, et al. A physical approach of the short-term wind power prediction based on CFD pre-calculated flow fields[J]. Journal of Hydrodynamics, 2013, 25(1): 56-61. DOI URL
[100]	陈树勇, 戴慧珠, 白晓民, 等. 尾流效应对风电场输出功率的影响[J]. 中国电力, 1998(11): 28-31.
	CHEN S Y, DAI H Z, BAI X M, et al. Impact of wind turbine wake on wind power output[J]. Electric Power, 1998(11): 28-31.
[101]	黄飞. 基于风速变化特性的短期风电功率预测方法研究[D]. 南京: 南京信息工程大学, 2019.
	HUANG F. Short-term wind power prediction method based on wind speed variation characteristics[D]. Nanjing: Nanjing University of Information Science and Technology, 2019.
[102]	MURATA A, OHTAKE H, OOZEKI T. Modeling of uncertainty of solar irradiance forecasts on numerical weather predictions with the estimation of multiple confidence intervals[J]. Renewable Energy, 2018, 117: 193-201. DOI URL
[103]	DE GIORGI M G, FICARELLA A, TARANTINO M. Error analysis of short term wind power prediction models[J]. Applied Energy, 2011, 88(4): 1298-1311. DOI URL
[104]	王贺. 风电短期功率预测与并网多目标调度优化研究[D]. 武汉: 武汉大学, 2014.
	WANG H. Study of short-term prediction and multi-objective optimal dispatching of grid-connected wind power[D]. Wuhan: Wuhan University, 2014.
[105]	ZHAO X, WANG S, LI T. Review of evaluation criteria and main methods of wind power forecasting[J]. Energy Procedia, 2011, 12: 761-769. DOI URL
[106]	POGGI P, MUSELLI M, NOTTON G, et al. Forecasting and simulating wind speed in Corsica by using an auto-regressive model[J]. Energy Conversion and Management, 2003, 44(20): 3177-3196. DOI URL
[107]	RAJAGOPALAN S, SANTOSO S. Wind power forecasting and error analysis using the autoregressive moving average modeling[C]// Proceedings of the 2009 IEEE Power & Energy Society General Meeting, Calgary, Jul 26-30, 2009. Piscataway: IEEE, 2009: 1-6.
[108]	HUANG R, HUANG T, GADH R, et al. Solar generation prediction using the ARMA model in a laboratory-level micro-grid[C]// Proceedings of the IEEE 3rd International Conference on Smart Grid Communications, Tainan, China, Nov 5-8, 2012. Piscataway: IEEE, 2012: 528-533.
[109]	杨叔子. 时间序列分析的工程应用[M]. 武汉: 华中理工大学出版社, 2003.
	YANG S Z. Time series analysis in engineering application[M]. Wuhan: Huazhong University of Science & Technology Press, 2003.
[110]	丁明, 张立军, 吴义纯. 基于时间序列分析的风电场风速预测模型[J]. 电力自动化设备, 2005, 25(8): 32-34.
	DING M, ZHANG L J, WU Y C. Wind speed forecast model for wind farms based on time series analysis[J]. Electric Power Automation Equipment, 2005, 25(8): 32-34.
[111]	CROONENBROECK C, DAHL C M. Accurate medium-term wind power forecasting in a censored classification framework[J]. Energy, 2014, 73: 221-232. DOI URL
[112]	MEENAL R, BINU D, RAMYA K C, et al. Weather forecasting for renewable energy system: a review[J]. Archives of Computational Methods in Engineering, 2022, 29: 2875-2891. DOI URL
[113]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32. DOI URL
[114]	MOHANDES M A, HALAWANI T O, REHMAN S, et al. Support vector machines for wind speed prediction[J]. Renewable Energy, 2004, 29(6): 939-947. DOI URL
[115]	凌武能, 杭乃善, 李如琦. 基于云支持向量机模型的短期风电功率预测[J]. 电力自动化设备, 2013, 33(7): 34-38.
	LING W N, HANG N S, LI R Q. Short-term wind power forecasting based on cloud SVM model[J]. Electric Power Automation Equipment, 2013, 33(7): 34-38.
[116]	LIU Y, SHI J, YANG Y, et al. Piecewise support vector machine model for short-term wind-power prediction[J]. International Journal of Green Energy, 2009, 6(5): 479-489. DOI URL
[117]	CHEN T, LEHR J, LAVROVA O, et al. Distribution-level peak load prediction based on Bayesian additive regression trees[C]// Proceedings of the 2016 IEEE Power and Energy Society General Meeting, Boston, Jul 17-21, 2016. Piscataway: IEEE, 2016: 1-5.
