Automation and Autonomous System Architecture Framework

As networks – through disaggregation and the move towards cloud-native – become increasingly complex it becomes ever more challenging to manage the network using existing processes and tools.  To keep pace there is a need to go beyond simple automation and towards the use of Artificial Intelligence (AI) and Machine Learning (ML) driven ‘autonomous’ systems that can learn how to manage and operate the network.  This publication describes a high-level framework, in terms of entities and functions that characterise autonomous system capabilities with an E2E (end-to-end) system perspective.

The architectural framework is intended to serve as guidance in the development of inter-operable and market enabling specifications, for a continuing advancement of the 5G ecosystem of heterogeneous access, virtualization, forward-looking service enablers, and emerging usage scenarios.