Multi-Site Photovoltaic Forecasting Exploiting Space-Time Convolutional Neural Network

Abstract

The accurate forecasting of photovoltaic (PV) power generation is critical for smart grids and the renewable energy market. In this paper, we propose a novel short-term PV forecasting technique called the space-time convolutional neural network (STCNN) that exploits the location information of multiple PV sites and historical PV generation data. The proposed structure is simple but effective for multi-site PV forecasting. In doing this, we propose a greedy adjoining algorithm to preprocess PV data into a space-time matrix that captures spatio-temporal correlation, which is learned by a convolutional neural network. Extensive experiments with multi-site PV generation from three typical states in the US (California, New York, and Alabama) show that the proposed STCNN outperforms the conventional methods by up to 33% and achieves fairly accurate PV forecasting, e.g., 4.6–5.3% of the mean absolute percentage error for a 6 h forecasting horizon. We also investigate the effect of PV sites aggregation for virtual power plants where errors from some sites can be compensated by other sites. The proposed STCNN shows substantial error reduction by up to 40% when multiple PV sites are aggregated.

Review on Spatio-Temporal Solar Forecasting Methods Driven by In Situ Measurements or Their Combination with Satellite and Numerical Weather Prediction (NWP) Estimates

“…There are also works implementing different deep learning models based on convolutional layers. For example, Jeong and Kim [107] proposed a Space-Time Convolutional Neural Network (STCNN) to forecast short-term PV power. The authors considered one year of data from 238, 67, and 103 PV sites from three different cities-the model was capable of obtaining indirectly the cloud cover and cloud movement without using more complex structures.…”

“…It is also interesting to note that several works that propose forecasting methods assume different data representations to capture the spatio-temporal component of solar variability. There are authors that use as input a sequence of irradiance maps [42], a matrix representation of the spatial-temporal relationship between the sites [107], a graph structure where the nodes are the measurements locations and the vertices are the distance [108] or the correlation relationship between them [34]. The works considered in this review study refer to spatially distributed ground sensors (e.g., [15,103,127]), complemented with gridded satellite estimates (e.g., [97]), or NWP forecasts (e.g., [29,32,65,99]), or a combination of these (e.g., [11,24,29]).…”

Spatio-temporal graph neural networks for multi-site PV power forecasting

“…This method uses an AR model and a group Lasso estimator to select relevant plants (nodes) for the prediction of each individual site (node). The second baseline for multi-site forecasting is the non-graph-based Space-time convolutional neural network (STCNN) [19]. It uses a greedyadjoining algorithm that rearranges the plants based on their geographical proximity, one by one, before applying 2D convolution layers as in image processing to produce spatiotemporal features.…”

“…Since passing clouds influence neighboring PV sites sequentially, the cloud cover and the cloud movements can be captured by considering spatial and temporal relations between PV stations. For that purpose, convolutional neural networks (CNN) have been proposed to extract the spatio-temporal correlations by stacking the PV signals as an image and reordering their position in the image based on their location [19], [20]. In addition, attention mechanisms have been also introduced to capture spatial correlations [21], [22].…”

Weather Data Mixing Models for Day-Ahead PV Forecasting in Small-Scale PV Plants

“…These WDCs may be deployed in various geographical regions within a certain distance. In [23], passing cloud issues were introduced and resolved based on the geographical region for multiplant PV forecasting. Wind speed is used to estimate the spatial correlation for modeling PV plants in new locations [24].…”