ITU-T E.475 PDF

With the increased number of connected devices and the proliferation of web and multimedia services, cloud services and IoT applications, the network are subject to various network incidents and unregulated network changes which are measured by network alerts and logs received from the underlying networks. Therefore, it is important for the network to be aware of the services and applications it facilitates when users are experiencing audio/video quality related problems and to operate the network to ensure that the offered services meet user expectations on service quality. The absence of network alerts or network logs is generally interpreted as an indication of good network health. However, service quality problems may not be the result of network device failures but the result of configuration errors, insufficient network capacity, wireless access point issues (e.g., insufficient coverage, interference or overlapping channel), or third party network issues, and these issues may not be detected by traditional network monitoring tools. Typically, the manual reconfiguration is time consuming and often error prone. In addition, service quality assessment methodologies need to further distinguish between network impairments and other causes of performance degradation by considering application-specific factors (e.g., encoding/decoding, interaction between an application and a network) because the traditional assessment tools cannot provide accurate fault diagnosis, fault prediction, and root cause analysis. Moreover, they usually respond to the network event slowly after the service disruption. In addition, the network performance metrics may contribute to QoS/QoE assessment, but many of the existing network performance metrics may reflect only limited aspects of the network quality.

The objective of this Recommendation is to describe the guidelines for intelligent network analytics and diagnostics for managing and troubleshooting networks. The guidelines derive its assessment from the analysis of data collected from networks and address the quality assessment of network anomalies based on data collected from the network. The network data can be in the form of network logs, network configuration data, service platform data, call details record (CDR), traffic statistics, alerts or performance data.

This Recommendation covers the following:

• Design consideration,

• Functional architecture overview,

• Network analytics and diagnostics methodology,

• Network analytics and diagnostics models,

• Network risk analysis by leveraging the key performance indicators (KPIs') correlation and the association between user experience and network performance,

• Network analytics and diagnostics applications.