Improved $k$ NN-Based Monitoring Schemes for Detecting Faults in PV Systems

Fouzi Harrou, Bilal Taghezouit, Ying Sun

Research output: Contribution to journalArticlepeer-review

86 Scopus citations


This paper presents a model-based anomaly detection method for supervising the direct current (dc) side of photovotaic (PV) systems. Toward this end, a framework combining the benefits of k-nearest neighbors (kNN) with univariate monitoring approaches has been proposed. Specifically, kNN-based Shewhart and exponentially weighted moving average (EWMA) schemes with parametric and nonparametric thresholds have been introduced to suitably detect faults in PV systems. The choice of kNN method to separate normal and abnormal features is motivated by its capacity to handle nonlinear features and do not make assumptions on the underlying data distribution. In addition, because the EWMA approach is sensitive in detecting small changes. First, a simulation model for the inspected PV array is constructed. Then, residuals generated from this model are employed as the input for kNN-based schemes for anomaly detection. Parametric and nonparametric thresholds using kernel density estimation have been used to detect faults. The effectiveness of the kNN-based procedures is verified using actual measurements from a 9.54-kWp grid-connected system in Algeria. Results proclaim the efficiency of the proposed strategy to supervise the dc side of PV systems.
Original languageEnglish (US)
Pages (from-to)811-821
Number of pages11
JournalIEEE Journal of Photovoltaics
Issue number3
StatePublished - Mar 18 2019

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): OSR-2015-CRG4-2582
Acknowledgements: This work was supported by the King Abdullah University of Science and Technology (KAUST), Office of Sponsored Research (OSR) under Award OSR-2015-CRG4-2582.


Dive into the research topics of 'Improved $k$ NN-Based Monitoring Schemes for Detecting Faults in PV Systems'. Together they form a unique fingerprint.

Cite this