Presentation 2012-03-09
Short Term PV Prediction Using Committee Kernel Adaptive Filters
Yuichiro YONEDA, Toshihisa TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We study short term power prediction of photovoltaic (PV) using data acquired from the PV panels. PV power out puts are usually unstable and nonlinear time series data. Besides PV outputs greatly vary depending on the weather. Therefore, PV power prediction should be made adaptivly and should consider the change of weather. To this end, we propose a system that committee of adaptive filters which have different properties respectively to consider charactristics of PV outputs. Since the proposed method has linear and nonlinear properties, it is expected that the proposed method tracks PV outputs adequately. By numerical experiments, we compare prediction performance of a sole adaptive filter to that of the proposed committee.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) photovoltaic power generation / photovoltaic system power forecasting / adaptive filter / kernel methods
Paper # CAS2011-162,SIP2011-182,CS2011-154
Date of Issue

Conference Information
Committee CAS
Conference Date 2012/3/1(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Circuits and Systems (CAS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Short Term PV Prediction Using Committee Kernel Adaptive Filters
Sub Title (in English)
Keyword(1) photovoltaic power generation
Keyword(2) photovoltaic system power forecasting
Keyword(3) adaptive filter
Keyword(4) kernel methods
1st Author's Name Yuichiro YONEDA
1st Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology()
2nd Author's Name Toshihisa TANAKA
2nd Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology
Date 2012-03-09
Paper # CAS2011-162,SIP2011-182,CS2011-154
Volume (vol) vol.111
Number (no) 465
Page pp.pp.-
#Pages 6
Date of Issue