106680 20230519145434.0 doi 10.1007/s00521-021-06254-6 sideral 124607 ART-2021-124607 eng Sanz Alcaine, José Miguel Universidad de Zaragoza (orcid)0000-0001-9376-543X Online voltage prediction using gaussian process regression for fault-tolerant photovoltaic standalone applications 2021 Access copy available to the general public Unrestricted This 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. info:eu-repo/grantAgreement/ES/DGA-FEDER/RIS3-LMP16-18 info:eu-repo/grantAgreement/ES/MINECO/RTC2015-3358-5 info:eu-repo/semantics/openAccess by-nc-nd http://creativecommons.org/licenses/by-nc-nd/3.0/es/ 5.102 2021 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE 45 / 146 = 0.308 2021 Q2 T1 1.072 2021 Software 2021 Q1 Artificial Intelligence 2021 Q1 8.7 2021 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Sebastián, Eduardo Universidad de Zaragoza (orcid)0000-0001-9671-4056 Sanz-Gorrachategui, Iván Universidad de Zaragoza (orcid)0000-0003-0198-5094 Bernal-Ruiz, Carlos Universidad de Zaragoza (orcid)0000-0001-9334-4870 Bono-Nuez, Antonio Universidad de Zaragoza (orcid)0000-0001-5664-7063 Pajovic, Milutin Orlik, Philip V. 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 5008 785 Universidad de Zaragoza Dpto. Ingeniería Electrón.Com. Área Tecnología Electrónica 33 (2021), 16577–16590 Neural comput. appl. Neural Computing and Applications 0941-0643 1768204 http://zaguan.unizar.es/record/106680/files/texto_completo.pdf Versión publicada 2330199 http://zaguan.unizar.es/record/106680/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:106680 articulos driver 2023-05-18-14:21:06 ARTICLE