[118]	LAHOUAR A, SLAMA J B H. Hour-ahead wind power forecast based on random forests[J]. Renewable Energy, 2017, 109: 529-541. DOI URL
[119]	SHI K, QIAO Y, ZHAO W, et al. An improved random forest model of short term wind power forecasting to enhance accuracy, efficiency, and robustness[J]. Wind Energy, 2018, 21(12): 1383-1394. DOI URL
[120]	王德文, 孙志伟. 电力用户侧大数据分析与并行负荷预测[J]. 中国电机工程学报, 2015, 35(3): 527-537.
	WANG D W, SUN Z W. Big data analysis and parallel load forecasting of electric power user side[J]. Proceedings of the CSEE, 2015, 35(3): 527-537.
[121]	WANG H, SUN J, SUN J, et al. Using random forests to select optimal input variables for short-term wind speed forecasting models[J]. Energies, 2017, 10(10): 1522. DOI URL
[122]	CHIPMAN H A, GEORGE E I, MCCULLOCH R E. BART: Bayesian additive regression trees[J]. The Annals of Applied Statistics, 2010, 4(1): 266-298.
[123]	CHEN T, LEHR J M, LAVROVA O, et al. Distribution feeder-level day-ahead peak load forecasting methods and comparative study[J]. IET Generation, Transmission & Distribution, 2018, 12(13): 3270-3278. DOI URL
[124]	ALIPOUR P, MUKHERJEE S, NATEGHI R. Assessing climate sensitivity of peak electricity load for resilient power systems planning and operation: a study applied to the Texas region[J]. Energy, 2019, 185: 1143-1153. DOI URL
[125]	杨海民, 潘志松, 白玮. 时间序列预测方法综述[J]. 计算机科学, 2019, 46(1): 21-28. DOI
	YANG H M, PAND Z S, BAI W. Review of time series prediction methods[J]. Computer Science, 2019, 46(1): 21-28.
[126]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Proceedings of the Annual Conference on Neural Information Processing Systems 2017, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 5998-6008.
[127]	周松林, 茆美琴, 苏建徽. 基于主成分分析与人工神经网络的风电功率预测[J]. 电网技术, 2011, 35(9): 128-132.
	ZHOU S L, MAO M Q, SU J H. Prediction of wind power based on principal component analysis and artificial neural network[J]. Power System Technology, 2011, 35(9): 128-132.
[128]	WANG Y S, GAO J, XU Z W, et al. A short-term output power prediction model of wind power based on deep learning of grouped time series[J]. European Journal of Electrical Engineering, 2020, 22(1).
[129]	薛阳, 王琳, 王舒, 等. 一种结合CNN和GRU网络的超短期风电预测模型[J]. 可再生能源, 2019, 37(3): 456-462.
	XUE Y, WANG L, WANG S, et al. An ultra-short-term wind power forecasting model combined with CNN and GRU networks[J]. Renewable Energy Resources, 2019, 37(3): 456-462.
[130]	CHITSAZ H, AMJADY N, ZAREIPOUR H. Wind power forecast using wavelet neural network trained by improved clonal selection algorithm[J]. Energy Conversion & Management, 2015, 89: 588-598.
[131]	FAWAZ H, FORESTIER G, WEBER J, et al. Deep learning for time series classification: a review[J]. Data Mining and Knowledge Discovery, 2019, 33(4): 917-963. DOI
[132]	LAI G, CHANG W C, YANG Y, et al. Modeling long-and short-term temporal patterns with deep neural networks[C]// Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Ann Arbor, Jul 8-12, 2018. New York: ACM, 2018: 95-104.
[133]	RANGAPURAM S S, SEEGER M W, GASTHAUS J, et al. Deep state space models for time series forecasting[C]// Proceedings of the Annual Conference on Neural Information Processing Systems 2018, Montréal, Dec 3-8, 2018: 7796-7805.
[134]	SALINAS D, FLUNKERT V, GASTHAUS J, et al. DeepAR: probabilistic forecasting with autoregressive recurrent networks[J]. International Journal of Forecasting, 2020, 36(3): 1181-1191. DOI URL
[135]	BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[J]. arXiv:1803.01271, 2018.
[136]	王玉. 基于深度学习的风电场短期风速预测组合模型[D]. 合肥: 中国科学技术大学, 2021.
