Authors: Alan Subedi, Avhishek Biswas, Apala Pramanik, Amlan Balabantaray, Mikhail Titov, Santosh Pitla, Ozgur Kilic, Mehmet C. Vuran
Organizations: School of Computing, University of Nebraska–Lincoln, Lincoln, NE, USA · Department of Biological Systems Engineering, University of Nebraska–Lincoln, Lincoln, NE 68583, USA · Brookhaven National Laboratory, Upton, NY 11973, USA
Modern sensing systems generate large volumes of heterogeneous data streams from multiple sensor modalities, increasing reliance on datacenters for computation, artificial intelligence/superintelligence (AI/SI) inference, and AI/SI training. Each sensor stream may have different network and compute requirements depending on its type and data volume. However, current wireless systems typically allocate resources at the device level, leading to contention among co-located sensor streams, where bulk data transfers may starve latency-critical telemetry. To this end, this paper introduces Sensor Slicing (SL). SL provides deterministic, medium access control (MAC)-level isolation for individual sensors within a single user equipment (UE) in open radio access networks (O-RAN). Using agentic coding techniques, SL is implemented in two O-RAN-compliant packages, reducing development time by 400 times (2 h 40 min [OCUDU] vs. 6.5 weeks [OAI]), 228-fold fewer human prompts (4 vs. 913), and less than half the tokens (0.64B vs. 1.43B). An associated end-to-end framework, SLED, is implemented to establish per-sensor radio and network isolation across edge, campus, and remote high-performance computing (HPC) tiers. Over-the-air wireless experiments demonstrate that while conventional network slicing causes critical delays to increase more than 2,300-fold under high traffic load, SLED maintains stable latency. Scaling evaluations on the two RAN stacks show that throughput remains within 0.9% and 1.4% of expected allocations even as the number of sensor slices increases. The results demonstrate that SLED preserves latency-critical telemetry while effectively utilizing resources across the sensor-to-HPC pipeline. The SLED software and evaluation datasets are publicly available at https://github.com/UNL-CPN-Lab/SLED-Sensor-SLicing-from-Edge-to-Datacenter.
Figures & tables
Fig. 1 : The field-to-HPC pipeline. A sensor-sliced private network couples heterogeneous sensor streams with distributed compute tiers.
Capability
srsRAN [ 15 ]
OCUDU [ 8 ]
OAI [ 7 ]
ORANSlice [ 6 ]
Sensor Slicing
5G Std. [ 18 ]
Network Slicing
✓
✓
✓
✓
✓
✓
Sensor Slicing (SL)
Downlink
✗
✗
✗
✓
✓
✓
Uplink
✗
✗
✗
✗
✓
✓
Deterministic isolation
✗
✗
✗
✗
✓
✗
Max. # slices
–
–
–
2
7
8
TABLE I : Comparison of network and sensor slicing capabilities and supported traffic in State-of-the-Art vs. Sensor Slicing.
Fig. 2 : Sensor Slicing algorithm with credit-based DL slot allocation (top) and deterministic UL slot ownership (bottom).
Fig. 3 : Agentic RAN development harness with the automated modify-build-simulate loop on HPC and human-orchestrated OTA validation on a live 5G/6G RAN testbed.
Activity
Prompts
Input (M) ∗
Output (M)
Total (M)
Share (%)
OAI
Debugging
386
997.0
3.79
1,000.7
70.1
Implementation
39
137.2
0.27
137.4
9.6
Testing
77
106.7
0.17
106.9
7.5
Building
62
78.5
0.20
78.7
5.5
Infrastructure
74
52.1
0.18
52.3
3.7
Learning
199
46.9
0.34
47.2
3.3
TABLE II : Agent token consumption by development activity.
Fig. 4 : OAI file modifications
Fig. 5 : Indoor OTA Testbed (top view)
Slice
Application
Transport
Packet
Data Rate
5QI [ 18 ]
Protocol
Size
eMBB-VA
Video Analytics (JPEG)
UDP
1,400 B
15 Mbps
2
eMBB-BT
Bulk Transfer
TCP
1,400 B
50 Mbps
9
eMBB-CL
Continual Learning
UDP
1,400 B
18 Mbps
4
eMBB-IQ
Raw Radio (IQ) Streaming
TCP
360 KB
25 Mbps
9
eMBB-LD
LiDAR Transfer
UDP
1,400 B
8 Mbps
3
TABLE III : Slice workload characteristics.
Fig. 6 : Per-slice OTA uplink (left) and downlink (right) throughput with 95% confidence intervals.
Fig. 7 : Per-slice allocation (Alc, %) and achieved UL/DL throughput (Mbps) for a UE with N={3,5,7} SLs.
