Wind Speed Forecast under a Distributed Learning Approach

Héctor Allende-Cid, Héctor Allende, Raúl Monge, Claudio Moraga

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper we apply a distributed learning approach to improve the perfomance of wind speed forecast. We use data obtained from 54 different weather stations in the U. S. and without sharing data between sites, we share model information between them, to improve the performance over local models trained with only local data. We show that sharing the information of the distributed models, improves the forecast we could obtain by only using locally trained models.

Original languageEnglish
Title of host publicationProceedings - 2013 32nd International Conference of the Chilean Computer Science Society, SCCC 2013
PublisherIEEE Computer Society
Pages44-48
Number of pages5
ISBN (Electronic)9781509004263
DOIs
StatePublished - 2 Jul 2013
Externally publishedYes
Event32nd International Conference of the Chilean Computer Science Society, SCCC 2013 - Temuco, Cautin, Chile
Duration: 13 Nov 201315 Nov 2013

Publication series

NameProceedings - International Conference of the Chilean Computer Science Society, SCCC
Volume0
ISSN (Print)1522-4902

Conference

Conference32nd International Conference of the Chilean Computer Science Society, SCCC 2013
Country/TerritoryChile
CityTemuco, Cautin
Period13/11/1315/11/13

Keywords

  • Distributed Machine Learning
  • Time Series Forecast
  • Wind Speed Forecast

Fingerprint

Dive into the research topics of 'Wind Speed Forecast under a Distributed Learning Approach'. Together they form a unique fingerprint.

Cite this