Forecasting Generating Power of Sun Tracking PV Plant using Long-Short Term Memory Neural Network Model: A case study in Ninh Thuan - Vietnam

Abstract

This article provides a reliable very short-term forecast (nowcasting) of the power generation capacity of PV power plants. Specifically, in this article, a deep learning method utilized the long-short term memory model (LSTM) to predict PV system’s power generation has been proposed using the Python programming language with TensorFlow library. In addition, other deep learning models such as recurrent neural network (RNN) and convolution neural network (CNN) are also used and compared with LSTM to demonstrate the advantages of LSTM compared to those models. To verify, the article used actual data collected from Ninh Thuan solar power plant - Vietnam. The results show the prediction ability with promising quality of the LSTM model.