CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production.

• A CNN-LSTM hybrid architecture is suggested for predicting the power outcome of a photovoltaic plant over different look back and look forward time windows. • A multivariate dataset is derived from a photovoltaic plant located in Morocco. It comprise power production records, meteorological variables, in addition to the plant's consumed power. • The correlation between the look-back value and the forecasts precision of the model is discussed, and the well-suited value for each predicting model is given. This allow us to properly choose the appropriate parameters for each forecasting model. • The experimental findings reveal that the proposed architecture has an overall good effect on the accuracy of the forecasts, which ensures that the model robustness and resilience are high. Each of the models' training times is given in this work to deliver more insights for researchers. • The accuracy of the CNN-LSTM model is compared to other machine learning models (LR, KNN, DTR), as well as deep learning models (CNN, LSTM, MLP). Three error indexes (RMSE, MAE, and MAPE) were used to evaluate models' performance. Climate change is pushing an increasing number of nations to use green energy resources, particularly solar power as an applicable substitute to traditional power sources. However, photovoltaic power generation is highly weather-dependent, relying mostly on solar irradiation that is highly unstable, and unpredictable which makes power generation challenging. Accurate photovoltaic power predictions can substantially improve the operation of solar power systems. This is vital for supplying prime electricity to customers and ensuring the resilience of power plants' operation. This research is motivated by the recent adoption and advances in DL models and their successful use in the sector of energy. The suggested model merges two deep learning architectures, the long short-term memory (LSTM) and convolutional neural network (CNN). Using a real-world dataset from Rabat, Morocco, as a case study to illustrate the effectiveness of the suggested topology. According to error metrics, MAE, MAPE, and RMSE, the suggested architecture CNN-LSTM performance exceeds that of standard machine learning and single DL models in terms of prediction, precision, and stability. [ABSTRACT FROM AUTHOR]