Artificial neural network‐based photovoltaic module temperature estimation for tropical climate of Malaysia and its impact on photovoltaic system energy yield

摘要: This article presents an artificial neural network (ANN)-based approach for predicting photovoltaic (PV) module temperature using meteorological variables. The proposed utilizes actual hourly records of various parameters, such as ambient Ta, solar irradiation G, relative humidity RH, and wind speed Ws input data were collected over 9?months in the year 2009 from a 92-kWp installed PV system Selangor, Malaysia. divided into two sets: training data, which are set 1849 (April–October) 578 (November–December) working test data. Four ANN models have been developed by different combination parameters inputs, and, each model, output is Tm. It was found that model all including RH gave most accurate results with correlation coefficient (r) 95.9%, 0.41, 0.1, 4.5% MBE, RMSE, MPE, respectively. To show superiority applicability compared conventional adopted Malaysia Energy Center another mathematical based on regression. With model's simplicity, can be used effective tool temperature, any type systems, remote or rural locations no direct measurement equipments. also will very useful studying performance estimating its energy output.