Entropy and Correntropy Against Minimum Square Error in Offline and Online Three-Day Ahead Wind Power Forecasting

被引：163

作者：

Bessa, Ricardo J. ^{[1
,2
]}

Miranda, Vladimiro ^{[3
]}

Gama, Joao ^{[4
]}

机构：

[1] INESC Porto, Inst Engn Sistemas & Computadores Porto, Oporto, Portugal

[2] Univ Porto, Fac Econ, FEP, P-4100 Oporto, Portugal

[3] Univ Porto, Fac Engn, FEUP, P-4100 Oporto, Portugal

[4] LA LIAAD, INESC Porto, Lab Artificial Intelligence & Decis Support, Oporto, Portugal

来源：

IEEE TRANSACTIONS ON POWER SYSTEMS | 2009年 / 24卷 / 04期

关键词：

Correntropy; entropy; neural networks; Parzen windows; wind power forecasting; SHORT-TERM PREDICTION; SPEED PREDICTION; GENERATION; REGRESSION;

D O I：

10.1109/TPWRS.2009.2030291

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

080906 [电磁信息功能材料与结构]; 082806 [农业信息与电气工程];

摘要：

This paper reports new results in adopting entropy concepts to the training of neural networks to perform wind power prediction as a function of wind characteristics (speed and direction) in wind parks connected to a power grid. Renyi's entropy is combined with a Parzen windows estimation of the error pdf to form the basis of two criteria (minimum entropy and maximum correntropy) under which neural networks are trained. The results are favorably compared in online and offline training with the traditional minimum square error (MSE) criterion. Real case examples for two distinct wind parks are presented.

引用

页码：1657 / 1666

页数：10

共 38 条

[1]

Ahlstrom M., 2005, Proc. IEEE/PES Transmission and Distribution Conf. and Exhib.: Asia and Pacific, P1, DOI DOI 10.1109/TDC.2005.1547203

[2]

[Anonymous], SELECTED PAPERS

[3]

[Anonymous], ON LINE LEARNING NEU

[4]

[Anonymous], P INT JOINT C NEUR N