Machine Learning-Based Probabilistic Forecasting of Wind Power Generation: A Combined Bootstrap and Cumulant Method

被引:14
作者
Wan, Can [1 ]
Cui, Wenkang [1 ]
Song, Yonghua [1 ,2 ]
机构
[1] Zhejiang Univ, Coll Elect Engn, Hangzhou 310027, Peoples R China
[2] Univ Macau, State Key Lab Internet Things Smart City, Taipa, Macau, Peoples R China
关键词
Uncertainty; Forecasting; Wind power generation; Predictive models; Probabilistic logic; Estimation; Machine learning; Probabilistic forecasting; bootstrap; cumulant; machine learning; uncertainty quantification; wind power; FLOW CONTROLLER; TRANSIENT STABILITY; SYSTEM OSCILLATIONS; UPFC CONTROLLER; DESIGN; COORDINATION; OPTIMIZATION; ENHANCEMENT; SERIES;
D O I
10.1109/TPWRS.2023.3264821
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Probabilistic forecasting provides complete probability information of renewable generation and load, which assists the diverse decision-making tasks in power systems under uncertainties. Conventional machine learning-based probabilistic forecasting methods usually consider the predictive uncertainty following prior distributional assumptions. This article develops a novel combined bootstrap and cumulant (CBC) method to generate nonparametric predictive distribution using higher order statistics for probabilistic forecasting. The CBC method successfully integrates machine learning with conditional moments and cumulants to describe the overall predictive uncertainty. A bootstrap-based conditional moment estimation method is proposed to quantify both the epistemic and aleatory uncertainties involved in machine learning. Higher order cumulants are utilized for overall uncertainty quantification based on the estimated conditional moments with its unique additivity. Three types of series expansions including Gram-Charlier, Edgeworth, and Cornish-Fisher expansions are adopted to improve the overall performance and the generalization ability. Comprehensive numerical studies using the actual wind power data validate the effectiveness of the proposed CBC method.
引用
收藏
页码:1370 / 1383
页数:14
相关论文
共 50 条
[1]  
Abdelkrim B., 2019, Int. J. Power Electron. Drive Syst. (IJPEDS), V10, P1281
[2]  
Balakrishnan FG, 2013, 2013 FOURTH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATIONS AND NETWORKING TECHNOLOGIES (ICCCNT)
[3]   Dynamic stability enhancement of power system based on a typical unified power flow controllers using imperialist competitive algorithm [J].
Banaei, M. R. ;
Seyed-Shenava, S. J. ;
Farahbakhsh, Parisa .
AIN SHAMS ENGINEERING JOURNAL, 2014, 5 (03) :691-702
[4]   UPFC with series and shunt FACTS controllers for the economic operation of a power system [J].
Bhattacharyya, Biplab ;
Gupta, Vikash Kumar ;
Kumar, Sanjay .
AIN SHAMS ENGINEERING JOURNAL, 2014, 5 (03) :775-787
[5]   TS-fuzzy-controlled active power filter for load compensation [J].
Bhende, C. N. ;
Mishra, S. ;
Jain, S. K. .
IEEE TRANSACTIONS ON POWER DELIVERY, 2006, 21 (03) :1459-1465
[6]   Further results on "Infinity norms as Lyapunov functions for linear systems" [J].
Christophersen, Frank J. ;
Morari, Manfred .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2007, 52 (03) :547-553
[7]   Design of a nonlinear variable-gain fuzzy controller for FACTS devices [J].
Dash, PK ;
Morris, S ;
Mishra, S .
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2004, 12 (03) :428-438
[8]   A radial basis function neural network controller for UPFC [J].
Dash, PK ;
Mishra, S ;
Panda, G .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2000, 15 (04) :1293-1299
[9]   A reconfigurable FACTS system for university laboratories [J].
Dong, L ;
Crow, ML ;
Yang, Z ;
Shen, C ;
Zhang, L ;
Atcitty, S .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2004, 19 (01) :120-128
[10]   Integral Terminal Synergetic-Based Direct Power Control for Distributed Generation Systems [J].
Elnady, A. ;
Noureldin, A. ;
Adam, Ali A. .
IEEE TRANSACTIONS ON SMART GRID, 2022, 13 (02) :1287-1297