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

Abstract

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 neurofuzzy 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.

A Linear Equivalent Method of PV Array for Fault Analysis of Medium-Voltage Networks

“…Finally, the above calculated parameters are substituted into (7), and the results as shown in ( 17), ( 18) and ( 19) are obtained.…”

“…R eq = −G eq u + G eq u eq (7) In (7), the slope of this equation in the I-U coordinate system −1/R eq , that is, −G eq , should be the same as the derivative of a specific equivalent point in the I-U characteristic curve of PV output.…”

“…The former focuses on the longterm operation of PV systems, such as power flow analysis, PV output forecasting, and control scheme research [5]. The latter focuses on the research of fault detection and handling methods related to PV systems [6], [7]. Compared to the control issues during long-term operation of PV systems, the working characteristics of PV systems during short-term fault scenarios are different and the duration is shorter.…”

On the Use of Indirect Measurements in Virtual Sensors for Renewable Energies: A Review

“…This includes factors such as variable power output and solar irradiance, which necessitate the use of predictive models. These models are crucial for forecasting PV generation, which in turn enables smart demand response, efficient energy management, and ensures an adequate supply [22][23][24][25][26][27][28]. Forecasts can be categorized into three types, based on the time horizon: short-term (from a few minutes to several hours), medium-term (from 1 week to 1 year), and long-term (longer than 1 year) [29].…”