Photovoltaic power forecasting based LSTM-Convolutional Network

• Published in: Energy (Oxford) 2019-12, Vol.189, p.116225, Article 116225
• Main Authors: Wang, Kejun, Qi, Xiaoxia, Liu, Hongda
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Convolutional neural network; Convolutional-LSTM network; Deep learning; Feature extraction; Long short-term memory; LSTM-Convolutional network; Machine learning; Neural networks; Performance indices; Photovoltaic power forecasting; Photovoltaics; Prediction models; Short term; Solar energy; Spatial data; Temporal variations
• ISSN: 0360-5442; 1873-6785
• DOI: 10.1016/j.energy.2019.116225

The volatile and intermittent nature of solar energy itself presents a significant challenge in integrating it into existing energy systems. Accurate photovoltaic power prediction plays an important role in solving this problem. With the development of deep learning, more and more scholars have applied the deep learning model to time series prediction and achieved very good results. In this paper, a hybrid deep learning model (LSTM-Convolutional Network) is proposed and applied to photovoltaic power prediction. In the proposed hybrid prediction model, the temporal features of the data are extracted first by the long-short term memory network, and then the spatial features of the data are extracted by the convolutional neural network model. In order to show the superior performance of the proposed hybrid prediction model, the prediction results of the hybrid model are compared with those of the single model (long-short term memory network, convolutional neural network) and the hybrid network (Convolutional-LSTM Network) model, and the results of eight error evaluation indexes are given. The results show that the hybrid prediction model has better prediction effect than the single prediction model, and the proposed hybrid model (extract the temporal characteristics of data first, and then extract the spatial characteristics of data) is better than Convolutional-LSTM Network (extract the spatial characteristics of data first, and then extract the temporal characteristics of data). •Hybrid deep learning neural network (LSTM-Convolutional Network) is used for PV power forecasting.•The performance of hybrid proposed network is better than single model.•The placement order of the hybrid model has a great influence on the accuracy of the prediction.•The better effect of deep learning network on PV power forecasting is demonstrated.