Bootstrapped Multi-Model Neural-Network Super-Ensembles for Wind Speed and Power Forecasting

PDF

Authors
  1. Men, Z.
  2. Yee, E.
  3. Lien, F-S.
  4. Ji, H.
  5. Liu, Y.
Corporate Authors
Defence Research and Development Canada, Suffield Research Centre, Ralston AB (CAN);Waterloo CFD Engineering Consulting Inc., Waterloo ON (CAN);Waterloo Univ, Waterloo Ont (CAN) Dept of Mechanical and Mechatronics Engineering;SCHOOL OF RENEWABLE ENERGY, NORTH CHINA ELECTRIC POWER UNIVERSITY, BEIJING 102206 (CHINA)
Abstract
The bootstrap resampling method is applied to an ensemble artificial neural network (ANN) approach (which combines machine learning with physical data obtained from a numerical weather prediction model) to provide a multi-ANN model super-ensemble for application to multi-step-ahead forecasting of wind speed and of the associated power generated from a wind turbine. A statistical combination of the individual forecasts from the various ANNs of the super-ensemble is used to construct the best deterministic forecast, as well as the prediction uncertainty interval associated with this forecast. The bootstrapped neural-network methodology is validated using measured wind speed and power data acquired from a wind turbine in an operational wind farm located in northern China.
Keywords
artificial neural network;bootstrap resampling;numerical weather prediction;super-ensemble;wind speed and power forecasting;uncertainty quantification
Report Number
DRDC-RDDC-2014-P58 — External Literature
Date of publication
22 Oct 2014
Number of Pages
10
DSTKIM No
CA039563
CANDIS No
800489
Format(s):
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: