Mobile video traffic is dominant in cellular and enterprise wireless networks. With the advent of myriads of applications from video telephony and streaming to virtual reality, network administrators face the challenge to provide high quality of experience (QoE) in the face of diverse wireless conditions and application contents. Yet, state-of-the-art networks lack analytics for QoE, as this requires support from the application or user feedback. While there are existing techniques to map quality of service (QoS) to QoE by training machine learning (ML) models without requiring user feedback, these techniques are limited to only few applications (e.g., Skype), due to insufficient QoE ground-truth annotation for ML. To address these limitations, we focus on video telephony applications and model key artefacts of spatial and temporal video QoE. Our key contribution is designing content- and device-independent metrics and training across diverse WiFi conditions. We show that our metrics achieve a median 90% accuracy by comparing with mean-opinion-score (MOS) from more than 200 users and 800 video samples. Our content-independent metrics significantly reduce the MOS prediction error of previous works and are validated over three popular video telephony applications - Skype, FaceTime and Google Hangouts.

Application Mobilization, or the ability of an enterprise employee to rely on mobile devices such as smartphones and tablets, to continue to perform business workflows even when mobile, is seen as a game changer to improve productivity. However, the practical adoption of enterprise mobility is very much in its in fancy, and seemingly has barriers. We posit that these barriers include heavy user-burden in accomplishing tasks (e.g. number of actions required to execute a workflow), high cost of mobile access (e.g. latency for content fetching), and irrelevance of available mobile functions (e.g. mobile app defeaturization done inappropriately).The novelty of our research is in a unified observe-patternize-mimic paradigm we explore to address these barriers, based on a simple question: could patterns in user-behavior be learned, and leveraged for reducing user-burden? If patterns are discovered, then we show that intelligent mimicking of these patterns at appropriate junctures can considerably relieve the mobile user burden. We motivate this paradigm through three application scenarios representing read, write, and act usage modalities.

Enterprise wireless networks face significant challenges to deliver Quality-of-Experience (QoE) with the variety of mobile applications. One of the fundamental challenges is that the traditional definition of network capacity (often defined as throughput capacity) is not sufficient to reflect applications' requirements in wireless networks. In this paper, we propose to rethink the network capacity of wireless networks to better incorporate QoE. Specifically, we first propose a novel concept of an Experiential Capacity Region (ExCR) for wireless networks. ExCR is defined as a set of simultaneous application flows whose QoE requirements can be satisfied by the network. Next, we present the infrastructure based ExBox system that measures per-application QoE metrics and determines the ExCR for wireless networks to better serve a set of mobile application flows. In its core, ExBox employs light-weight machine learning techniques that are tailored for dynamic wireless environments. Through both large-scale simulations and extensive real-life experiments on WiFi and LTE networks, we show that ExBox delivers QoE in admission control decision with a precision of ≈ 0.8 - 0.9, even when clients experience diverse channel quality. Moreover, ExBox quickly adapts to changing network environments without much overhead.

With the great success of LTE(-A) outdoor, LTE-based small cell technology has become popular and is penetrating indoor enterprise environment, co-existing with WiFi networks, to provide better user experience or Quality-of-Experience (QoE). However, accurate estimation of LTE links is challenging and critical to continue providing QoE for many enterprise applications (e.g., video/audio) and services (network selection). While prior work on LTE link throughput estimation depends mostly on a single factor (e.g., link rate), we argue that it needs to consider more factors to improve the estimation to meet increasing demands on QoE. In this paper, we propose a new metric, called Pulsar (Per-user LTE ShAre of Resources), that estimates per flow throughput in LTE networks by leveraging both underlying channel information and application traffic characteristics. Our extensive evaluation study through ns-3 shows that Pulsar reduces the estimation error more than 92%, compared to prior work, in various scenarios, while keeping estimation overhead low.

Network deduplication (dedup) is an attractive approach to improve network performance for mobile devices. With traditional deduplication, the dedup~source uses only the portion of the cache at the dedup~destination that it is aware of. We argue in this work that in a mobile environment, the dedup~destination (say the mobile) could have accumulated a much larger cache than what the current dedup~source is aware of. This can occur because of several reasons ranging from the mobile consuming content through heterogeneous wireless technologies, to the mobile moving across different wireless networks.

The IEEE 802.11n standard is gaining popularity to achieve high throughput in Wireless LANs. In this paper, we explore link adaptation in practical 802.11n systems using experiments with off-the-shelf hardware. Our experiments reveal several non-trivial insights. Specifically, (1) trivial extensions of algorithms developed for 802.11g provide minimal benefits in 802.11n systems; (2) in contrast to theoretical expectation, multiple antenna transmission does not always lead to higher throughput in practice; (3) both stream and antenna selection are essential to reap the full benefits of MIMO technologies. We use insights developed from experiments to develop a new metric for stream selection called the Median Multiplexing Factor (MMF). The proposed metric can be used to develop intelligent rate selection algorithms that can achieve high throughput with purely software changes.

The focus of this work is to study the efficacy of TCP's flow control algorithm on mobile phones. Specifically, we identify the design limitations of the algorithm when operating in environments, such as mobile phones, where flow control assumes greater importance because of device resource limitations. We then propose an adaptive flow control (AFC) algorithm for TCP that relies not just on the available buffer space but also on the application read-rate at the receiver. We show, using NS2 simulations, that AFC can provide considerable performance benefits over classical TCP flow control.