UNICORN: URLLC Network Traffic Classification and OOD Detection for O-RAN

The promise of Ultra-Reliable Low Latency Communication (URLLC) will transform verticals such as virtual reality, telesurgery, and tactile Internet among others. There are subtle differences in resource requirements between applications within URLLC category that may allow the network to perform fine-tuned resource allocation to satisfy stringent latency/jitter constraints. This paper proposes UNICORN, a neural network (NN)-based approach that aims to classify previously seen as well as detect new/emerging URLLC applications at the near real-time Radio access network Intelligence Controller (RIC), without any interactions from the application layer or from the user equipment (UE). The core approach leverages standardized key performance indicators (KPIs) exposed by an Open Radio Access Network (O-RAN) compliant cellular network stack. UNICORN is evaluated on a real-world dataset collected from a commercial cellular network using six URLLC smartphone applications with network KPIs obtained from a full-stack O-RAN implementation on the NSF Colosseum emulator. Results reveal classification accuracy of >96% with upto 88% true positive out-of-distribution (OOD) detection rate, and per class false positive rate as low as 8%.