Video Streaming Analytics | Network Experience & Technology Leadership Solutions

Video Streaming Analytics

A machine learning solution to understand and monitor your subscribers’ online video experiences

Video quality: the new CSP yardstick

Video services account for more than half of all network traffic, a trend that is on an upward trajectory. Such growth sets significant pressure on Communications Service Providers (CSPs) who need to satisfy their subscribers’ expectations for video quality; anywhere, anytime. Video Quality of Experience (QoE) is now the proxy for network service quality.

Network teams need to assess service quality and validate their network planning and optimization initiatives to ensure consistent delivery of expected video QoE. However, Video KPIs like resolution, initial buffering time, and stall events are unavailable because the video services are delivered via encrypted streams.
The new CSP yardstick

Leverage machine learning to deduce video streaming KPIs

Video Streaming Analytics is a solution that computes Video KPIs, such as resolution, initial buffering time, and stall events, by employing machine-learning algorithms. With these KPIs, your network teams can monitor and analyze the QoE of the video streaming services delivered through the network. Video usage statistics and KPIs are presented in near real-time and historically, within a dedicated workspace that allows your network teams to observe trends and analyze deviations.
Leverage machine learning to deduce video streaming KPIs
 

Normalize the definition of video quality with a single metric

With the availability of video KPIs, Mobileum has defined and converged on a single metric that normalizes the definition of video quality: the video Mean Opinion Score (vMOS). It is the unitary quality indicator, built up from video KPIs, that allows network teams to objectively assess if the QoE of video streaming services delivered meets the desired quality expectations.
Normalize the definition of video quality with a single metric

Video Streaming Analytics Datasheet

Learn more how Mobileum helps CSPs understand and monitor their subscribers’ online video experiences.

Understand video streaming utilization and performance across the network

The Overview and KPIs Dashboards offer a consolidated view of video streaming utilization and performance throughout the network. Network teams can seamlessly navigate between map and chart visualizations to get up-to-date insights for utilization and key performance metrics over the past 24 hours or for the desired custom range, and monitor trends. Beyond an intuitive interface that offers a bird’s-eye view of total and per session video streaming QoE, at different locations and for the desired custom time range, network teams can combine multiple filtering options, such as application, granularity, and RAT, to drill down to their desired level of analysis.
Understand video streaming utilization

Monitor video streaming QoE per location, network element, and device

The Location, Core Network, and Devices Dashboards offer more focused analyses for network planning and optimization teams, who need to monitor and isolate service degradation issues occurring in particular locations, network elements, or device models. Using interactive visualizations, they can monitor critical metrics that affect subscribers’ video QoE over a selected time period. By isolating problematic geographical areas, network topologies, and devices where most streaming issues are encountered, they can take proactive steps to optimize and distribute network resources more effectively.
Monitor video streaming QoE

5 ways you can deliver better video experiences to your subscribers with Mobileum
Video Streaming Analytics

Proactively manage the quality of video streaming services
by tracking key metrics that impact subscribers’ streaming experiences.
Fix radio interference or congestion in hotspot cells
by identifying the worst-performing locations of video streaming services for metrics like resolution downgrades, stalling, and initial buffering time.
Find and remediate problematic video streaming devices
by monitoring the variance in video streaming quality across different device models.
Selectively manage network resources during peak hours
by activating traffic shaping tools that limit video streaming within areas and times of the day.
Optimize capacity management and expansions
by increasing the number of eNodeBs/gNodeBs and adding new frequency carriers in locations with heavy video streaming demand.