Automated Analytics WiFi

With Automated Analytics WiFi, automation is applied to the connectivity and performance of WiFi networks with modern AI/ML techniques. This approach, combined with domain expertise is used to identify users and populations of users experiencing WiFi login problems, to characterize last mile performance against thresholds for packet loss and last mile latency, and to evaluate throughput metrics and top app tonnage visibility at the transport layer.

Resulting information from WiFi smart analytics chains, support guided investigation of the performance issues experienced by subscriber type (paid vs guest) and regions alongside evaluations of potential contributing sources (SSID, Access Point Make/Model). Armed with evidence and localization of problems, Cable/MSO and fixed line providers can prioritize troubleshooting resources and improve decision-making for future rollouts and capacity planning.

Go beyond proactive service monitoring to understand and isolate how and why WiFi services are performing from the customer’s point of view. With Automated Analytics WiFi, customer-impacting problems are highlighted for at-a-glance investigation and resolution.

Localize and Isolate Login Problems
Subscribers expect instantaneous connection to available and subscribed WiFi networks. While DHCP 4-way handshake latency metrics are often used to evaluate network wide login performance, visibility to underlying issues experienced by users in a particular Market or on a particular SSID add additional clarity and actionable insights. With Automated Analytics WiFi, service providers can determine when a newly deployed or updated access point is contributing to login latency.

Address the Impact of Packet Loss in the Last Mile
When service issues occur between the WiFi Access Gateway and the end user (AP/UE), service providers need a way to quickly assess the severity of the impact on the user experience by market and region. Among poor-performing areas, specific SSIDs and AP models may be easily evaluated and compared against daily performance thresholds.

Correlate Application Issues with Network Problems
With WiFi networks supporting massive amounts of internet traffic, providers need to stay on top of fluctuations in throughput as well as the impacts and tonnage of top apps such as Facebook, Amazon, Apple, Netflix, and Google. In addition, the ability to correlate service degradation of top apps with transport layer visibility to latency, packet loss enables swift actions to restore and maintain the user experience.