000106680 001__ 106680
000106680 005__ 20230519145434.0
000106680 0247_ $$2doi$$a10.1007/s00521-021-06254-6
000106680 0248_ $$2sideral$$a124607
000106680 037__ $$aART-2021-124607
000106680 041__ $$aeng
000106680 100__ $$0(orcid)0000-0001-9376-543X$$aSanz Alcaine, José Miguel$$uUniversidad de Zaragoza
000106680 245__ $$aOnline voltage prediction using gaussian process regression for fault-tolerant photovoltaic standalone applications
000106680 260__ $$c2021
000106680 5060_ $$aAccess copy available to the general public$$fUnrestricted
000106680 5203_ $$aThis paper presents a fault detection system for photovoltaic standalone applications based on Gaussian Process Regression (GPR). The installation is a communication repeater from the Confederacion Hidrografica del Ebro (CHE), public institution which manages the hydrographic system of Aragon, Spain. Therefore, fault-tolerance is a mandatory requirement, complex to fulfill since it depends on the meteorology, the state of the batteries and the power demand. To solve it, we propose an online voltage prediction solution where GPR is applied in a real and large dataset of two years to predict the behavior of the installation up to 48 hour. The dataset captures electrical and thermal measures of the lead-acid batteries which sustain the installation. In particular, the crucial aspect to avoid failures is to determine the voltage at the end of the night, so different GPR methods are studied. Firstly, the photovoltaic standalone installation is described, along with the dataset. Then, there is an overview of GPR, emphasizing in the key aspects to deal with real and large datasets. Besides, three online recursive multistep GPR model alternatives are tailored, justifying the selection of the hyperparameters: Regular GPR, Sparse GPR and Multiple Experts (ME) GPR. An exhaustive assessment is performed, validating the results with those obtained by Long Short-Term Memory (LSTM) and Nonlinear Autoregressive Exogenous Model (NARX) networks. A maximum error of 127 mV and 308 mV at the end of the night with Sparse and ME, respectively, corroborates GPR as a promising tool.
000106680 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FEDER/RIS3-LMP16-18$$9info:eu-repo/grantAgreement/ES/MINECO/RTC2015-3358-5
000106680 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
000106680 590__ $$a5.102$$b2021
000106680 592__ $$a1.072$$b2021
000106680 594__ $$a8.7$$b2021
000106680 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b45 / 146 = 0.308$$c2021$$dQ2$$eT1
000106680 593__ $$aSoftware$$c2021$$dQ1
000106680 593__ $$aArtificial Intelligence$$c2021$$dQ1
000106680 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000106680 700__ $$0(orcid)0000-0001-9671-4056$$aSebastián, Eduardo$$uUniversidad de Zaragoza
000106680 700__ $$0(orcid)0000-0003-0198-5094$$aSanz-Gorrachategui, Iván$$uUniversidad de Zaragoza
000106680 700__ $$0(orcid)0000-0001-9334-4870$$aBernal-Ruiz, Carlos$$uUniversidad de Zaragoza
000106680 700__ $$0(orcid)0000-0001-5664-7063$$aBono-Nuez, Antonio$$uUniversidad de Zaragoza
000106680 700__ $$aPajovic, Milutin
000106680 700__ $$aOrlik, Philip V.
000106680 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000106680 7102_ $$15008$$2785$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Tecnología Electrónica
000106680 773__ $$g33 (2021), 16577–16590$$pNeural comput. appl.$$tNeural Computing and Applications$$x0941-0643
000106680 8564_ $$s1768204$$uhttps://zaguan.unizar.es/record/106680/files/texto_completo.pdf$$yVersión publicada
000106680 8564_ $$s2330199$$uhttps://zaguan.unizar.es/record/106680/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000106680 909CO $$ooai:zaguan.unizar.es:106680$$particulos$$pdriver
000106680 951__ $$a2023-05-18-14:21:06
000106680 980__ $$aARTICLE