Summary - Y.3142 (04/2024) - Requirements and framework for AI/ML-based network design optimization in future networks including IMT-2020

Due to the development of IMT-2020 networks, a large number of new applications and services have emerged, leading to explosive growth in network traffic and much more complicated networks, which results in increased difficulty in attaining network design optimization. Many services are changing rapidly, and network operators need to dynamically design and adjust their networks based on the traffic distribution and the traffic increment trends in order to guarantee the necessary quality of service (QoS). Artificial intelligence (AI) can be used for prediction and decision-making, which can make network design more intelligent and automated.
Recommendation ITU-T Y.3142 focuses on the use of artificial intelligence (AI)/machine learning (ML) technologies to improve network design mechanisms. This Recommendation describes how AI/ML can be integrated in order to optimize the design of network capacity, network topology, and routing to satisfy all of the demands of service level agreements (SLAs) in a cost-effective way, instead of only guaranteeing the SLAs without taking into account the overall cost.