Transformer-Based Multipath Congestion Control: A Decoupled Approach for Wireless Uplinks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914369906933760 |
|---|---|
| author | Zhang, Zongyuan Duan, Tianyang Wang, Liang Fang, Zihan Lin, Zheng Lu, Yijun Wu, Jiening Du, Xia Yang, Miao Chen, Zhe Cui, Heming Luo, Jun |
| author_facet | Zhang, Zongyuan Duan, Tianyang Wang, Liang Fang, Zihan Lin, Zheng Lu, Yijun Wu, Jiening Du, Xia Yang, Miao Chen, Zhe Cui, Heming Luo, Jun |
| contents | The proliferation of artificial intelligence applications on edge devices necessitates efficient transport protocols that leverage multi-homed connectivity across heterogeneous networks. While Multipath TCP enables bandwidth aggregation, its in-kernel congestion control mechanisms lack the programmability and flexibility needed for achieving efficient transmission. Additionally, inherent measurement noise renders network state partially observable, challenging data-driven approaches like deep reinforcement learning (DRL). To address these challenges, we propose a Transformer-based Congestion Control Optimization (TCCO) framework for multipath transport. TCCO employs a decoupled architecture that offloads control decisions to an external decision engine via a lightweight in-kernel client and user-space proxy, enabling edge devices to leverage external computational resources while maintaining TCP/IP compatibility. The Transformer-based DRL agent in the external decision engine uses self-attention to capture temporal dependencies, filter noise, and coordinate control across subflows through a unified policy. Extensive evaluation on both simulated and real dual-band Wi-Fi testbeds demonstrates that TCCO achieves superior adaptability and performance than state-of-the-art baselines, validating the feasibility and effectiveness of TCCO for wireless networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04550 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Transformer-Based Multipath Congestion Control: A Decoupled Approach for Wireless Uplinks Zhang, Zongyuan Duan, Tianyang Wang, Liang Fang, Zihan Lin, Zheng Lu, Yijun Wu, Jiening Du, Xia Yang, Miao Chen, Zhe Cui, Heming Luo, Jun Networking and Internet Architecture The proliferation of artificial intelligence applications on edge devices necessitates efficient transport protocols that leverage multi-homed connectivity across heterogeneous networks. While Multipath TCP enables bandwidth aggregation, its in-kernel congestion control mechanisms lack the programmability and flexibility needed for achieving efficient transmission. Additionally, inherent measurement noise renders network state partially observable, challenging data-driven approaches like deep reinforcement learning (DRL). To address these challenges, we propose a Transformer-based Congestion Control Optimization (TCCO) framework for multipath transport. TCCO employs a decoupled architecture that offloads control decisions to an external decision engine via a lightweight in-kernel client and user-space proxy, enabling edge devices to leverage external computational resources while maintaining TCP/IP compatibility. The Transformer-based DRL agent in the external decision engine uses self-attention to capture temporal dependencies, filter noise, and coordinate control across subflows through a unified policy. Extensive evaluation on both simulated and real dual-band Wi-Fi testbeds demonstrates that TCCO achieves superior adaptability and performance than state-of-the-art baselines, validating the feasibility and effectiveness of TCCO for wireless networks. |
| title | Transformer-Based Multipath Congestion Control: A Decoupled Approach for Wireless Uplinks |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2603.04550 |