TR2022-038

Online Voltage Prediction Using Gaussian Process Regression for Fault-Tolerant Photovoltaic Standalone Applications


    •  Sanz-Alcaine, J.M., Sanz-Gorrachategui, I., Pajovic, M., Orlik, P.V., "Online Voltage Prediction Using Gaussian Process Regression for Fault-Tolerant Photovoltaic Standalone Applications", Neural Computing and Applications, March 2022.
      BibTeX TR2022-038 PDF
      • @article{Sanz-Alcaine2022mar,
      • author = {Sanz-Alcaine, José Miguel and Sanz-Gorrachategui, Ivan and Pajovic, Milutin and Orlik, Philip V.},
      • title = {Online Voltage Prediction Using Gaussian Process Regression for Fault-Tolerant Photovoltaic Standalone Applications},
      • journal = {Neural Computing and Applications},
      • year = 2022,
      • month = mar,
      • url = {https://www.merl.com/publications/TR2022-038}
      • }
  • MERL Contact:
  • Research Areas:

    Machine Learning, Optimization, Signal Processing

Abstract:

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 Confederación Hidrográfica del Ebro (CHE), public institution which manages the hydrographic system of Aragón, 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 hours. 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 ShortTerm Memory (LSTM) and Nonlinear Autoregressive Exogenous Model (NARX) networks. A maximum error of 127mV and
308mV at the end of the night with Sparse and ME respectively corroborates GPR as a promising tool.