	WANG Y. Combined model of short-term wind speed prediction for wind farms based on deep learning[D]. Hefei: University of Science and Technology of China, 2021.
[137]	YILDIZ C, ACIKGOZ H, KORKMAZ D, et al. An improved residual-based convolutional neural network for very short-term wind power forecasting[J]. Energy Conversion and Management, 2021, 228: 113731. DOI URL
[138]	NIU Z, YU Z, TANG W, et al. Wind power forecasting using attention-based gated recurrent unit network[J]. Energy, 2020, 196: 117081. DOI URL
[139]	ZHANG H, YAN J, LIU Y, et al. Multi-source and temporal attention network for probabilistic wind power prediction[J]. IEEE Transactions on Sustainable Energy, 2021, 12(4): 2205-2218. DOI URL
[140]	JIAO R, HUANG X, MA X, et al. A model combining stacked auto encoder and back propagation algorithm for short-term wind power forecasting[J]. IEEE Access, 2018, 6: 17851-17858. DOI URL
[141]	PENG X, ZHANG Z, XU Q, et al. A three-stage ensemble short-term wind power prediction method based on VMD-WT transform and SDAE deep learning[C]// Proceedings of the 2020 IEEE/IAS Industrial and Commercial Power System Asia, Weihai, Jul 13-15, 2020. Piscataway: IEEE, 2020: 1350-1356.
[142]	HUANG B, LIANG Y, QIU X. Wind power forecasting using attention-based recurrent neural networks: a comparative study[J]. IEEE Access, 2021, 9: 40432-40444. DOI URL
[143]	陈刚, 王印, 单锦宁, 等. 生成对抗网络在风电功率预测中的应用[J]. 辽宁工程技术大学学报(自然科学版), 2021, 40(3): 258-264.
	CHEN G, WANG Y, SHAN J N, et al. Application of generation countermeasure network in wind power forecasting[J]. Journal of Liaoning Technical University (Natural Science), 2021, 40(3): 258-264.
[144]	潘霄, 张明理, 刘德宝, 等. 基于鲁棒多标签生成对抗的风电场日前出力区间预测[J]. 电力系统自动化, 2022, 46(10): 216-223.
	PAN X, ZHANG M L, LIU D B, et al. Interval prediction of wind farm day-ahead output based on robust multi-label generative adversarial[J]. Automation of Electric Power Systems, 2022, 46(10): 216-223.
[145]	YUAN R, WANG B, MAO Z, et al. Multi-objective wind power scenario forecasting based on PG-GAN[J]. Energy, 2021, 226: 120379. DOI URL
[146]	SONG J, WANG J, LU H. A novel combined model based on advanced optimization algorithm for short-term wind speed forecasting[J]. Applied Energy, 2018, 215: 643-658. DOI URL
[147]	TASCIKARAOGLU A, UZUNOGLU M. A review of combined approaches for prediction of short-term wind speed and power[J]. Renewable and Sustainable Energy Reviews, 2014, 34: 243-254. DOI URL
[148]	SHI J, DING Z, 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, 2013, 5(1): 521-526. DOI URL
[149]	ZHANG S, ZHEN Z, WANG F, et al. Ultra-short-term wind power forecasting model based on time-section fusion and pattern classification[C]// Proceedings of the 2020 IEEE/IAS Industrial and Commercial Power System Asia, Weihai, Jul 13-15, 2020. Piscataway: IEEE, 2020: 1325-1333.
[150]	CHEN C, LIU H. Medium-term wind power forecasting based on multi-resolution multi-learner ensemble and adaptive model selection[J]. Energy Conversion and Management, 2020, 206: 112492. DOI URL
[151]	CHANG G W, LU H J, WANG P K, et al. Gaussian mixture model based neural network for short term wind power forecast[J]. International Transactions on Electrical Energy Systems, 2017, 27(6): e2320. DOI URL
[152]	BANIK A, BEHERA C, SARATHKUMAR T V, et al. Uncertain wind power forecasting using LSTM-based prediction interval[J]. IET Renewable Power Generation, 2020, 14(14): 2657-2667. DOI URL
[153]	SUN Z, SUN H, ZHANG J. Multistep wind speed and wind power prediction based on a predictive deep belief network and an optimized random forest[J]. Mathematical Problems in Engineering, 2018: 6231745.
[154]	ALENCAR D B, AFFONSO C M, OLIVEIRA R C L, et al. Hybrid approach combining SARIMA and neural networks for multi-step ahead wind speed forecasting in Brazil[J]. IEEE Access, 2018, 6: 55986-55994. DOI URL
[155]	ZHOU B, LIU C, LI J, et al. A hybrid method for ultrashort-term wind power prediction considering meteorological features and seasonal information[J]. Mathematical Problems in Engineering, 2020: 1795486.
