Dilip Antony Joseph

Understanding the impact of video quality on user engagement

As the distribution of the video over the Internet becomes main- stream and its consumption moves from the computer to the TV screen, user expectation for high quality is constantly increasing. In this context, it is crucial for content providers to understand if and how video quality affects user engagement and how to best invest their resources to optimize video quality. This paper is a first step towards addressing these questions. We use a unique dataset that spans different content types, including short video on demand (VoD), long VoD, and live content from popular video con- tent providers. Using client-side instrumentation, we measure quality metrics such as the join time, buffering ratio, average bitrate, rendering quality, and rate of buffering events. We quantify user engagement both at a per-video (or view) level and a per-user (or viewer) level. In particular, we find that the percentage of time spent in buffering (buffering ratio) has the largest impact on the user engagement across all types of content. However, the magnitude of this impact depends on the content type, with live content being the most impacted. For example, a 1% increase in buffering ratio can reduce user engagement by more than three minutes for a 90-minute live video event. We also see that the average bitrate plays a significantly more important role in the case of live content than VoD content.

A policy-aware switching layer for data centers

Data centers deploy a variety of middleboxes (e.g., firewalls, load balancers and SSL offloaders) to protect, manage and improve the performance of applications and services they run. Since existing networks provide limited support for middleboxes, administrators typically overload path selection mechanisms to coerce traffic through the desired sequences of middleboxes placed on the network path. These ad-hoc practices result in a data center network that is hard to configure and maintain, wastes middlebox resources, and cannot guarantee middlebox traversal under network churn. To address these issues, we propose the policy-aware switching layer or PLayer, a new layer-2 for data centers consisting of inter-connected policy-aware switches or pswitches. Unmodified middleboxes are placed off the network path by plugging them into pswitches. Based on policies specified by administrators, pswitches explicitly forward different types of traffic through different sequences of middleboxes. Experiments using our prototype software pswitches suggest that the PLayer is flexible, uses middleboxes efficiently, and guarantees correct middlebox traversal under churn.

Modeling the adoption of new network architectures

We propose an economic model based on user utility to study the adoption of new network architectures such as IPv6. We use mathematical analysis and simulation studies to understand the role of various factors such as user and network benefits, switching costs, and the impact of converters on the adoption of new network architectures. In addition to corroborating various commonly held beliefs about new network architecture adoption, our analysis and simulation studies also reveal several surprising and non-intuitive results. For example, while in general, increasing the efficiency of converters hastens the adoption of new network architectures, there are cases in which more efficient converters hinder the adoption of such architectures. This and other results in the paper increase our understanding of new network architecture adoption and guide the design and implementation of mechanisms to hasten new network architecture adoption.

Interoperability of Wi-Fi hotspots and cellular networks

The widespread deployment of Wi-Fi hotspots and wide area cellular networks opens up the exciting possibility of interoperability between these types of networks. Interoperability allows a mobile device to dynamically use the multiple net-work interfaces available to it so as to maximize user satisfaction and system performance. In this paper, we define three basic user profiles for the network users and demonstrate through simulation studies that dynamic switching on the basis of the user profiles of the mobile devices leads to higher network performance and increased user satisfaction. Careful design of pricing, billing and revenue sharing schemes is necessary to ensure the commercial viability of the multiple service providers involved in an inter-operable network setting. Different pricing and revenue sharing schemes are introduced and analyzed using simulation studies. We also demonstrate how load balancing can improve network performance in an inter-operable network.

The interoperability of Wi-Fi hotspots and packet cellular networks and the impact of user behaviour

The rapid emergence of Wi-Fi hotspots (access points), that are aimed at providing broadband wireless access to users in and around places of commercial interest, presents the unique problem of integrating existing cellular networks with these. We present a novel architecture that explores the interoperability issues between Wi-Fi hotspots and packet cellular networks. In the presence of multiple wireless networks with different access costs, different areas of coverage and bandwidth, the users choice to select a particular network can significantly impact user benefits and resource usage. We identify three major user profiles - bandwidth conscious, cost conscious and glitch conscious - and study their impact on resource utilization. Contrary to intuition, simulation experiments have shown that bandwidth conscious users may get fewer bandwidth resources compared to glitch conscious users at high mobility. Similarly, it was found that bandwidth conscious users achieve high packet delivery ratios, even while incurring lower costs than cost conscious users, in certain situations. Although increasing the number of access points (APs) leads to higher packet delivery ratios, system performance degrades when the number of APs becomes very large.