Kernel methods for short-term spatio-temporal wind prediction

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

3 Citations (Scopus)
56 Downloads (Pure)

Abstract

Two nonlinear methods for producing short-term spatio-temporal wind speed forecast are presented. From the relatively new class of kernel methods, a kernel least mean squares algorithm and kernel recursive least squares algorithm are introduced and used to produce 1 to 6 hour-ahead predictions of wind speed at six locations in the Netherlands. The performance of the proposed methods are compared to their linear equivalents, as well as the autoregressive, vector autoregressive and persistence time series models. The kernel recursive least squares algorithm is shown to offer significant improvement over all benchmarks, particularly for longer forecast horizons. Both proposed algorithms exhibit desirable numerical properties and are ripe for further development.

Original languageEnglish
Title of host publication2015 IEEE Power and Energy Society General Meeting
PublisherIEEE
Number of pages5
ISBN (Print)9781467380409
DOIs
Publication statusPublished - 30 Sep 2015
EventIEEE Power and Energy Society General Meeting, PESGM 2015 - Denver, United States
Duration: 26 Jul 201530 Jul 2015

Conference

ConferenceIEEE Power and Energy Society General Meeting, PESGM 2015
CountryUnited States
CityDenver
Period26/07/1530/07/15

Keywords

  • least squares approximation
  • wind power
  • kernel method
  • nonlinear methods

Fingerprint Dive into the research topics of 'Kernel methods for short-term spatio-temporal wind prediction'. Together they form a unique fingerprint.

  • Projects

    Cite this