[156]	LIU D, NIU D, WANG H, et al. Short-term wind speed forecasting using wavelet transform and support vector machines optimized by genetic algorithm[J]. Renewable Energy, 2014, 62: 592-597. DOI URL
[157]	YUAN X, CHEN C, YUAN Y, et al. Short-term wind power prediction based on LSSVM-GSA model[J]. Energy Conversion and Management, 2015, 101: 393-401. DOI URL
[158]	肖峰, 陈国初. 基于改进果蝇算法优化的SVM风电功率短期预测[J]. 华东理工大学学报(自然科学版), 2016, 42(3): 420-426.
	XIAO F, CHEN G C. Wind power short-term prediction based on SVM trained by improved FOA[J]. Journal of East China University of Science and Technology (Natural Science Edition), 2016, 42(3): 420-426.
[159]	张超. 基于信息融合的短期风电功率预测研究[D]. 合肥: 合肥工业大学, 2020.
	ZHANG C. Research on short-term wind power prediction based on information fusion[D]. Hefei: Hefei University of Technology, 2020.
[160]	LI L L, CEN Z Y, TSENG M L, et al. Improving short-term wind power prediction using hybrid improved cuckoo search arithmetic-support vector regression machine[J]. Journal of Cleaner Production, 2021, 279: 126-133.
[161]	ZHANG Y, WANG J, WANG X. Review on probabilistic forecasting of wind power generation[J]. Renewable and Sustainable Energy Reviews, 2014, 32: 255-270. DOI URL
[162]	YAN J, LI K, BAI E W, et al. Hybrid probabilistic wind power forecasting using temporally local Gaussian process[J]. IEEE Transactions on Sustainable Energy, 2015, 7(1): 87-95. DOI URL
[163]	LIANG Z, LIANG J, WANG C, et al. Short-term wind power combined forecasting based on error forecast correction[J]. Energy Conversion and Management, 2016, 119: 215-226. DOI URL
[164]	石珂凡. 基于组合模型的风电超短期功率预测[D]. 秦皇岛: 燕山大学, 2020.
	SHI K F. Ultra-short-term wind power prediction based on combined model[D]. Qinhuangdao: Yanshan University, 2020.
[165]	TAIEB S B, TAYLOR J W, HYNDMAN R J. Coherent probabilistic forecasts for hierarchical time series[C]// Proceedings of the 2017 International Conference on Machine Learning, Sydney, Aug 6-11, 2017: 3348-3357.
[166]	SHIRATORI T, KOBAYASHI K, TAKANO Y. Prediction of hierarchical time series using structured regularization and its application to artificial neural networks[J]. PLoS One, 2020, 15(11): e0242099. DOI URL
[167]	KARMY J P, LÓPEZ J, MALDONADO S. Simultaneous model construction and noise reduction for hierarchical time series via support vector regression[J]. Knowledge-Based Systems, 2021, 232: 107492. DOI URL
[168]	SAGHEER A, HAMDOUN H, YOUNESS H. Deep LSTM-based transfer learning approach for coherent forecasts in hierarchical time series[J]. Sensors, 2021, 21(13): 4379. DOI URL
[169]	RANGAPURAM S S, WERNER L D, BENIDIS K, et al. End-to-end learning of coherent probabilistic forecasts for hierarchical time series[C]// Proceedings of the 38th International Conference on Machine Learning, 2021: 8832-8843.
[170]	GHEIBI O, WEYNS D, QUIN F. Applying machine learning in self-adaptive systems: a systematic literature review[J]. ACM Transactions on Autonomous and Adaptive Systems, 2021, 15(3): 1-37.
[171]	THRUN S, MITCHELL T M. Lifelong robot learning[J]. Robotics and Autonomous Systems, 1995, 15(1/2): 25-46. DOI URL
[172]	CHEN T. On using retrained and incremental machine learning for modeling performance of adaptable software: an empirical comparison[J]. arXiv:1903.10614, 2019.
[173]	CHEN T, BAHSOON R. Self-adaptive and online QoS modeling for cloud-based software services[J]. IEEE Transactions on Software Engineering, 2016, 43(5): 453-475. DOI URL
[174]	GHEIBI O, WEYNS D. Lifelong self-adaptation: self-adaptation meets lifelong machine learning[J]. arXiv:2204.01834, 2022.
