EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Physics-Informed Neural Network for Graph-Based Network Traffic Prediction

Yuhao Zhang, Yuhao Feng, Suyu Zhang, Peifeng Liang, Wei Guan

Electronics · 24.07.2026 · 15 (15) · 3270

DOI: 10.3390/electronics15153270 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 24.07.2026. Verfasst von Yuhao Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of the Jiangsu Higher Education Institutions of China, Changzhou Science and Technology Plan Projects, Jiangsu Province Undergraduate Cybersecurity Innovation, Entrepreneurship and Social Practice Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate network traffic prediction is important for the autonomy, resilience and resource orchestration of 6G and AI-native communication infrastructures, while also supporting green networking and digital twin network applications. However, existing data-driven prediction models face several limitations: over-reliance on massive labeled data, physically implausible predictions, black-box non-interpretability and over-parameterization that impairs edge deployment. To address these issues, this paper proposes a Physics-Informed Network Traffic Prediction (PINTP) framework for graph topology network traffic prediction, which formalizes network traffic evolution as Graph-based Advection–Diffusion–Reaction (ADR) equations and embeds physical regularization into the neural architecture. The framework adopts a hybrid differentiation paradigm unifying automatic differentiation for temporal dynamics and spectral graph theory-derived operators for discrete spatial topologies, and designs a physics-constrained composite loss function with data-driven collocation to balance data fidelity and physical consistency. Experiments are conducted in two complementary settings: a 100-node synthetic random-graph benchmark that evaluates the full graph-topological formulation, and a topology-unavailable real-world telemetry proxy based on Alibaba Cluster Trace v2018 for evaluating sparse-label physics-informed temporal regularization. Comparative analysis with mainstream baselines, including Multilayer Perceptron (MLP), Spatio-Temporal Graph Convolutional Network (STGCN), Graph WaveNet, Transformer, Temporal Convolutional Network (TCN), and XGBoost, shows that the proposed PINTP/PINN implementation achieves a test R2 of 0.898 and MSE of 0.000723 on the 100-node synthetic graph benchmark, close to the strongest Transformer result (R2=0.900, MSE = 0.000710), while using substantially fewer trainable parameters. PINTP/PINN also outperforms Graph WaveNet, STGCN and TCN in this setting, indicating that physics-informed regularization can remain competitive as graph size increases. On the Alibaba proxy task, PINTP/PINN achieves the strongest result among the evaluated models with a test R2 of 0.963. In an independent Alibaba ablation protocol, physical regularization (e.g., λ=10.0) reduces the mean squared error by 89.15% compared with pure data-driven models and helps mitigate overfitting. This work presents a systematic PINTP framework for graph topology network traffic prediction, achieving competitive prediction accuracy with high parameter efficiency and a degree of physical interpretability. It helps address several limitations of traditional data-driven models, indicates potential for future deployment-oriented studies on real-time network management and resource-constrained edge analytics, and provides an interpretable modeling route for physics-informed network analytics in next-generation communication systems.

Förderung

  • Natural Science Foundation of the Jiangsu Higher Education Institutions of China
  • Changzhou Science and Technology Plan Projects
  • Jiangsu Province Undergraduate Cybersecurity Innovation, Entrepreneurship and Social Practice Program

Zitieren

APA

Zhang, Y., Feng, Y., Zhang, S., Liang, P., & Guan, W. (2026). A Physics-Informed Neural Network for Graph-Based Network Traffic Prediction. Electronics, 15(15), 3270. https://doi.org/10.3390/electronics15153270

Vancouver

Zhang Y, Feng Y, Zhang S, Liang P, Guan W. A Physics-Informed Neural Network for Graph-Based Network Traffic Prediction. Electronics. 2026;15(15):3270. doi:10.3390/electronics15153270

BibTeX
@article{Zhang2026,
  author = {Zhang, Yuhao and Feng, Yuhao and Zhang, Suyu and Liang, Peifeng and Guan, Wei},
  title = {A Physics-Informed Neural Network for Graph-Based Network Traffic Prediction},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {15},
  pages = {3270},
  doi = {10.3390/electronics15153270}
}
Kostenlos starten →