Logo image
Back
AM2-STGNN: An attention guided spatiotemporal GraphSAGE framework for photovoltaic power forecasting from cloud images
Journal article   Open access   Peer reviewed

AM2-STGNN: An attention guided spatiotemporal GraphSAGE framework for photovoltaic power forecasting from cloud images

Md Rahad Islam Bhuiyan, Nur Mohammad Fahad, Abdul Hasib Siddique, Md Rafiqul Islam, Yakub Sebastian, Asif Karim, Kheng Cher Yeo and Sami Azam
Computers & electrical engineering, Vol.139(Part C), 111474
2026
DOI: https://doi.org/10.1016/j.compeleceng.2026.111474
pdf
Published5.51 MBDownloadView
Open Access CC BY V4.0

Abstract

Computer Science Computer Science, Hardware & Architecture Computer Science, Interdisciplinary Applications Engineering Engineering, Electrical & Electronic Science & Technology Technology
The nature of cloud cover over photovoltaic (PV) arrays causes significant variability in power generation, posing challenges for grid stability and energy management. Tracking cloud motion from sky images offers a promising solution for short-term PV forecasting; however, noisy images, unexpected cloud transitions, high computational burden, and temporal leakage in large datasets remain critical barriers. To address these challenges, we propose the multi-relational Attention-guided Mean-Max Spatiotemporal GraphSAGE Neural Network (AM2-STGNN). The framework begins by extracting spatiotemporal motion features from cloud images. As finding the connection between PV and Cloud motions is a challenge, the Apriori rule mining algorithm identifies interrelationships between cloud motion and spatiotemporal features, validating their correlation with high lift and confidence score. Subsequently, a multi-relational graph is constructed from the mined rules and spatiotemporal features for processing by the model. Within AM2-STGNN, the mean-max aggregation replaces the conventional Laplacian matrix, reducing time complexity. Experimental results demonstrate that the proposed model outperforms conventional machine learning, deep learning, and baseline Graph Neural Network (GNN) models, achieving superior R2 scores and surpassing the studies on the same dataset in short-term PV forecasting. In addition, temporal leakage during training is explicitly addressed through a three-stage temporal holdout evaluation. Finally, node-level interpretability analysis is illustrated to show the model's decision-making process.

Details

Metrics

1 Record Views
Logo image