[175]	彭小圣, 熊磊, 文劲宇, 等. 风电集群短期及超短期功率预测精度改进方法综述[J]. 中国电机工程学报, 2016, 36(23): 6315-6326.
	PENG X S, XIONG L, WEN J Y, et al. A summary of the state of the art for short-term and ultra-short-term wind power prediction of regions[J]. Proceedings of the CSEE, 2016, 36(23): 6315-6326.
[176]	薛禹胜, 郁琛, 赵俊华, 等. 关于短期及超短期风电功率预测的评述[J]. 电力系统自动化, 2015, 39(6): 141-151.
	XUE Y S, YU C, ZHAO J H, et al. A review on short-term and ultra-short-term wind power prediction[J]. Automation of Electric Power Systems, 2015, 39(6): 141-151.
[177]	张亚超, 刘开培, 秦亮, 等. 基于聚类经验模态分解-样本熵和优化极限学习机的风电功率多步区间预测[J]. 电网技术, 2016, 40(7): 2045-2051.
	ZHANG Y C, LIU K P, QIN L, et al. Wind power multi-step interval prediction based on ensemble empirical mode decomposition-sample entropy and optimized extreme learning machine[J]. Power System Technology, 2016, 40(7): 2045-2051.
[178]	李海波, 鲁宗相, 乔颖, 等. 大规模风电并网的电力系统运行灵活性评估[J]. 电网技术, 2015, 39(6): 1672-1678.
	LI H B, LU Z X, QIAO Y, et al. Assessment on operational flexibility of power grid with grid-connected large-scale wind farms[J]. Power System Technology, 2015, 39(6): 1672-1678.
[179]	郑培. 超短期风电功率预测及储能系统在风电场中的应用研究[D]. 上海: 上海交通大学, 2020.
	ZHENG P. Research on the application of ultra-short-term wind power forecasting and energy storage system in wind farm[D]. Shanghai: Shanghai Jiao Tong University, 2020.
[180]	WANG H, LIU Y, ZHOU B, et al. Taxonomy research of artificial intelligence for deterministic solar power forecasting[J]. Energy Conversion and Management, 2020, 214: 112909. DOI URL
[181]	ZERVEAS G, JAYARAMAN S, PATEL D, et al. A transformer-based framework for multivariate time series representation learning[C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Singapore, Aug 14-18, 2021. New York: ACM, 2021: 2114-2124.
[182]	赵天琪, 赵海燕, 张伟, 等. 基于模型的自适应方法综述[J]. 软件学报, 2018, 29(1): 23-41.
	ZHAO T Q, ZHAO H Y, ZHANG W, et al. Survey of model-based self-adaptation methods[J]. Journal of Software, 2018, 29(1): 23-41.

方法	文献	技术特点	优点	缺陷与不足
