Graph-based reinforcement learning for software-defined networking traffic engineering
Guardado en:
| Publicado en: | Journal of King Saud University. Computer and Information Sciences vol. 37, no. 6 (Aug 2025), p. 119 |
|---|---|
| Autor principal: | |
| Otros Autores: | , , |
| Publicado: |
Springer Nature B.V.
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3257123389 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 1319-1578 | ||
| 024 | 7 | |a 10.1007/s44443-025-00133-z |2 doi | |
| 035 | |a 3257123389 | ||
| 045 | 2 | |b d20250801 |b d20250831 | |
| 100 | 1 | |a Lu, Jingwen |u Chongqing University, School of Microelectronics and Communication Engineering, Chongqing, China (GRID:grid.190737.b) (ISNI:0000 0001 0154 0904) | |
| 245 | 1 | |a Graph-based reinforcement learning for software-defined networking traffic engineering | |
| 260 | |b Springer Nature B.V. |c Aug 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a With the continuous expansion of global Internet infrastructure, wide area networks play a crucial role in transmitting traffic between multiple data centers and users worldwide. However, efficient traffic management has become a core challenge due to the high costs of building and maintaining these networks. Traditional traffic engineering methods based on linear programming achieve optimal solutions but suffer from exponential computational complexity growth with network size, making them impractical for real-time applications in large-scale networks. Recent machine learning approaches show promise but still face fundamental limitations in handling complex network constraints and maintaining performance across different network scales. This paper proposes GRL-TE (Graph-based Reinforcement Learning for Traffic Engineering), a novel framework that achieves near-optimal performance while maintaining computational efficiency across diverse network scales. GRL-TE introduces three key innovations: (1) TopoFlowNet, a graph neural network architecture that models WANs as bipartite graphs with edge nodes representing physical links and path nodes representing candidate paths, enabling efficient bidirectional information propagation through GINConv layers while MLP modules handle collaborative relationships among paths serving the same demand; (2) A one-step A2C mechanism specifically designed for TE with immediate reward structure, eliminating the need for future state estimation and significantly simplifying training; (3) Integration of ADMM as a post-processing step to iteratively reduce constraint violations while improving solution quality. Extensive experiments on six real-world WAN topologies ranging from 12 to 1,739 nodes demonstrate that GRL-TE achieves an overall average demand satisfaction rate of 89.36%, outperforming state-of-the-art learning-based methods (Teal: 82.04%, Figret: 82.20%) and the clustering-based NCFlow (76.48%), while providing 3-4 orders of magnitude speedup compared to LP solvers on large-scale networks. The framework maintains robust performance under link failures and meets real-time scheduling requirements for production deployment. | |
| 653 | |a Mathematical programming | ||
| 653 | |a Software | ||
| 653 | |a Linear programming | ||
| 653 | |a Wide area networks | ||
| 653 | |a Network topologies | ||
| 653 | |a Clustering | ||
| 653 | |a Graph neural networks | ||
| 653 | |a Neural networks | ||
| 653 | |a Real time | ||
| 653 | |a Optimization | ||
| 653 | |a Production scheduling | ||
| 653 | |a Traffic engineering | ||
| 653 | |a Traffic control | ||
| 653 | |a Topology | ||
| 653 | |a Nodes | ||
| 653 | |a State estimation | ||
| 653 | |a Complexity | ||
| 653 | |a Machine learning | ||
| 653 | |a Graphical representations | ||
| 653 | |a Fault tolerance | ||
| 653 | |a Constraints | ||
| 700 | 1 | |a Tang, Chaowei |u Chongqing University, School of Microelectronics and Communication Engineering, Chongqing, China (GRID:grid.190737.b) (ISNI:0000 0001 0154 0904) | |
| 700 | 1 | |a Ma, Wenyu |u Chongqing University, School of Microelectronics and Communication Engineering, Chongqing, China (GRID:grid.190737.b) (ISNI:0000 0001 0154 0904) | |
| 700 | 1 | |a Xing, Wenjuan |u Chongqing University, School of Microelectronics and Communication Engineering, Chongqing, China (GRID:grid.190737.b) (ISNI:0000 0001 0154 0904); Beijing Research Institute, China Telecom Corporation Limited, Beijing, China (GRID:grid.506877.b) | |
| 773 | 0 | |t Journal of King Saud University. Computer and Information Sciences |g vol. 37, no. 6 (Aug 2025), p. 119 | |
| 786 | 0 | |d ProQuest |t Computer Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3257123389/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/3257123389/fulltext/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3257123389/fulltextPDF/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |