"The goal of this thesis is to address network management research challenges faced by operational networks - with specific focus on cellular networks, content delivery networks, and online social networks. Next, I give an overview of my research on network management of these networks. Cellular networks utilize existing service quality management systems for detecting performance degradation issues inside the network, however, under certain conditions degradation in End-to-End (E2E) performance may go undetected. These conditions may arise due to problems in the mobile device hardware, smartphone applications, and content providers. In this thesis, I present a system for detecting and localizing E2E performance degradation at cellular service providers across four administrative domains: cellular network, content providers, device manufacturers, and smartphone applications. Cellular networks also need systems that can prioritize performance degradation issues according to the number of customers impacted. Cell tower outages are performance degradation issues that directly impact connectivity of cellular network users. In this thesis, we design and evaluate a cell tower outage monitoring system that analyzes and estimates device level impact during cell tower outages. Content delivery networks (CDNs) maintain multiple transit routes from content distribution servers to eyeball ISP networks which provide Internet connectivity to end users. Two major considerations for CDNs are transit prices and performance dynamics of delivering content to end users. The dynamic nature of transit pricing and performance makes it challenging to optimize the cost and performance tradeoff. There are thousands of eyeball ISPs which are reachable via different transit routes and different geographical locations. Each choice of transit route for a particular eyeball ISP and geographical location has distinct cost and performance characteristics, which makes the problem of developing a transit routing strategy challenging. In this thesis, I present a measurement approach to actively collect client perceived network performance and then use these measurements towards optimal transit route selection for CDNs. Online Social Networks (OSNs) often refuse to publish their social network graphs due to privacy concerns. Differential privacy has been the widely accepted criteria for privacy preserving data publishing. In this thesis, I present a random matrix approach to OSN graph publishing, which achieves storage and computational efficiency by reducing dimensions of adjacency matrices and achieves differential privacy by adding a small amount of noise."--Pages ii-iii.
Read