基于统计的异常值检测技术	HBOS^[12]、统计量分析法^[15]、3σ准则^[17]	假定数据服从某种分布，并根据数据不一致性判断其是否异常	简单、易懂	需提前确定数据的分布特征，应用困难
基于聚类的异常值检测技术	马氏距离与K-means结合^[20]、DPC^[21]、自适应DBSCAN^[22]	使用聚类算法挖掘风电数据中数据间相互关系，并将离群数据标记为异常	较为简单，且避免了人为原因造成的误差现象，迁移能力强	检测耗时长，算法效率低
基于距离的异常值检测技术	AnomalyDetect^[12]、SODRNN^[24]、 KNN^[25,27]、TCM-KNN^[26]	通过计算每个数据间距离来判断数据是否异常	不要求数据满足某种分布，适用于高维数据	参数选取敏感，全局检测，需提前得知数据的先验知识，无法区分数据异常程度
基于密度的异常值检测技术	LOF^[31]、PCA-LOF^[32]、COAS^[33]、 DLC^[34]	通过检测数据局部的密度信息判断是否异常	检测精度高	参数选取敏感，局部检测造成时间复杂度高
基于序列偏差的异常值检测技术	SCREEN^[35]	根据相邻序列中存在的明显偏差判断是否异常	时间复杂度低	波动性强的数据适用性低，搜索范围大，效率低
基于预测偏差的异常值检测技术	LSTM-AE^[10]、DeepAnT^[36]	根据预测值与实际值偏差大小判断是否异常	时间复杂度低	对拟合模型精度要求高，检测效果低于其他算法
基于集成的异常值检测技术	ODCA^[39]、dAE^[40]、LSTM-AE-ADV^[41]、OmniAnomaly^[42]、Fuzzy clustering^[43]、SLADE-TS和SLADE-MTS^[44]	通过组合多种异常检测算法来判断是否异常	精准度高，鲁棒性好	时间复杂度高

方法	文献	技术特点	优点	缺陷与不足
基于统计的异常值检测技术	HBOS^[12]、统计量分析法^[15]、3σ准则^[17]	假定数据服从某种分布，并根据数据不一致性判断其是否异常	简单、易懂	需提前确定数据的分布特征，应用困难
基于聚类的异常值检测技术	马氏距离与K-means结合^[20]、DPC^[21]、自适应DBSCAN^[22]	使用聚类算法挖掘风电数据中数据间相互关系，并将离群数据标记为异常	较为简单，且避免了人为原因造成的误差现象，迁移能力强	检测耗时长，算法效率低
基于距离的异常值检测技术	AnomalyDetect^[12]、SODRNN^[24]、 KNN^[25,27]、TCM-KNN^[26]	通过计算每个数据间距离来判断数据是否异常	不要求数据满足某种分布，适用于高维数据	参数选取敏感，全局检测，需提前得知数据的先验知识，无法区分数据异常程度
基于密度的异常值检测技术	LOF^[31]、PCA-LOF^[32]、COAS^[33]、 DLC^[34]	通过检测数据局部的密度信息判断是否异常	检测精度高	参数选取敏感，局部检测造成时间复杂度高
基于序列偏差的异常值检测技术	SCREEN^[35]	根据相邻序列中存在的明显偏差判断是否异常	时间复杂度低	波动性强的数据适用性低，搜索范围大，效率低
基于预测偏差的异常值检测技术	LSTM-AE^[10]、DeepAnT^[36]	根据预测值与实际值偏差大小判断是否异常	时间复杂度低	对拟合模型精度要求高，检测效果低于其他算法
基于集成的异常值检测技术	ODCA^[39]、dAE^[40]、LSTM-AE-ADV^[41]、OmniAnomaly^[42]、Fuzzy clustering^[43]、SLADE-TS和SLADE-MTS^[44]	通过组合多种异常检测算法来判断是否异常	精准度高，鲁棒性好	时间复杂度高

方法	文献	技术特点	优点	缺陷与不足
常规处理方法	直接删除法	直接删除数据集中缺失数据	简单、易懂、时间复杂度低	数据信息丢失，缺失率提高，影响后期数据挖掘效果
常规处理方法	均值插补法、零值插补法、上一次观测值插补法等	使用未缺失数据均值、0值或缺失值前一个未缺失数据填补	简单、易懂、时间复杂度低	改变原始数据分布，忽略了不同特征间的相互关联程度，缺乏数据时序性利用
辨别式的插补方法	线性回归插补、非线性回归插补	通过回归分析得出缺失数据	构建简便，计算量小	线性：应用面窄非线性：相较于线性应用面广，不适应于高维数据
	MLP^[55]	通过特殊的前馈神经网络估计数据中的缺失值	可用于线性或非线性插值，整体适用面广泛	参数较多
	递推式非邻均值补全法^[53-54]	由缺失值两侧观测值递推缺失值的方式	构造简单	未充分挖掘数据信息，插补精度低
	三次样条插值法^[57]	通过三次多项式拟合离散数据，以此获得缺失值的估计值	相对于普通插值拟合曲线更为平滑，插补更加准确	离散节点数增加，插补曲线边缘稳定性降低
