Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2605.10070 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917479861714944 |
|---|---|
| author | Li, Yuehan Ren, Zhiyuan Zhang, Tao Cheng, Wenchi |
| author_facet | Li, Yuehan Ren, Zhiyuan Zhang, Tao Cheng, Wenchi |
| contents | Emergency communications networks require in-network intelligence for timely traffic handling under dynamic demands and runtime constraints. In these environments, packets may need different inference behaviors, and conventional model replacement via control-plane updates is too slow for responsive operation. We propose an in-network artificial computing framework with lightweight model-switching, where multiple Binary Neural Network (BNN) models are kept resident within a shared execution framework. Packet metadata selects the active model at packet granularity with O(1) selection cost. A fixed 1024-byte payload is aligned with x86 AVX-512, enabling efficient memory access. The framework is realized on an eBPF/XDP + AF_XDP stack. Experimental results show that the system sustains 1.894 Mpps with a 0.528 us inference latency, while model selection adds only 0.005 us. Our results demonstrate that different resident models induce distinct packet-processing behaviors, that scaling to 16 slots preserves low switching overhead, and that online model switching completes without wrong-verdict packets. These results show the practicality of lightweight in-network artificial computing on commodity hardware. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10070 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | In-Network Artificial Computing Enhanced Light Model-Switching for Emergency Communications Networks Li, Yuehan Ren, Zhiyuan Zhang, Tao Cheng, Wenchi Networking and Internet Architecture Emergency communications networks require in-network intelligence for timely traffic handling under dynamic demands and runtime constraints. In these environments, packets may need different inference behaviors, and conventional model replacement via control-plane updates is too slow for responsive operation. We propose an in-network artificial computing framework with lightweight model-switching, where multiple Binary Neural Network (BNN) models are kept resident within a shared execution framework. Packet metadata selects the active model at packet granularity with O(1) selection cost. A fixed 1024-byte payload is aligned with x86 AVX-512, enabling efficient memory access. The framework is realized on an eBPF/XDP + AF_XDP stack. Experimental results show that the system sustains 1.894 Mpps with a 0.528 us inference latency, while model selection adds only 0.005 us. Our results demonstrate that different resident models induce distinct packet-processing behaviors, that scaling to 16 slots preserves low switching overhead, and that online model switching completes without wrong-verdict packets. These results show the practicality of lightweight in-network artificial computing on commodity hardware. |
| title | In-Network Artificial Computing Enhanced Light Model-Switching for Emergency Communications Networks |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2605.10070 |