Telecoms, Media & Technology is part of the Knowledge and Networking Division of Informa PLC
This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 3099067.
The autonomous network is here. Are you ready for it?
The Scope for Robotic Process Automation & Machine Learning in Telecom Operations
Intent-based modeling could significantly reduce the time spent on design, implementation and testing a new service (such as SD-WAN) compared with traditional workflows. Intent modelling can also be applied to assurance in addition to fulfillment providing a feedback loop for self-healing networks. This panel will explore how CSPs can use intent-based-modeling for order management, provisioning, task management, and quality management in their next generation networks.
A vast array of technology ingredients is essential to make automation possible -- virtualization, AI, machine learning, telemetry, robotics, analytics, etc. This panel will discuss how mature solutions are for real world telecom operations and what is holding back operators from adopting them more aggressively.
SD-WAN adoption is sky-rocketing, but where is this leading and what can we learn? This presentation will explore how automation and machine learning are being applied in the context of SD-WAN, and how they provide a path toward an autonomous, self-driving WAN.
Two key trends are evident. First, as IT organizations transition toward framing network or service objectives in terms of higher-level business intent, in contrast to specifying static device-by-device configurations, automation must be complemented with machine learning. This will facilitate the translation of high-level intent into the continuous and dynamic optimization of hundreds or thousands of individual network components. Second, to process enormous volumes of data in real-time, traditional data collection and analysis methods will be augmented with AI, backed by web-scale compute infrastructure.
Automation means different things to different people. For industrial vendors, it's about the electrical and mechanical process automation on the production line. IT vendors see automation at a higher level within a company's systems. This panel will explore what the telecom industry can learn from automation initiatives in other industries, in particular the reference architecture used to define the degree of development for autonomous cars: from automated components (such as parking sensors) to macro-level autonomous systems (self-driving cars).
Closed-loop automation is the end goal for NFV. Current solutions are highly manual but with machine learning the network can detect or predict faults, know how to fix it (e.g., re-route traffic, spin up a new instance) and execute it without any human intervention. However, in the early days it may be perceived as a risky proposition and many CSPs will want tools that will let them confirm changes were handled correctly. The panel will discuss the state of play for closed loop automation in NFV and what needs to be done to make it a reality.
This panel will discuss software-based automation in the service provider (or carrier) WAN, which includes access, aggregation, metro core and long-haul/backbone networks. It will explore how carriers can use automation internally to boost efficiency, and externally to improve existing services and enable new services such as bandwidth on demand, customer-facing portals and SDWANs for branch office connectivity.