In this paper, we propose data clustering techniques to predict temporal characteristics of data consumption behavior of different mobile applications via wireless communications. While most of the research on mobile data analytics focuses on the analysis of call data records and mobility traces, our analysis concentrates on mobile application usages, to characterize them and predict their behavior. We exploit mobile application usage logs provided by a Wi-Fi local area network service provider to characterize temporal behavior of mobile applications. More specifically, we generate daily profiles of "what" types of mobile applications users access and "when" users access them. From these profiles, we create usage classes of mobile applications via aggregation of similar profiles depending on data consumption rate, using three clustering techniques that we compare. Furthermore, we show that we can utilize these classes to analyze and predict future usages of each mobile application through progressive comparison using distance and similarity comparison techniques. Finally, we also detect and exploit outlying behavior in application usage profiles and discuss methods to efficiently predict them.

Voice over Wireless LAN (VoWLAN) is becoming more and more helpful in our life and is expected to be among the most important applications in next generation networks. However, the maximum number of VoIP sessions that a WLAN can ensure is very small. Moreover, when the WLAN reaches its capacity the addition of one VoIP session affects the QoS parameters of all VoIP sessions. In this paper, we propose an adaptive technique to ensure the active VoIP sessions of users with high priority (from a provider perspective). Thus, in order to guarantee the quality of high priority sessions, we propose to downgrade the quality (low but acceptable MOS) of user sessions with low priority by changing their used codecs (e.g., ITU G729 instead of ITU G711). This technique and all related monitoring functions are defined into the proposed session-based QoS management architecture [1]. In order to validate our approach a complete test-bed is made up by which we have performed some feasibility and gain tests.

International audienceGrowing demands for the public wireless broadband services will require more capacity than the one provided by IP-based service providers (ISPs). The increasing popularity of WLANs due to the use of license-free radio spectrum with low-cost, easily deployable, high-data-rate wireless services, has encouraged service providers to consider their deployment in high density usage areas such us public hotspots to provide complementary broadband access to their networks and services. In order to provide consistent QoS control for multimedia applications (VoIP, VoD,...) over hotspots, a Session Initiation Protocol (SIP) based QoS management architecture is proposed in this article. Performance evaluations are discussed to illustrate the feasibility of the proposed architecture

International audienceIn this paper, we contribute on the service-driven management of quality of service and user access in wireless corporate networks. We propose a Service-Level Agreement (SLA) oriented nomadism management architecture with a top-down vision starting by the specification of company objectives and going down to device-level configurations. We define an algorithm for the automatic translation of application-level quality assurance parameters into network-level configuration parameters. A prototype implementation of our solution to the SLA-driven enterprise nomadism management is presented along with preliminary results on the self-adaptive capabilities of our QoS mapping algorithm