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.

Deep convolutional long short-term memory for forecasting wind speed and direction

“…where • means hadamard product, and W means weight [4,11,17]. Deep fully connected-LSTM (DFC-LSTM), which is a multivariate type of LSTM that uses multiple LSTM layers, was applied in this study as it is easy to learn with the FC layer, and learns temporal features [18,19]. DFC-LSTM is composed of five LSTM layers and one FC layer.…”

“…CLSTM system combines CNN (convolutional neural network) and LSTM to improve the solving capability of sequential images. CLSTM is known for being able to learn representation from spatiotemporal features and learning processes by sequence to sequence that uses the input of the image [4,11,19]. Figure 5 shows the inner structure of CLSTM that uses convolutional structure in state-to-state and inputto-state transitions [4,11].…”

“…In CLSTM, the matrix product "•" of the LSTM is a substituted convolutional operation " * ". The equation of CLSTM is shown in [4,11,17,19].…”

Explainable Credit Card Fraud Detection with Image Conversion

“…By presenting a different perspective in time series data representation, the studies that transform time series into images have gained importance in recent years. These studies, which are used in many different application areas, were carried out for the following purposes: human activity recognition (Qin et al, 2020), day-ahead solar irradiation forecasting (Hong et al, 2020), traffic incident detection (Liu et al, 2020), single residential load forecasting (Estebsari et al, 2020), fault diagnosis of induction motors (Hsueh et al, 2020), and fraud detection (Zhang et al, 2018).…”

A Day-Ahead Irradiance Forecasting Strategy for the Integration of Photovoltaic Systems in Virtual Power Plants

“…The success of this alternative relies on the low computational burden it imposes on the forecast algorithm. On the other hand, ANNs have been extensively used for daily solar irradiance forecasts [28]- [33]. The forecast performance of an ANN relies on the learning algorithm along with the data available for the training process, the transfer function, the architecture, the nonlinear mapping capacity and the choice of input variables.…”