	MICE^[59]	多次插补降低单次插补造成的标准误差	插补误差较小	整体时长、空间复杂度大幅度提升，应用局限
	MF^[60-61]	通过矩阵分解技术学习时序矩阵的整体特征，进而修补缺失数据	计算复杂度低，可用于处理大规模数据集	模型整体适用受限
	KNN^[52]	通过缺失值周围k个观测值估计缺失值	计算精度高	很少考虑数据间的时序性，计算成本高，空间复杂度高，K值设置
	RNN^[67⇓-69]	通过RNN估计数据中的缺失值	考虑数据间的时序性，插补精度高	插补时仅进行顺序插补，时间复杂度高
生成式的插补方法	EM^[72-73]	迭代计算期望E和最大化M以获得插补数据	简单、插补精度高	对数据集依赖性强，未考虑数据间时序性
	AE^{[74⇓⇓⇓⇓-79]}	通过Encoder和Decoder后重建原始数据	与数据关联性高，插补效果良好	生成数据并非真实数据，训练极端，易记忆训练样本，影响后续工作
	GAN^{[80⇓⇓⇓⇓⇓-86]}	从随机的“噪声”中生成“真实”的样本数据	整体精度高于其他插补模型	网络训练不稳定，训练时需要完整数据，随机噪声
基于物理特性的插补方法	文献[87]、文献[88]	使用临近风场、风机同时刻未缺失数据进行插补	简便，考虑风机、地形等信息特点	需保证风机型号等信息一致，限制性强

方法	文献	技术特点	优点	缺陷与不足
常规处理方法	直接删除法	直接删除数据集中缺失数据	简单、易懂、时间复杂度低	数据信息丢失，缺失率提高，影响后期数据挖掘效果
常规处理方法	均值插补法、零值插补法、上一次观测值插补法等	使用未缺失数据均值、0值或缺失值前一个未缺失数据填补	简单、易懂、时间复杂度低	改变原始数据分布，忽略了不同特征间的相互关联程度，缺乏数据时序性利用
辨别式的插补方法	线性回归插补、非线性回归插补	通过回归分析得出缺失数据	构建简便，计算量小	线性：应用面窄非线性：相较于线性应用面广，不适应于高维数据
	MLP^[55]	通过特殊的前馈神经网络估计数据中的缺失值	可用于线性或非线性插值，整体适用面广泛	参数较多
	递推式非邻均值补全法^[53-54]	由缺失值两侧观测值递推缺失值的方式	构造简单	未充分挖掘数据信息，插补精度低
	三次样条插值法^[57]	通过三次多项式拟合离散数据，以此获得缺失值的估计值	相对于普通插值拟合曲线更为平滑，插补更加准确	离散节点数增加，插补曲线边缘稳定性降低
	MICE^[59]	多次插补降低单次插补造成的标准误差	插补误差较小	整体时长、空间复杂度大幅度提升，应用局限
	MF^[60-61]	通过矩阵分解技术学习时序矩阵的整体特征，进而修补缺失数据	计算复杂度低，可用于处理大规模数据集	模型整体适用受限
	KNN^[52]	通过缺失值周围k个观测值估计缺失值	计算精度高	很少考虑数据间的时序性，计算成本高，空间复杂度高，K值设置
	RNN^[67⇓-69]	通过RNN估计数据中的缺失值	考虑数据间的时序性，插补精度高	插补时仅进行顺序插补，时间复杂度高
生成式的插补方法	EM^[72-73]	迭代计算期望E和最大化M以获得插补数据	简单、插补精度高	对数据集依赖性强，未考虑数据间时序性
	AE^{[74⇓⇓⇓⇓-79]}	通过Encoder和Decoder后重建原始数据	与数据关联性高，插补效果良好	生成数据并非真实数据，训练极端，易记忆训练样本，影响后续工作
	GAN^{[80⇓⇓⇓⇓⇓-86]}	从随机的“噪声”中生成“真实”的样本数据	整体精度高于其他插补模型	网络训练不稳定，训练时需要完整数据，随机噪声
基于物理特性的插补方法	文献[87]、文献[88]	使用临近风场、风机同时刻未缺失数据进行插补	简便，考虑风机、地形等信息特点	需保证风机型号等信息一致，限制性强

方法	文献		技术特点		优点		缺陷与不足
物理模型	[87-93]		使用物理方法进行计算		简单、易懂		对原始数据依赖性较强，抗干扰性、可移植性差
统计模型	传统统计模型^[85]		采用历史数据作为未来时刻预测值使用		简单、易懂		仅限于超短期预测使用，且精度极低
	时间序列模型^{[96⇓⇓⇓⇓-101]}		当前时刻观测值由先前若干时刻观测值及干扰项构成		计算简便		难以挖掘非线性数据信息，预测精度不足，数据较大时计算复杂度较大
	其他机器学习模型	SVM^{[104⇓⇓-107]}	利用定义的核函数进行回归估计	高维计算速度快，不易陷入局部最优解		效果与核函数选取有关，严重依赖于使用者经验
		RF^{[108⇓⇓-111]}	重复执行从根节点开始根据阈值判断进入当前节点的左/右节点，直至叶子节点输出预测值的平均值	适用于大量数据集，计算速度高，准确率较高		原始数据质量差时效果较差
