Hierarchical context-aware anomaly diagnosis in large-scale PV systems using SCADA data

Abstract

Accurate anomaly diagnosis is essential for reducing operation and maintenance (O&M) cost, while improving safety and reliability of large-scale photovoltaic (PV) systems. Although many methods have been proposed, they either require extra sensing devices or suffer from high false alarm rates. In this work, we present a cost-effective hierarchical context-aware method for string-level anomaly diagnosis in large-scale PV systems. The proposed approach is based on unsupervised machine learning techniques and requires no additional hardware support beyond widely adopted supervisory control and data acquisition (SCADA) systems. The effectiveness and efficiency of our proposed approach are evaluated with a 40 MW PV system located in East China. The experimental results demonstrate that the proposed approach can support string-level anomaly diagnosis with high accuracy and provide sufficient lead time for daily maintenance.