AI
SLED: Sensor SLicing from Edge to Datacenter
Publication: cs.AI updates on arXiv.org
Author: Alan Subedi, Avhishek Biswas, Apala Pramanik, Amlan Balabantaray, Mikhail Titov, Santosh Pitla, Ozgur Kilic, Mehmet C. Vuran
Source published: 18/11/2026, 05:00:00 UTC
Briefing created: 18/11/2026, 05:44:16 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 18/11/2026, 05:03:25 UTC.
Briefings
This briefing reports on the SLED framework, a new system designed to isolate and manage sensor data streams at the MAC level within O-RAN networks. Developed by the UNL-CPN-Lab, SLED enables deterministic resource allocation across edge, campus, and remote HPC tiers, significantly reducing development time and human prompts compared to existing methods. Experimental results show that while conventional network slicing causes latency to increase over 2,300-fold under high traffic, SLED maintains stable latency and throughput remains within 1% of expected allocations even with many sensor slices.
Key points
- SLED is a software framework implementing Sensor SLicing (SL) in two O-RAN-compliant packages, reducing development time by 400 times and human prompts by 228-fold compared to traditional approaches.
- Over-the-air wireless experiments demonstrate that SLED maintains stable latency under high traffic load, whereas conventional network slicing causes critical delays to increase more than 2,300-fold.
Context
Modern sensing systems generate large volumes of heterogeneous data streams requiring AI/SI inference and training. Current wireless systems allocate resources at the device level, causing contention among co-located sensor streams. SLED addresses this by providing MAC-level isolation for individual sensors across edge, campus, and remote HPC tiers.
Limitations
Scaling evaluations were conducted on two specific RAN stacks. The study relies on experimental data from over-the-air wireless tests and does not include long-term operational data or field deployment results. The framework is currently in development and evaluation phases, with no published production metrics.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 18/11/2026, 05:44:16 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeic6suhjgjvjuiou365u7mjq4ccuppvavt2a64dji2wa26l3umjm2y