		BART^[113-114]	计算单棵树的均值	精度高，不易过拟合		计算时长较高
	深度学习模型	BP^[117]	—	具有较强的容错和泛化能力		学习速度慢，易出现局部最优
		RNN^{[118,122⇓-124]}	—	可用于长时间数据处理		传统RNN存在梯度消失和梯度爆炸问题，模型训练困难
		CNN^{[119,125⇓-127]}	—	卷积核参数共享，短期信息提取较好		需要调参，计算量大
		AE^[130⇓-132]	对原始数据进行重构，以获得预测结果	数据关联性高		训练极端，易出现驯良样本记忆现象
		GAN^[133⇓-135]	通过生成器鉴别器获得尽可能接近原始数据分布的预测数据	数据无需人工标注		传统GAN训练不稳定，计算效率低，无法描述输入数据特征
组合模型	基于多模型加权的组合预测方法^{[138⇓⇓⇓⇓-143]}		对多个模型预测结果进行加权输出	灵活性、适应性、预测精度较高		计算效率低，应用场景较窄
	基于数据预处理的组合预测方法^[15,144-145]		将原始数据分解为多个平稳子序列后进行预测的方式	结构简单，计算效率高，迁移性强		预测精度有限
	基于优化技术的组合预测方法^{[146⇓⇓⇓-150]}		采用优化技术对模型参数进行优化	促使模型更好收敛和更好的泛化误差		无法保证最优解
	基于误差修正的组合预测方法^{[151⇓⇓-154]}		对预测误差进行估计及预测修正	具有较高的预测精度		相较于其他组合模型计算效率较低

风电输出功率预测技术研究综述

Survey of Wind Power Output Power Forecasting Technology

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 182

相关文章 15

编辑推荐

Metrics

[1]	张璐, 芦天亮, 杜彦辉. 人脸视频深度伪造检测方法综述[J]. 计算机科学与探索, 2023, 17(1): 1-26.
[2]	王仕宸, 黄凯, 陈志刚, 张文东. 深度学习的三维人体姿态估计综述[J]. 计算机科学与探索, 2023, 17(1): 74-87.
[3]	梁佳利, 华保健, 吕雅帅, 苏振宇. 面向深度学习算子的循环不变式外提算法[J]. 计算机科学与探索, 2023, 17(1): 127-139.
[4]	王剑哲, 吴秦. 坐标注意力特征金字塔的显著性目标检测算法[J]. 计算机科学与探索, 2023, 17(1): 154-165.
[5]	张祥平, 刘建勋. 基于深度学习的代码表征及其应用综述[J]. 计算机科学与探索, 2022, 16(9): 2011-2029.
[6]	李冬梅, 罗斯斯, 张小平, 许福. 命名实体识别方法研究综述[J]. 计算机科学与探索, 2022, 16(9): 1954-1968.
[7]	任宁, 付岩, 吴艳霞, 梁鹏举, 韩希. 深度学习应用于目标检测中失衡问题研究综述[J]. 计算机科学与探索, 2022, 16(9): 1933-1953.
[8]	杨才东, 李承阳, 李忠博, 谢永强, 孙方伟, 齐锦. 深度学习的图像超分辨率重建技术综述[J]. 计算机科学与探索, 2022, 16(9): 1990-2010.
[9]	吕晓琦, 纪科, 陈贞翔, 孙润元, 马坤, 邬俊, 李浥东. 结合注意力与循环神经网络的专家推荐算法[J]. 计算机科学与探索, 2022, 16(9): 2068-2077.
[10]	安凤平, 李晓薇, 曹翔. 权重初始化-滑动窗口CNN的医学图像分类[J]. 计算机科学与探索, 2022, 16(8): 1885-1897.
[11]	曾凡智, 许露倩, 周燕, 周月霞, 廖俊玮. 面向智慧教育的知识追踪模型研究综述[J]. 计算机科学与探索, 2022, 16(8): 1742-1763.
[12]	刘艺, 李蒙蒙, 郑奇斌, 秦伟, 任小广. 视频目标跟踪算法综述[J]. 计算机科学与探索, 2022, 16(7): 1504-1515.
[13]	赵小明, 杨轶娇, 张石清. 面向深度学习的多模态情感识别研究进展[J]. 计算机科学与探索, 2022, 16(7): 1479-1503.
[14]	夏鸿斌, 肖奕飞, 刘渊. 融合自注意力机制的长文本生成对抗网络模型[J]. 计算机科学与探索, 2022, 16(7): 1603-1610.
[15]	孙方伟, 李承阳, 谢永强, 李忠博, 杨才东, 齐锦. 深度学习应用于遮挡目标检测算法综述[J]. 计算机科学与探索, 2022, 16(6): 1243-1259.