000001037 001__ 1037
000001037 005__ 20190611210126.0
000001037 022__ $$a978-1-4799-8872-3
000001037 0247_ $$2DOI$$a10.1109/IMIS.2015.54
000001037 037__ $$aCONFERENCE
000001037 041__ $$aeng
000001037 245__ $$aSolar production prediction based on non-linear meteo source adaptation
000001037 260__ $$c2015$$b8-10 July 2015$$aBlumenau, Brazil
000001037 269__ $$a2015-07
000001037 300__ $$a5 p.
000001037 506__ $$avisible
000001037 520__ $$aThis work presents a data-intensive solution to predict Photovoltaïque energy (PV) production. PV and other renewable sources have widely spread in recent years. Although those sources provide an environmentally-friendly solution, their integration is a real challenge in terms of power management as it depends on meteorological conditions. The ability to predict those variable sources considering meteorological uncertainty plays a key role in the management of the energy supply needs and reserves. This paper presents an easy-to-use methodology to predict PV production using time series analyses and sampling algorithms. The aim is to provide a forecasting model to set the day-ahead grid electricity need. This information useful for power dispatching plans and grid charge control. The main novelties of our approach is to provide an easy implemented and flexible solution that combines classification algorithms to predict the PV plant efficiency considering weather conditions and nonlinear regression to predict weather forecasted errors in order to improve prediction results. The results are based on the data collected in the Technople's micro grid in Sierre (Switzerland) described further in the paper. The best experimental results have been obtained using hourly historical weather measures (radiation and temperature) and PV production as training inputs and weather forecasted parameters as prediction inputs. Considering a 10 month dataset and despite the presence of 17 missing days, we achieved a Percentage Mean Absolute Deviation (PMAD) of 20% in August and 21% in September. Better results can be obtained with a larger dataset but as more historical data were not available, other months have not been tested.$$9eng
000001037 592__ $$aHEG-VS
000001037 592__ $$bInstitut Informatique de gestion
000001037 592__ $$cEconomie et Services
000001037 65017 $$aInformatique
000001037 6531_ $$aadvanced metering infrastructure$$9eng
000001037 6531_ $$adata intelligence analysis$$9eng
000001037 655_7 $$afull paper
000001037 6531_ $$aenergy information management$$9eng
000001037 6531_ $$aKNIME$$9eng
000001037 6531_ $$amicrogrid$$9eng
000001037 6531_ $$aPV forecast$$9eng
000001037 6531_ $$asolar production prediction$$9eng
000001037 700__ $$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)$$aBarque, Mariam
000001037 700__ $$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)$$aDufour, Luc
000001037 700__ $$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)$$aGenoud, Dominique
000001037 700__ $$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)$$aZufferey, Arnaud
000001037 700__ $$uUMR CNRS 5302, Mines Albi, France$$aLadevie, Bruno
000001037 700__ $$aBezian, Jean-Jacques$$uUMR CNRS 5302, Mines Albi, France
000001037 711__ $$a9 th Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS)$$cBlumenau, Brazil$$d08/07/2015 / 10/07/2015
000001037 773__ $$tProceedings of the 9th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS) 2015
000001037 8564_ $$uhttps://hesso.tind.io/record/1037/files/Barry_SolarProductionPredictionBasedOnNonLinearMeteoSourceAdaptation_2015.pdf$$s690848
000001037 85641 $$zSite de l'éditeur$$uhttp://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7284974
000001037 909CO $$pDOMAINE_ECONOMIESERVICE_CONFERENCE$$pGLOBAL_SET$$pECONOMIESERVICES_CONFERENCE$$ooai:hesso.tind.io:1037
000001037 906__ $$aNONE
000001037 950__ $$aI1
000001037 980__ $$aconference