No abstract

This study employed a cerebellar model articulation controller (CMAC) neural network to conduct fault diagnoses on photovoltaic power generation systems. We composed a module array using 9 series and 2 parallel connections of SHARP NT-R5E3E 175 W photovoltaic modules. In addition, we used data that were outputted under various fault conditions as the training samples for the CMAC and used this model to conduct the module array fault diagnosis after completing the training. The results of the training process and simulations indicate that the method proposed in this study requires fewer number of training times compared to other methods. In addition to significantly increasing the accuracy rate of the fault diagnosis, this model features a short training duration because the training process only tunes the weights of the exited memory addresses. Therefore, the fault diagnosis is rapid, and the detection tolerance of the diagnosis system is enhanced.

This paper aims to present a smart, particle swarm optimization (PSO)-based, real time configuration strategy for a photovoltaic (PV) module array in the event of shadow cast on a PV module(s) and/or module failure as an effective approach to power generation efficiency elevation. At the first step, the respective maximum output power levels provided by a normal operating array at various levels of irradiation and module surface temperatures are measured and entered as references into a database. Subsequently, the maximum output power (MPP) level, tracked by a MPP tracker, is feedbacked for a comparison with an aforementioned reference as a way to tell whether there is either a shadow or a malfunction event on a PV module(s). Once an abnormal operation is detected, the presented smart configuration algorithm is performed to reconfigure the PV module array such that the array is operated at the global MPP as intended. Furthermore, by use of a PIC microcontroller that is a family of microcontrollers made by Microchip Technology for compact implementation, this study is experimentally validated as an effective approach to locating the global MPP at all events.

No abstract