eCite Digital Repository

Investigating using stochastic methods to generate training data for windpower prediction


Potter, C and Negnevitsky, M, Investigating using stochastic methods to generate training data for windpower prediction, Australian Journal of Electrical & Electronics Engineering, 3, (2) pp. 137-145. ISSN 1448-837X (2007) [Refereed Article]

Restricted - Request a copy

Copyright Statement

Copyright 2007 Institution of Engineers, Australia

Official URL:


This paper investigates the potential capability of stochastic methods to generate data for unndpower prediction purposes. Stochastic models have been used to develop data before, however, this paper shows that a simplistic single histogram model will not suffice for windpower purposes. The need to generate data is important as often there is only a short period of data available for use in developing a prediction system. This need is then exaggerated if information from multiple wind turbines is desired for the data input. © Institution of Engineers.

Item Details

Item Type:Refereed Article
Keywords:stochastic methods, training data, windpower prediction
Research Division:Engineering
Research Group:Electrical and Electronic Engineering
Research Field:Control Systems, Robotics and Automation
Objective Division:Energy
Objective Group:Environmentally Sustainable Energy Activities
Objective Field:Environmentally Sustainable Energy Activities not elsewhere classified
UTAS Author:Potter, C (Mr Potter)
UTAS Author:Negnevitsky, M (Professor Michael Negnevitsky)
ID Code:50794
Year Published:2007
Deposited By:Engineering
Deposited On:2007-08-01
Last Modified:2012-12-03

Repository Staff Only: item control page