A Spatiotemporal Coupled Prediction Method for Multi-Energy Flows in Transportation Hubs Based on H3 Grid Representation and Heterogeneous Graph Attention–Transformer Networks

Weiyi Jiang; Liyan Zhang; Ze Zhou; Dongqi Zhao; Qihong Chen

doi:10.53941/aiet.2026.100012

Abstract

Large transportation hubs such as ports are becoming high-density agglomerations of energy consumption, in which electricity, hydrogen, and thermal/cooling energy flows are increasingly coupled with traffic activity, so their coordinated and low-carbon operation has become an important concern for both intelligent transportation and integrated energy systems. However, the multi-source data of such hubs differ greatly in spatial granularity and physical meaning, and traffic and energy loads are jointly coupled across space and time, which makes conventional methods that forecast a single system unable to characterize the overall dynamics. To address this problem, this paper proposes a heterogeneous data fusion and spatiotemporal coupled prediction method for multi-energy flows in transportation hubs. A unified representation framework based on H3 hexagonal grids is first designed, which aligns multi-source data onto a common spatial index and fuses theminto a standardized fourth-order tensor through area, length, and frequency spatial weights together with quantile truncation. On this basis, a hybrid model that couples a heterogeneous graph attention network (HetGAT) with a Transformer encoder is constructed, in which HetGAT models the heterogeneous spatial topology formed by four node types and five edge types, while the Transformer encoder extracts long-range temporal dependencies. An uncertainty-weighted dual-task head then jointly outputs traffic states and multi-energy loads. Experiments on a Ningbo-Zhoushan Port scenario built with the SUMO simulation platform show that the proposed method achieves R² values of 0.9763, 0.8088, 0.9644, and 0.9583 for traffic flow, electricity load, hydrogen consumption, and thermal/cooling load, respectively, while consistently outperforming single-system and homogeneous-graph baselines on the energy-side prediction tasks.

