QUINCE (Quality of User Internet Customer Experience): a Reactive Crowdsourcing-based QoE Monitoring Platform

We are developing a framework which integrates existing network measurement infrastructures and crowdsourcing platforms to measure the Quality-of-Experience on network paths.

Sponsored by:
Nippon Telegraph And Telephone West Corporation (NTT)

Principal Investigators: Amogh Dhamdherekc claffy

Funding source:  NTT Joint Experiment Period of performance: January 1, 2018 - November 30, 2018.


Project Summary

Measuring the Quality of Experience (QoE) in a real-world environment is challenging. Even though a number of platforms have been deployed to gauge network path performance from the edge of the Internet, one cannot easily infer QoE from that data because of the subjective nature of QoE. On the other hand, crowdsourcing-based QoE assessment, namely QoE crowdtesting, is increasingly popular in conducting subjective assessments for various services, including video streaming, VoIP, and IPTV. Workers on crowdsouring platforms can access and participate in assessment tasks remotely through the Internet. The experimenter can also select a pool of potential workers according to their geolocation or their historical accuracy. Existing QoE crowdtesting mainly evaluates emulated scenarios, instead of studying the impact of Internet events. This is because the launching of QoE crowdtesting is usually not based on network measurement results. Although we can measure network path quality from the workers, it will be difficult to correlate the assessment results with Internet events because of differences in the assessment time and network path being measured.

In this project, we propose a novel framework to launch QoE crowdtesting in a timely manner when adverse network events are detected. We will use existing network measurement infrastructures to detect network events, such as link congestion. Based on information of the events, the framework would initiate QoE crowdtesting to recruit workers who are potentially affected, who then will provide feedback on their perceived QoE. The main advantage of this reactive approach is that it will improve the effectiveness of launching QoE crowdtesting tasks thus helping to evaluate the impact of network events as they occur.

Research Plan

Task Description Projected Timeline Status
1 Find resources Jan - Feb 2018 done
2 Finalize the schedules Jan - Feb 2018 done
3 Set up the necessary software and hardware for the platform Jan - Feb 2018 done
4 Start the experiment Mar 2018 done
5 Check the preliminary results. Are we collecting 150 records/month? Is the QoE score within the expected range? Apr 2018 done
6 Finish the initial result analysis May 2018 done
7 Modify parameters as necessary, repeat the experiment Jun - Aug 2018 done
8 Collect the targeted number of records Oct 2018 done
9 Report the results Nov 2018 done

Expected Outcomes

  • A platform which can automatically launch QoE crowdtesting according to network events
  • A mechanism for creating suitable QoE crowdtesting and recruiting appropriate set of workers from the crowd
  • A set of data obtained from the platform and the models derived from them

Additional Content

QUINCE (Quality of User Internet Customer Experience): a Reactive Crowdsourcing-based QoE Monitoring Platform

The proposal “A Reactive Crowdsourcing-based QoE Monitoring Platform” is also available in PDF.

Published
Last Modified