LSTM-CNN Tabanlı Derin Öğrenme Tekniği Kullanılarak Küresel Yatay Güneş Radyasyonu ile Hava Durumu Parametrelerinin Tahmini ve Analizi

Abstract

Predicting global horizontal solar irradiance (GHSI) as well as important climate parameters plays an important role in energy management and resource planning of photovoltaic panels. To further benefit from solar energy, it is necessary to obtain information regarding future values by frequently analyzing and predicting such time series parameter data. Hence, predicting long-term solar irradiance data is a challenging task. For these purposes, in this work, a hybrid method, with modeling of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) deep neural networks, is proposed to ensure the most accurate prediction of such data. The GHSI as well as temperature, relative humidity, and wind speed data obtained in the Jordan valley are used in the forecasting methodology. In the CNN block of the proposed deep architecture, the input parameters are passed through the convolution, pooling, and flattening layers, and the outputs are forwarded to the LSTM data input. With this method, it is aimed to make more effective and accurate estimations. The proposed method has been compared according to Root Mean Square Error (RMSE), Mean Absolute Deviation Error (MADE), and Mean Absolute Percentage Error (MAPE) error performance criteria in order to reveal the difference from other methods. The proposed method produces superior results compared to other algorithms, especially in GHSI estimation.