Artificial neural network based temperature prediction and its impact on solar cell

Along with many other parameters, the overall efficiency of pv module depends on cell temperature, which, in turn, relies on various environmental factors. Environmental conditions such as solar irradiance, wind speed, and wind direction and most importantly, the temperature around the cell affects cell´s performance. Although weather prediction and meteorology is a very complex and imprecise science, recent research activities with artificial neural network (ANN) have shown that it has powerful pattern classification and pattern recognition capabilities which can be used as a tool to get a reasonable accurate prediction of weather patterns. This paper presents an application of Artificial Neural Network (ANN) to estimate the Daily Mean, Maximum and Minimum temperature of Dhaka, capital of Bangladesh. The trend of temperature all over the Bangladesh has been studied over last sixty years. An Artificial Neural Network model based on Multilayer Perceptron concept has been developed and trained using backpropagation learning algorithm for prediction. The model was tested and trained using ten years of temperature data of Dhaka Station, from Bangladesh Meteorological Department (BMD). The accuracy of the model was calculated on basis of Mean Absolute Percentage Error. The result shows that Neural Network can be used for temperature prediction successfully.