Cartography of the Quality of Experience for Mobile Internet Access

Estimation et cartographie de la qualité d’expérience pour l’accès à l’Internet mobile



Spirals Research Group

Inria Lille - Nord Europe

40, avenue Halley

59650 Villeneuve d'Ascq - FRANCE

Madynes Research Group

Inria Nancy - Grand Est
LORIA Campus Scientifique - BP 239

54506 Vandoeuvre Les Nancy - FRANCE

Scientific context

Over the last decade, the Internet has become a central component of communications, technology development and online business. In particular, new usages—induced by mobile and Internet-of-Things (IoT) devices—have been recently emerging, thus enforcing our dependency towards Internet. Given the best effort nature of the Internet and its unceasing growth both in size and heterogeneity, Internet stakeholders (researchers, service and content providers, civil society, regulators, etc.) need to better understand its characteristics, its limitations, and its dynamics, both globally and locally, to improve applications and protocols design, detect and correct anomalous behaviors. Therefore, a collaborative environment is required where observation tools and methods can be developed, and where data can be acquired, analyzed, and shared appropriately in order to get a better knowledge about the Internet as perceived by users. This knowledge of the Internet usage will first allow researchers in the field of networks, information technology, applied mathematics, social sciences to design theoretical models or new concepts and compare them with facts through the collected data. It will also provide public and private policy makers, and private citizens in general, with a more accurate and reliable basis for decisions making.

Measuring Internet usage will involve a new user-centered paradigm as users now are always connected and access different services through different networks and devices at different locations. In addition to measuring end-to-end Quality of user Experience (QoE), we have to diagnose the sources of degraded experience and understand how users deal with this degradation.

Research topic

As part of this PhD thesis, we plan to focus on a crowd-scale analysis of the end-users’ QoE when accessing the Internet from a mobile device. In particular, we intend to confront human and social aspects of QoE to technical metrics collected in the wild. Given that Google promotes the Page Load Time[1] or the Time to Start Render[2] as the key metrics reflecting the QoE,[3] a lot of research efforts have been spent to optimize the delivery of web pages on the browser driven by these metrics [1,2]. Nevertheless, all these studies are mostly motivated by the content providers and their quest increase their revenue, and none of them really takes into account the perspective of the end-user and her perception of the QoE. The objective of this project is therefore to better identify the principal components of an ideal QoE, as perceived by the end-user. In particular, we believe that the time to render the relevant content, the reactivity of the mobile interface, the effects of mobile handoffs, the user context and expectations are further dimensions to be considered to deliver a realistic cartography of the QoE when accessing the Internet from a mobile device.

Previous results

This PhD thesis topic builds on the outcome of the PhD thesis of Nicolas Haderer, defended in 2014 [4], which resulted in the deployment of a mobile crowdsourcing platform, named APISENSE® (, that supports the continuous monitoring of human and environmental activities in the wild. The APISENSE® platform therefore provides a suitable environment to conduct the research plan within this PhD thesis. In particular, we plan to demonstrate our research contributions by extending this platform to leverage its evaluation.

Beyond the results we already obtained on APISENSE®, we also intend to benefit from the expertise we acquired on PRACTIC (, a large-scale study on smartphone usages [5]. This study revealed the gap between the user perception and the ground truth that can be measured by physical sensors.

Work plan

Our work plan for this PhD thesis is organized along six periods of six months. While the first 6 months will be devoted to bootstrap the research activities by considering the study of the state-of-the-art in the area of end-user’s quality of experience modeling and monitoring, the next four periods will deliver contributions in the areas of QoE monitoring, human and social analysis, multi-dimensional cartography, and service recommendation, respectively. The last period will focus on the delivery of the PhD manuscript and the associated PhD defense.

Research collaborations

Eric Guichard (ENS ERST) provide its competences in sociology (surveys, analysis of speeches, etc.), cartography of the internet and of its practices (, edition, history and philosophy of technique and of the Internet (including critical thought), epistemology.

Chadi Barakat (Inria Diana) has a strong expertise on the estimation of the quality of experience at the Internet access, while specifying this estimation to the main classes of applications ran by the end-users.

Renata Texeira (Inria Muse) is a network expert focusing on the measurement and tanalysis of user online activity to then develop tools to assist users in selecting Internet service plans.

Expected outcome

Beyond the proof of concept developments that will be carried on as part of this PhD thesis and published as open source software, we intend to promote the transfer our research contributions within the civil society through our APISENSE® platform, and within the industrial ecosystem through transfer collaborations.


  1. Demystifying Page Load Performance with WProf. X. S. Wang, A. Balasubramanian, A. Krishnamurthy, and D. Wetherall. NSDI 2013.
  2. Understanding website complexity: measurements, metrics, and implications. M. Butkiewicz, H. V. Madhyastha, and V. Sekar. IMC 2011.
  3. Dynamic Deployment of Sensing Experiments in the Wild Using Smartphones. N. Haderer, R. Rouvoy, L. Seinturier. DAIS 2013: 43-56
  4. APISENSE®  : une plate-forme répartie pour la conception, le déploiement et l'exécution de campagnes de collecte de données sur des terminaux intelligents. N. Haderer. Thèse de doctorat. Université de Lille 1. Novembre 2014.
  5. Refining smartphone usage analysis by combining crowdsensing and survey. V. Rivron, M. Irfan Khan, S. Charneau, I. Chrisment. PerCom Workshops 2015: 366-371