UniPhy Technologies← Innovation testbeds
O-RAN slicing / 2026 preprint

MORPH:
learn PRB handling across environments.

Alireza Ebrahimi Dorcheh · Tolunay Seyfi · Ryan Barker · Fatemeh Afghah

A slice-priority demonstration that combines OAI measurements, empirical MCS behavior, and a PHY-fidelity simulator so the same policy can be tested across practical, simulated, and hybrid environments.

Testbed focus

Replay one network under three priorities.

Switch between Smart Factory, Stadium, and Smart City demand profiles, then compare practical, simulated, and hybrid agents on SLA, latency, throughput, and connected devices.

Technical significance

Smart Factory / URLLC-centric

The hybrid agent achieves the lowest average URLLC latency, stays below the reported 400 ms SLA threshold, and reduces SLA violations, with a tradeoff in eMBB throughput.

Stadium / eMBB-centric

The hybrid agent reaches the highest average eMBB throughput with near-zero SLA violations and the highest satisfaction in the reported scenario.

Smart City / mMTC-centric

The hybrid agent supports the largest number of connected IoT devices by prioritizing connectivity while limiting the effect on URLLC and eMBB performance.

MORPH O-RAN slicing framework
Measurement-grounded O-RAN slicing framework.
MORPH evaluation results
Average latency, throughput, and mMTC service performance across scenarios.

Figures are cropped from the submitted paper to show the system and the most relevant reported results.

Back to demos ↗