Fig. 8 : Two-slice downlink latency and delivery ratio for Sensor Slicing vs. State-of-the-Art (DL, 70/30, 52 fps).
Fig. 9 : Latency of each application under network slicing (NS) and sensor slicing (SL) as the eMBB-BT load increases.
Fig. 10 : Compute placement impact on eMBB-VA latency, frame rate, and throughput.
Slice
Compute
Required
Measured
Delivered
UL
Location
(%)
(Mbps)
eMBB-CL
Campus HPC
60 fps
60.3 fps
99.9
18.1
eMBB-IQ
LCF
0% loss
0% loss
100
25.6
URLLC-RT
Edge
≤ 30 ms
29 ms
100
0.4
TABLE IV : HPC-grade workloads at a 40/50/10 allocation.
Next-generation (NextG) cellular networks are designed to support emerging applications with diverse data rate and latency requirements, such as immersive multimedia services and large-scale Internet of Things deployments. A key enabling mechanism is radio access network (RAN) slicing, which dynamically partitions radio resources into virtual resource blocks to efficiently serve heterogeneous traffic classes, including enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC). In this paper, we study the impact of adversarial attacks on AI-driven RAN slicing decisions, where a budget-constrained adversary selectively jams slice transmissions to bias deep reinforcement learning (DRL)-based resource allocation, and quantify the resulting service level agreement (SLA) violations and post-attack recovery behavior. Our results indicate that budget-constrained adversarial jamming can induce severe and slice-dependent steady-state SLA violations. Moreover, the DRL agent's reward converges toward the clean baseline only after a non-negligible recovery period.
Deemah H. Tashman, Soumaya Cherkaoui
Department of Computer and Software Engineering, Polytechnique Montreal, Montreal, Canada
LLM inference is increasingly deployed as a core service for enterprise and interactive applications, but sovereignty, compliance, latency and resource-locality requirements can limit the suitability of centralised cloud deployments. Telco operators offer geographically distributed compute and network infrastructure for addressing these constraints. However, existing LLM serving frameworks are designed for tightly coupled data centres and provide limited support for coordinating geographically distributed and heterogeneous resources. We present InferSlice, a reference architecture for Service-Level Objective (SLO)-driven LLM inference over a telco infrastructure, integrating network slicing, GPU partitioning, elastic serving and observability. Led by BT in collaboration with the University of Bristol and NVIDIA, and realised on the JOINER UK national-scale wide-area network (WAN), InferSlice is evaluated on service differentiation across tiers, elastic scale-out, client-edge bandwidth as a bottleneck, and the reach of tensor, pipeline, data parallelism, and prefill/decode disaggregation over the WAN. Our results show that, on a general-purpose telco network, tiers yield distinct latency-throughput regimes, and weight streaming shortens scale-out time. Replication is placement-insensitive but memory-bound; pipeline parallelism tolerates near- and mid-cross-site hops, while tensor parallelism and disaggregation fail beyond a single subnet hop. We share practical insights from operating SLO-driven inference on a telco network, lessons learned and open questions, and hope to encourage further research on distributed and heterogeneous LLM inference systems.
Juan Parra-Ullauri, Anthony Chiu, Hari Madhukumar +6
Semantic sensing (SemS) acquires task-relevant information rather than reconstructing complete physical information. Existing SemS formulations typically operate open loop: sensing configurations and observation schedules are fixed before inference and cannot respond to evolving task-level evidence. We propose Agentic SemS, a closed-loop framework for AI-enabled radio access networks (AI-RANs) that controls sensing within a communication-feasible profile set. A profile-conditioned causal Transformer updates the semantic belief from streaming observations, while key-value caching enables efficient state updates across profile changes without repeatedly processing the complete history. A semantic utility network estimates the task-level benefit of acquiring the next observation block under each feasible profile after accounting for sensing cost. The resulting continuation utilities jointly support next-profile selection and semantic early exit, adapting sensing configuration and duration to evolving evidence. The expected semantic gain is further related to conditional mutual information, providing a value-of-information interpretation of continued online sensing. Experiments on Widar3.0 with six emulated sensing profiles show that, in comparison with full-sequence High, the resource-efficient Agentic setting reduces normalized cumulative sensing cost by 25.33% while achieving 85.79% Macro-F1. At the same utility checkpoint, semantic early exit provides a further 12.35% cost reduction over adaptive sensing without early exit, with a 0.97-percentage-point Macro-F1 decrease.
Zhongqin Wang, Xiaoqi Zhang, Nan Yang +3
Global Big Data Technologies Centre, University of Technology Sydney, Sydney, NSW 2007, Australia · School of Science, Engineering and Digital Technologies, University of Southern Queensland, Toowoomba, QLD 4350, Australia · School of Electrical and Computer Engineering, The University of Sydney, Sydney, NSW 2006, Australia