4.7 Article

Solar Power Prediction Based on Satellite Measurements - A Graphical Learning Method for Tracking Cloud Motion

Journal

IEEE TRANSACTIONS ON POWER SYSTEMS
Volume 37, Issue 3, Pages 2335-2345

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRS.2021.3119338

Keywords

Satellites; Clouds; Extrapolation; Forecasting; Predictive models; Brightness temperature; Bidirectional control; Solar PV power prediction; deep learning; graphical learning; satellite images

Funding

  1. National Natural Science Foundation of China [52077062]

Ask authors/readers for more resources

This study proposes a graphical learning framework for intra-hour PV power prediction. By simulating cloud motion, a directed graph is generated to represent pixel values from historical images. A spatial-temporal graph neural network (GNN) is used to process the graph. Comparing with conventional deep-learning-based models, GNN is more flexible and able to handle dynamic regions of interest (ROIs), while reducing redundancy of image inputs and slightly improving prediction accuracy.
The stochastic cloud cover on photovoltaic (PV) panels affects the solar power outputs, producing high instability in the integrated power systems. It is an effective approach to track the cloud motion during short-term PV power forecasting based on data sources of satellite images. However, since temporal variations of these images are noisy and non-stationary, pixel-sensitive prediction methods are critically needed in order to seek a balance between the forecast precision and the huge computation burden due to a large image size. Hence, a graphical learning framework is proposed in this study for intra-hour PV power prediction. By simulating the cloud motion using bi-directional extrapolation, a directed graph is generated representing the pixel values from multiple frames of historical images. The nodes and edges in the graph denote the shapes and motion directions of the regions of interest (ROIs) in satellite images. A spatial-temporal graph neural network (GNN) is then proposed to deal with the graph. Comparing with conventional deep-learning-based models, GNN is more flexible for varying sizes of input, in order to be able to handle dynamic ROIs. Referring to the comparative studies, the proposed method greatly reduces the redundancy of image inputs without sacrificing the visual scope, and slightly improves the prediction accuracy.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available