Day-ahead hourly photovoltaic power forecasting using attention-based CNN-LSTM neural network embedded with multiple relevant and target variables prediction pattern

Accurate forecasting of photovoltaic power plays a pivotal role in the integration, operation, and scheduling of smart grid systems. Notably, volatility and intermittence of solar energy are the primary constraints influencing the accuracy of photovoltaic power prediction. This work proposes, an attention-based long-term and short-term temporal neural network prediction model (ALSM) assembled using the convolutional neural network (CNN), long short-term memory neural network (LSTM), and attention mechanism under the multiple relevant and target variables prediction pattern (MRTPP). This is geared towards capturing the short-term and long-term temporal modes and achieving the day-ahead hourly photovoltaic power forecasting. The proposed method is verified by the historical data of the photovoltaic system downloaded from the DKASC website. Consequently, the results indicate that the forecasting accuracy using the MRTPP pattern is better than those common input-output prediction patterns. Moreover, the proposed ALSM model under the MRTPP pattern demonstrates more superiority compared to a few PV power forecasting methods including the statistical methods as well as artificial intelligence methods. Subsequently, different important parameters affecting the accuracy of forecasting range of the model are analyzed, and suggestions on memory lengths corresponding to the divergent prediction range are provided.