A combination of novel hybrid deep learning model and quantile regression for short-term deterministic and probabilistic PV maximum power forecasting

Abstract

Recently, the increasing penetration of renewable energy resources in power system, especially photovoltaic (PV) systems, has caused severe technical issues due to its randomness and dependency on primary sources. Therefore, precise output power forecast is vital for both system operators and PV system owners to improve grid stability and generation quality, respectively. This article proposes a novel hybrid deep learning model named EDSACL comprising four components, namely, convolutional neural network (CNN), long short-term memory (LSTM), self-attention mechanism (SAm), and residual learning (RL) strategy for short-term PV maximum power prediction with forecast horizon of 1, 2, and 4 h. This proposed model initially extracts spatial-temporal features of input data based on CNN and LSTM before using SAm to achieve hidden features of LSTM layers. RL strategy is employed to maintain the information flow entering the network. Besides, interval prediction is also implemented based on a combination of the EDSACL model and quantile regression with different probabilities. The forecast accuracy of the proposed model is validated based on two real-world data sets. The predicted results show the superiority of the proposed model over numerous predictive models; in particular, mean absolute percentage error values of the proposed hybrid model are under 6% in all case studies.