Day-Ahead Solar Irradiation Forecasting Utilizing Gramian Angular Field and Convolutional Long Short-Term Memory

Abstract

The operations of power systems are becoming more challenging on account of the high penetration of renewable power generation, including photovoltaic systems. One method for improving the power system operation involves making accurate forecasts of day-ahead solar irradiation, enabling operators to minimize uncertainty in managing the balance between generation and load. To overcome the limitations of Long Short-term Memory (LSTM) in a one-dimensional forecasting problem, this work proposes a novel method in forecasting solar irradiation by encoding time-series data into images using the Gramian Angular Field and the Convolutional LSTM (ConvLSTM) network. The pre-processed data become a five-dimensional input tensor that is perfectly suitable for ConvLSTM. The ConvLSTM network uses convolution operations in its input-to-state transition and state-to-state transition. The network thus enables time-series forecasting by a feature-rich approach, which ultimately provides competitive forecasting performance despite the use of a small dataset. The proposed method was evaluated in day-ahead solar irradiation forecasting using a univariate dataset of Global Horizontal Irradiation (GHI) data from Fuhai in Taiwan. The proposed method was resampled using 5×2-fold cross-validation, and assessed using the Wilcoxon signed-rank test to determine the statistical significance of the result. It outperformed benchmark methods such as Autoregressive Integrated Moving Average (ARIMA), Convolutional Neural Network cascaded with Long Short-term Memory (CNN-LSTM), and LSTM cascaded with a fully-connected (FC) network.