Cognitive Assurance Architecture for Optical Network Fault Management

TLDR

Staggering traffic growth from cloud platforms forces modern optical networks to demand higher operational reliability, prompting a shift toward cognition‑driven learning and fault management workflows. This paper proposes and demonstrates a cognitive fault detection architecture for intelligent network assurance. The architecture integrates cognitive fault management into a transport software‑defined network controller and is validated using real‑world fault examples. The framework detects and identifies significant faults, outperforming conventional fixed‑threshold operations in detection accuracy and proactive reaction time.

Abstract

In face of staggering traffic growth driven by cloud-based platforms, modern optical networks—forming the backbone of such connectivity—are faced with increasing requirements in terms of operational reliability. The challenge is that of cognition-driven learning and fault management workflows, cost-effectively assuring the next-generation networks. Machine learning, an artificial intelligence tool, can be conceived as an extremely promising instrument to address network assurance via dynamic data-driven operation, as opposed to static pre-engineered solutions. In this paper, we propose and demonstrate a cognitive fault detection architecture for intelligent network assurance. We introduce the concept of cognitive fault management, elaborate on its integration in transport software defined network controller, and demonstrate its operation based on real-world fault examples. Our framework both detects and identifies significant faults, and outperforms conventional fixed threshold-triggered operations, both in terms of detection accuracy and proactive reaction time.