Transfer Learning for Photovoltaic Power Forecasting with Long Short-Term Memory Neural Network
Siyu Zhou, Lin Zhou, Mingxuan Mao, Xinze Xi
Abstract
Data-driven modeling is one of the research hotspots of photovoltaic (PV) power prediction. However, for some newly built PV power plants, there are not enough historical data to train an accurate model. Therefore, constructing a forecasting model for the PV plants lacking historical data is an urgent problem to be solved. In this paper, we propose a method to transfer the knowledge obtained from historical solar irradiance data to the output prediction. Firstly, based on the historical solar irradiance data, the hyperparameters of the long short-term memory neural network (LSTM) are optimized and the weights in the neurons are pre-trained, then fine-tuning the deep transfer model with PV output data. In this way, knowledge can be transferred from solar irradiance data to PV output data. The experimental results show that the proposed method can significantly reduce the prediction error.