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

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 ( $k$ NN) with univariate monitoring approaches has been proposed. Specifically, $k$ NN-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 $k$ NN 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 $k$ NN-based schemes for anomaly detection. Parametric and nonparametric thresholds using kernel density estimation have been used to detect faults. The effectiveness of the $k$ NN-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.