Table 1 - Traffic Impact on Apps
(Click to Enlarge)

As you can see from the table above, simply delivering a decent average throughput will not necessarily result in good subscriber experience. A good average score does not translate to a consistently good experience either, as conditions may vary throughout the day, week, or month. However, if operators collect these key metrics, they can create their own network experience scorecards and use them to improve customer experience.

The Future is Experiential

ETSI’s Experiential Network Intelligence specification group aims to improve quality by adding closed-loop AI mechanisms based on context-aware, metadata-driven policies to more quickly recognize changing conditions so that the most suitable actions can be taken by the network.

Of course, bandwidth, latency, and packet loss must be considered, but so must factors such as application, location, time of day, device type, service plan, and end-to-end network conditions. AI should incorporate these factors and many more, providing far richer context and situational insight so that network modifications would be more specific, precise, and likely to deliver positive QoE outcomes.

The future of mobile data analytics and the automation that will invariably follow will need to combine the emerging Network Data Analytics function with robust, AI-based, Experiential Network Intelligence engines. The NWDA function will identify the changes needed, and the ENI engine will initiate the actions that resolve QoE issues in real-time.