Short-term multi-step wind speed prediction using statistical methods and artificial neural networks

The results of the observations made by TUBITAKT60 national observation house meteorological station in April, 2016 werecompiled on this website using the PHP programming language. Obtained windspeed data were analysed using statistical and artificial neural networkmethods and predicted wind speed p...

Full description

Saved in:
Bibliographic Details
Main Author: İsmail Kırbaş
Format: Article
Language:English
Published: Sakarya University 2018-02-01
Series:Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi
Subjects:
Online Access:https://dergipark.org.tr/tr/download/article-file/332568
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The results of the observations made by TUBITAKT60 national observation house meteorological station in April, 2016 werecompiled on this website using the PHP programming language. Obtained windspeed data were analysed using statistical and artificial neural networkmethods and predicted wind speed predictions over the time series brought tothe field. There is a significant difference in error rates between the ARIMAmodels and the artificial neural networks examined as a result of comparisonswith the calculated calculations and actual data. While the wind speedestimation studies in the literature generally focus only on single stepprediction success, detailed evaluation of commonly used estimation methods atthe prospective 12 step level has been carried out.
ISSN:2147-835X