Analysis of the effects of a passing cloud on a grid-interactive photovoltaic system with battery storage using neural networks

In this paper, a combined radial-basis-functions (RBF) and backprop network is used to predict the effects of passing clouds on a Utility-Interactive Photovoltaic (PV) system with battery storage. Using the irradiance as inpu t signal, the network models the effects of random cloud movement on the el ectrical variables of the Maximum Power Point Tracker (MPPT) and the variab les of the utility-linked inverter over a short period of timer During shor t time intervals, the irradiance is considered as the only varying input pa rameter affecting the electrical variables of the system. The advantages of Artificial Neural Network (ANN) simulation over standard linear model is t hat it does not require the knowledge of internal system parameters, involv es less computational effort, and offers a compact solution for multiple-va riable problems. The model can be easily integrated into a typical utility system and resulting system behavior can be determined. The viability of th e battery-supported PV system as dispatchable unit is also investigated. Th e simulated results are compared with the experimental results captured dur ing cloudy days. This model can be a useful, tool in solar Energy Engineeri ng design and in PV-integrated utility operation.