TY - GEN
T1 - Wind Speed Forecast under a Distributed Learning Approach
AU - Allende-Cid, Héctor
AU - Allende, Héctor
AU - Monge, Raúl
AU - Moraga, Claudio
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2013/7/2
Y1 - 2013/7/2
N2 - 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.
AB - 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.
KW - Distributed Machine Learning
KW - Time Series Forecast
KW - Wind Speed Forecast
UR - http://www.scopus.com/inward/record.url?scp=85011796870&partnerID=8YFLogxK
U2 - 10.1109/SCCC.2013.24
DO - 10.1109/SCCC.2013.24
M3 - Conference contribution
AN - SCOPUS:85011796870
T3 - Proceedings - International Conference of the Chilean Computer Science Society, SCCC
SP - 44
EP - 48
BT - Proceedings - 2013 32nd International Conference of the Chilean Computer Science Society, SCCC 2013
PB - IEEE Computer Society
T2 - 32nd International Conference of the Chilean Computer Science Society, SCCC 2013
Y2 - 13 November 2013 through 15 November 2013
ER -