Training a FIS with EPSO under an Entropy Criterion for Wind Power prediction

Author

Miranda, V. ; Cerqueira, C. ; Monteiro, C.

Author_Institution

INESC Porto

fYear

2006

fDate

11-15 June 2006

Firstpage

1

Lastpage

8

Abstract

This paper summarizes efforts in understanding the possible application of information theoretic learning principles to power systems. It presents the application of Renyi´s entropy combined with Parzen windows as a measure of information content of the error distribution in model parameter estimation in supervised learning. It illustrates the concept with an application to the prediction of power generated in a wind park, made by Takagi-Sugeno fuzzy inference systems, whose parameters are discovered with an EPSO-evolutionary particle swarm optimization algorithm

Keywords

entropy; fuzzy neural nets; fuzzy systems; parameter estimation; particle swarm optimisation; wind power; EPSO; FIS; Parzen window; Renyi´s entropy; error distribution; evolutionary particle swarm optimization algorithm; fuzzy inference systems; parameter estimation; supervised learning; wind power prediction; Entropy; Parameter estimation; Power generation; Power system measurements; Power system modeling; Supervised learning; Wind energy; Wind energy generation; Wind forecasting; Wind power generation; Information theoretic learning; fuzzy inference systems; power systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Probabilistic Methods Applied to Power Systems, 2006. PMAPS 2006. International Conference on

Conference_Location

Stockholm

Print_ISBN

978-91-7178-585-5

Type

conf

DOI

10.1109/PMAPS.2006.360208

Filename

4202220