An ANN-based method for wind speed forecasting with S-Transform

Hiroyuki Mori, Soichiro Okura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, a new method is proposed for wind speed forecasting. The proposed method makes use of RBFN (Radial Basis Function Network) of ANN (Artificial Neural Network) to evaluate one-step ahead wind speed. To improve the performance of RBFN, two techniques are introduced into RBFN. One is to use the prefiltering technique of the S-Transform for the feature extraction of input variables. It plays a key rule to extract the feature in frequency domain with the excellent function. The other is to apply a two-staged forecasting method to wind speed time-series. It is effective for reducing the forecasting model errors. The proposed method is successfully applied to real data of wind speed in Japan.

Original languageEnglish
Title of host publicationProceedings of the 2016 IEEE Region 10 Conference, TENCON 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages642-645
Number of pages4
ISBN (Electronic)9781509025961
DOIs
Publication statusPublished - 8 Feb 2017
Event2016 IEEE Region 10 Conference, TENCON 2016 - Singapore, Singapore
Duration: 22 Nov 201625 Nov 2016

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Conference

Conference2016 IEEE Region 10 Conference, TENCON 2016
CountrySingapore
CitySingapore
Period22/11/1625/11/16

    Fingerprint

Keywords

  • RBFN
  • S-transform
  • artificial neural network
  • prediction
  • time series analysis
  • two staged forecasting
  • wind speed

Cite this

Mori, H., & Okura, S. (2017). An ANN-based method for wind speed forecasting with S-Transform. In Proceedings of the 2016 IEEE Region 10 Conference, TENCON 2016 (pp. 642-645). [7848081] (IEEE Region 10 Annual International Conference, Proceedings/TENCON). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TENCON.2016.7848081