Real-Time Streaming Telemetry Based Detection and Mitigation of OOK and Power Interference in Multi-User OSaaS Networks

TL;DR

This paper addresses the vulnerability of multi-user OSaaS networks to rogue OOK signals and power interference. It proposes a real-time framework combining fine-grained ingress power measurements from ROADM OCM with streaming telemetry and a CNN-LSTM segmentation model to locate interfering channels and trigger automated mitigation. On a 273 km OpenIreland OLS testbed with three OSaaS users, the approach achieves up to 89% recall within 10 seconds for detecting rogue OOK signals and demonstrates complete mitigation of power increase and ADD/DROP interferences, highlighting practical potential for SLA preservation in dynamic, multi-tenant optical networks.

Abstract

We present a framework to identify and mitigate rogue OOK signals and user-generated power interference in a multi-user Optical-Spectrum-as-a-Service network. Experimental tests on the OpenIreland-testbed achieve up to 89% detection rate within 10 seconds of an interference event.

Figures (6)

• Figure 1: Experimental Setup
• Figure 2: OSaaS Channel Configuration
• Figure 3: OSaaS user configurations, and defined SLA
• Figure 4: Modeling and Mitigation framework
• Figure 5: Performance metrics of the user-specific models for detection of OOK signal (probability threshold(p)=0.50)