Machine learning-based statistical testing hypothesis for fault detection in photovoltaic systems

R. Fazai, K. Abodayeh, Majdi Mansouri, M. Trabelsi, Hazem Nounou, Mohamed Nounou, G. E. Georghiou

Research output: Contribution to journalArticle

Abstract

In this paper, we consider a machine learning approach merged with statistical testing hypothesis for enhanced fault detection performance in photovoltaic (PV) systems. The developed method makes use of a machine learning based Gaussian process regression (GPR) technique as a modeling framework, while a generalized likelihood ratio test (GLRT) chart is applied to detect PV system faults. The developed GPR-based GLRT approach is assessed using simulated and real PV data through monitoring the key PV system variables (current, voltage, and power). The computation time, missed detection rate (MDR), and false alarm rate (FAR) are computed to evaluate the fault detection performance of the proposed approach.

Original languageEnglish
Pages (from-to)405-413
Number of pages9
JournalSolar Energy
Volume190
DOIs
Publication statusPublished - 15 Sep 2019

Fingerprint

Fault detection
Learning systems
Testing
Monitoring
Electric potential

Keywords

  • Fault detection
  • Gaussian process regression (GPR)
  • Generalized likelihood ratio test (GLRT)
  • Machine learning
  • Photovoltaic (PV) systems

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Materials Science(all)

Cite this

Machine learning-based statistical testing hypothesis for fault detection in photovoltaic systems. / Fazai, R.; Abodayeh, K.; Mansouri, Majdi; Trabelsi, M.; Nounou, Hazem; Nounou, Mohamed; Georghiou, G. E.

In: Solar Energy, Vol. 190, 15.09.2019, p. 405-413.

Research output: Contribution to journalArticle

@article{93e35cc1ff6b404b9539453a512e04da,
title = "Machine learning-based statistical testing hypothesis for fault detection in photovoltaic systems",
abstract = "In this paper, we consider a machine learning approach merged with statistical testing hypothesis for enhanced fault detection performance in photovoltaic (PV) systems. The developed method makes use of a machine learning based Gaussian process regression (GPR) technique as a modeling framework, while a generalized likelihood ratio test (GLRT) chart is applied to detect PV system faults. The developed GPR-based GLRT approach is assessed using simulated and real PV data through monitoring the key PV system variables (current, voltage, and power). The computation time, missed detection rate (MDR), and false alarm rate (FAR) are computed to evaluate the fault detection performance of the proposed approach.",
keywords = "Fault detection, Gaussian process regression (GPR), Generalized likelihood ratio test (GLRT), Machine learning, Photovoltaic (PV) systems",
author = "R. Fazai and K. Abodayeh and Majdi Mansouri and M. Trabelsi and Hazem Nounou and Mohamed Nounou and Georghiou, {G. E.}",
year = "2019",
month = "9",
day = "15",
doi = "10.1016/j.solener.2019.08.032",
language = "English",
volume = "190",
pages = "405--413",
journal = "Solar Energy",
issn = "0038-092X",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Machine learning-based statistical testing hypothesis for fault detection in photovoltaic systems

AU - Fazai, R.

AU - Abodayeh, K.

AU - Mansouri, Majdi

AU - Trabelsi, M.

AU - Nounou, Hazem

AU - Nounou, Mohamed

AU - Georghiou, G. E.

PY - 2019/9/15

Y1 - 2019/9/15

N2 - In this paper, we consider a machine learning approach merged with statistical testing hypothesis for enhanced fault detection performance in photovoltaic (PV) systems. The developed method makes use of a machine learning based Gaussian process regression (GPR) technique as a modeling framework, while a generalized likelihood ratio test (GLRT) chart is applied to detect PV system faults. The developed GPR-based GLRT approach is assessed using simulated and real PV data through monitoring the key PV system variables (current, voltage, and power). The computation time, missed detection rate (MDR), and false alarm rate (FAR) are computed to evaluate the fault detection performance of the proposed approach.

AB - In this paper, we consider a machine learning approach merged with statistical testing hypothesis for enhanced fault detection performance in photovoltaic (PV) systems. The developed method makes use of a machine learning based Gaussian process regression (GPR) technique as a modeling framework, while a generalized likelihood ratio test (GLRT) chart is applied to detect PV system faults. The developed GPR-based GLRT approach is assessed using simulated and real PV data through monitoring the key PV system variables (current, voltage, and power). The computation time, missed detection rate (MDR), and false alarm rate (FAR) are computed to evaluate the fault detection performance of the proposed approach.

KW - Fault detection

KW - Gaussian process regression (GPR)

KW - Generalized likelihood ratio test (GLRT)

KW - Machine learning

KW - Photovoltaic (PV) systems

UR - http://www.scopus.com/inward/record.url?scp=85070873393&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070873393&partnerID=8YFLogxK

U2 - 10.1016/j.solener.2019.08.032

DO - 10.1016/j.solener.2019.08.032

M3 - Article

VL - 190

SP - 405

EP - 413

JO - Solar Energy

JF - Solar Energy

SN - 0038-092X

ER -