Estimation of Daily Photovoltaic Power One Day Ahead With Hybrid Deep Learning and Machine Learning Models

Abstract

In this study, hybrid LSTM-SVM and hybrid LSTM-KNN models were developed to predict hourly PV power one day ahead. The performances of these hybrid models were compared with K-nearest neighbors (KNN), long short-term memory (LSTM), and support vector machine (SVM) models. The input data of these models were pressure, cloudiness, humidity, temperature, and solar intensity, while the output data was the daily photovoltaic (PV) power one day ahead. The performances of the models were evaluated using mean square error (MSE), root mean square error (RMSE), normalized root mean square error (NRMSE), and peak signal-to-noise ratio (PSNR). The prediction accuracies of hybrid LSTM-KNN, LSTM, KNN, hybrid LSTM-SVM, and SVM were 98.72%, 95.8%, 90.25%, 76.3%, and 48.87%, respectively. Hybrid LSTM-KNN predicted the daily PV power of the day ahead with higher accuracy than LSTM, KNN, SVM, and hybrid LSTM-SVM. The effect of input variables on output variables was examined with sensitivity analysis. Sensitivity analyses showed that the most important meteorological data affecting the daily PV power one day ahead was solar intensity with a rate of 95%.