Networks are complex interacting systems involving cloud operations, core and metro transport, and mobile connectivity all the way to video streaming and similar user applications. With localized and highly engineered operational tools, it is typical of these networks to take days to weeks for any changes, upgrades, or service deployments to take effect. Machine learning, a sub-domain of artificial intelligence, is highly suitable for complex system representation. In this tutorial paper, we review several machine learning concepts tailored to the optical networking industry and discuss algorithm choices, data and model management strategies, and integration into existing network control and management tools. We then describe four networking case studies in detail, covering predictive maintenance, virtual network topology management, capacity optimization, and optical spectral analysis.
8 December 2017 in Journal of Lightwave Technology
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.