Abstract:

In order to achieve the goal of autonomous networks and improve the automation of network operation, an autonomous network model was explored.The model introduced algorithms such as multidimensional data automatic clustering, adaptive sliding time window mechanism, user traffic loss assessment model based on spatiotemporal sequence correlation, fault propagation graph based on graph theory and spatiotemporal clustering, and builded automation capabilities through network event management, fault self-identification, self-positioning, self-scheduling, and intelligent quality inspection.The goal is achieving L4 advanced intelligent network by 2025.

Key words: network event, autonomous network, self-identification, self-positioning, self-scheduling, intelligent quality inspection