Hybrid Deep Learning Models for Power Output Forecasting of Grid-Connected Solar PV Systems: A Monocrystalline and Polycrystalline PV Panel Analysis

Abstract

Increasing the use of renewable energy, particularly photovoltaic (PV) systems, is essential for mitigating climate change. However, the intermittent nature of PV power generation creates challenges in accurately forecasting and managing electricity supply within grid systems. This study proposes a hybrid deep learning (DL) model combining improved harmony search (IHS) optimization, convolutional neural networks (CNNs), and long short-term memory (LSTM) networks (IHS-CNN-LSTM) for forecasting the 15-min power output of grid-connected monocrystalline and polycrystalline PV systems. The model uses 14 input features obtained from numerical weather prediction (NWP) and local measurement data (LMD), with data sourced from the Public Photovoltaic Output Dataset (PVOD) covering June 2018 to June 2019 in Hebei Province, China. Comparative evaluations against genetic algorithm-based (GA-CNN-LSTM), differential evolution-based (DE-CNN-LSTM), and conventional CNN-LSTM models showed that the IHS-CNN-LSTM provided superior forecasting accuracy. Specifically, the proposed model achieved reductions in root mean square error (RMSE) of 3.7% for polycrystalline and 1.8% for monocrystalline PV systems, and reductions in mean absolute error (MAE) of 2.6% and 1.2%, respectively, along with high R2 values of 98% and 99%. The results confirm the effectiveness and accuracy of the proposed hybrid approach for PV power output forecasting.