Guardado en:
Detalles Bibliográficos
Autores principales: Li, Yuehan, Ren, Zhiyuan, Zhang, Tao, Cheng, Wenchi
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