More
    spot_img
    HomeAutomation/AINGMN's new framework supports autonomous networks based on AI

    NGMN’s new framework supports autonomous networks based on AI

    -

    NGMN publishes Automation and Autonomous system Architecture Framework – Phase 2

    The NGMN has published Automation and Autonomous system Architecture Framework – Phase 2. It provides guidance and direction on the use cases, requirements and architectural principles to ease the adoption of autonomous networks. In particular, network environments that are interoperable, multi-vendor and standards-based and designed to manage the complex, still evolving 5G Advanced ecosystem. 

    The framework outlines architectural considerations for using AI, including machine learning, to improve network operations by adding capabilities that are beyond human response times. The schematic above is taken from the paper and shows a view of machine learning-enabled operations or MLOps.

    The paper also seeks to act as a guide for organisations that develop standards aimed at more customised, user-centric experiences.

    Topics covered in the publication include: managing complexity; evolution of the network, services and devices; autonomous system management and orchestration and the role of large language models (LLMs); cooperative technologies and processes; use cases; security and privacy; and the role of industry standards.

    The publication was developed with input from across the industry: NGMN’s membership comprises operators, vendors and research institutions.

    Arash Ashouriha, Chairman of the NGMN Alliance Board and SVP Group Technology at Deutsche Telekom, noted, “AI has huge potential to revolutionise the way we plan, build, operate and maintain networks, the services we offer and our ability to respond rapidly to customer needs.

    “This publication provides a further foundation for the mobile industry to move forward together by developing and embracing a standards-based approach to autonomous networks.” 

    Further information and all NGMN publications can be found on the website at ngmn.org.