References

1.
Chen, S.; Wei, Z.; Gu, W.; et al. Energy System Transition and Transformation toward Carbon Neutrality: Multi-Energy Flow Coordination Technologies. Electr. Power Autom. Equip. 2021, 41, 3–12. https://doi.org/10.16081/j.epae.202109037. (In Chinese)
2.
Guo, Y.; Li, Y.; Zhou, S.; et al. Optimal Dispatch for Integrated Energy System Considering Data-Driven Dynamic Energy Hubs and Thermal Dynamics of Pipeline Networks. IEEE Trans. Smart Grid 2024, 15, 4537–4549. https://doi.org/10.1109/tsg.2024.3382740.
3.
Qian, T.; Liang, Z.; Shao, C.; et al. Unsupervised Learning for Efficiently Distributing EVs Charging Loads and Traffic Flows in Coupled Power and Transportation Systems. Appl. Energy 2025, 377, 124476. https://doi.org/10.1016/j.apenergy.2024.124476.
4.
Li, J.; Zhu, M.; Lu, Y.; et al. Review on Optimal Scheduling of Integrated Energy Systems. Power Syst. Technol. 2021, 45, 2256–2269. https://doi.org/10.13335/j.1000-3673.pst.2021.0020. (In Chinese)
5.
Geidl, M.; Koeppel, G.; Favre-Perrod, P.; et al. The Energy Hub—A Powerful Concept for Future Energy Systems. In Proceedings of the Third Annual Carnegie Mellon Conference on the Electricity Industry, Pittsburgh, PA, USA, 13–14 March 2007.
6.
Mohammadi, M.; Noorollahi, Y.; Mohammadi-Ivatloo, B.; et al. Energy Hub: From a Model to a Concept—A Review. Renew. Sustain. Energy Rev. 2017, 80, 1512–1527. https://doi.org/10.1016/j.rser.2017.07.030.
7.
Song, C.; Yang, H.; Cai, J.; et al. Multi-Energy Load Forecasting via Hierarchical Multi-Task Learning and Spatiotemporal Attention. Appl. Energy 2024, 373, 123788. https://doi.org/10.1016/j.apenergy.2024.123788.
8.
Su, Z.; Zheng, G.; Hu, M.; et al. Short-TermLoad Forecasting ofRegional Integrated Energy System Based on Spatio-Temporal Convolutional Graph Neural Network. Electr. Power Syst. Res. 2024, 232, 110427. https://doi.org/10.1016/j.epsr.2024.110427.
9.
Kim, H.J.; Kim, D.; Tak, H.; et al. Global-Local Attention-Enabled Multiple Decoder Transformer for Multi-Energy Load Forecasting in User-Level Integrated Energy System. Appl. Energy 2025, 396, 126255. https://doi.org/10.1016/j.apenergy.2025.126255.
10.
Yang, X.; Yun, J.; Zhou, S.; et al. A Spatiotemporal Distribution Prediction Model for Electric Vehicles Charging Load in Transportation Power Coupled Network. Sci. Rep. 2025, 15, 4022. https://doi.org/10.1038/s41598-025-88607-y.
11.
Scarselli, F.; Gori, M.; Tsoi, A.C.; et al. The Graph Neural Network Model. IEEE Trans. Neural Netw. 2009, 20, 61–80. https://doi.org/10.1109/tnn.2008.2005605.
12.
Jin, C.; Ruan, T.; Wu, D.; et al. HetGAT: A Heterogeneous Graph Attention Network for Freeway Traffic Speed Prediction. J. Ambient Intell. Humaniz. Comput. 2021. https://doi.org/10.1007/s12652-020-02807-0.
13.
Vaswani, A.; Shazeer, N.; Parmar, N.; et al. Attention Is All You Need. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017.
14.
Li, B.; Li, Z.; Chen, J.; et al. MAST-GNN: A Multimodal Adaptive Spatio-Temporal Graph Neural Network for Airspace Complexity Prediction. Transp. Res. Part C Emerg. Technol. 2024, 160, 104521. https://doi.org/10.1016/j.trc.2024.104521.
15.
Hou, D.; Gao, L.; Qian, Z.; et al. Vehicle Model Development and Integration for a Heterogeneous Traffic Flow Simulation Platform Based on SUMO Software. J. Tongji Univ. (Nat. Sci.) 2021, 49, 957–963. https://doi.org/10.11908/j.issn.0253-374x.21156. (In Chinese)
16.
Gallardo-Gomez, J.A.; Dıaz-del-Rıo, F.; Moron Fernandez, M.J.; et al. An Iterative Calibration and Validation Methodology for Large-Scale Traffic Simulations in SUMO. In Proceedings of the 40thACMSIGSIM International Conference on Principles of Advanced Discrete Simulation, Vienna, Austria, 24–26 June 2026; pp. 197–198. https://doi.org/10.1145/3806789.3810970.
17.
Khan, M.A.; Jang, J.H.; Iqbal, N.; et al. Enhancing Patient Rehabilitation Predictions with a Hybrid Anomaly Detection Model: Density-Based Clustering and Interquartile Range Methods. CAAI Trans. Intell. Technol. 2025, 10, 983–1006. https://doi.org/10.1049/cit2.70000.
18.
Wu, B.; Chen, Z.; Lu, X.; et al. A Hierarchical Model with Hexagon Grids for Multi-Objective Route Planning in Large-Scale Off-Road Environments. Int. J. Geogr. Inf. Sci. 2024, 38, 1388–1413. https://doi.org/10.1080/13658816.2024.2347319.
19.
Liu, R.; Wang, Z.; Han, T.; et al. HetGAT-LMI: Interpretable Heterogeneous Graph Attention Method for Predicting lncRNA–miRNA Interactions. J. Chem. Inf. Model. 2026, 66, 796–807. https://doi.org/10.1021/acs.jcim.5c02664.
20.
Velickovic, P.; Cucurull, G.; Casanova, A.; et al. Graph Attention Networks. In Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, 30 April–3 May 2018. https://doi.org/10.48550/arxiv.1710.10903.
21.
Ba, J.L.; Kiros, J.R.; Hinton, G.E. Layer Normalization. arXiv 2016, arXiv:1607.06450.
22.
He, K.; Zhang, X.; Ren, S.; et al. Deep Residual Learning for Image Recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. https://doi.org/10.1109/cvpr.2016.90.
23.
Kendall, A.; Gal, Y.; Cipolla, R. Multi-Task Learning Using Uncertainty toWeigh Losses for Scene Geometry and Semantics. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–22 June 2018; pp. 7482–7491. https://doi.org/10.1109/cvpr.2018.00781.

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us