Mi DSpace
Please use this identifier to cite or link to this item: http://hdl.handle.net/UCSP/15773
Title: On predicting wind power series by using Bayesian Enhanced modified based-neural network
Authors: Rodriguez Rivero, Cristian
Pucheta, Julian
Otano, Paula
Túpac Valdivia, Yván Jesús
Gorrostieta, Efren
Laboret, Sergio
Keywords: Complex networks;Dynamical systems;Linear systems;Time series;Time series analysis;Wind power;Bayesian;Data classification;Extract informations;Forecasting methods;Mathematical conversion;Short term prediction;Time series forecasting;Wind power forecasting;Weather forecasting
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers Inc.
metadata.dc.relation.uri: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85046491666&doi=10.23919%2fRPIC.2017.8214355&partnerID=40&md5=386e57fee0bb809de58f5007410326c2
Abstract: In this paper, wind power series prediction using BEA modified (BEAmod.) neural networks-based approach is presented. Wind power forecasting is a complex, multidimensional, and highly non-linear system. Neural network is able to learn the relationship between system inputs and outputs without mathematical conversion, and perform complex nonlinear mapping, data classification, prediction, and is also suitable for wind power forecasting. The purpose of this paper is to use neural network to design a wind power forecasting system. The focus, with particularly interest in short-term prediction, is by using the data model selected, in which the Bayesian enhanced modified approach (BEAmod.) is used to extract information to make prediction. The efficiency analysis of the proposed forecasting method is examined through the underlying dynamical system, in which the nonlinear and temporal dependencies span long time intervals (long memory process). The conducted results show that this method can be used to improve the predictability of short-term wind time series with a suitable number of hidden units compared to that of reported in the literature. © 2017 Comisión Permanente RPIC.
URI: http://repositorio.ucsp.edu.pe/handle/UCSP/15773
ISBN: 9789875447547
Appears in Collections:Artículos de investigación

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.