Data-Driven Approach for Condition Monitoring and Improving Power Output of Photovoltaic Systems

Increasing renewable energy targets globally has raised the requirement for the efficient and profitable operation of solar photovoltaic (PV) systems. In light of this requirement, this paper provides a path for evaluating the operating condition and improving the power output of the PV system in a grid integrated environment. To achieve this, different types of faults in grid-connected PV systems (GCPVs) and their impact on the energy loss associated with the electrical network are analyzed. A data-driven approach using neural networks (NNs) is proposed to achieve root cause analysis and localize the fault to the component level in the system. The localized fault condition is combined with a parallel operation of adaptive neuro-fuzzy inference units (ANFIUs) to develop a power mismatch-based control unit (PMCU) for improving the power output of the GCPV. To develop the proposed framework, a 10-kW single-phase GCPV is simulated for training the NN-based anomaly detection approach with 14 deviation signals. Further, the developed algorithm is combined with the PMCU implemented with the experimental setup of GCPV. The results identified 98.2% training accuracy and 43000 observations/sec prediction speed for the trained classifier, and improved power output with reduced voltage and current harmonics for the grid-connected PV operation.