Many large content publishers use multiple content distribution networks to deliver their content, and many commercial systems have become available to help a broader set of content publishers to benefit from using multiple distribution networks, which we refer to as content multihoming. In this paper, we conduct the first systematic study on optimizing content multihoming, by introducing novel algorithms to optimize both performance and cost for content multihoming. In particular, we design a novel, efficient algorithm to compute assignments of content objects to content distribution networks for content publishers, considering both cost and performance. We also design a novel, lightweight client adaptation algorithm executing at individual content viewers to achieve scalable, fine-grained, fast online adaptation to optimize the quality of experience (QoE) for individual viewers. We prove the optimality of our optimization algorithms and conduct systematic, extensive evaluations, using real charging data, content viewer demands, and performance data, to demonstrate the effectiveness of our algorithms. We show that our content multihoming algorithms reduce publishing cost by up to 40%. Our client algorithm executing in browsers reduces viewer QoE degradation by 51%.

Network resiliency is crucial to IP network operations. Existing techniques to recover from one or a series of failures do not offer performance predictability and may cause serious congestion. In this paper, we propose Resilient Routing Reconfiguration (R3), a novel routing protection scheme that is (i) provably congestion-free under a large number of failure scenarios; (ii) efficient by having low router processing overhead and memory requirements; (iii) flexible in accommodating different performance requirements (e.g., handling realistic failure scenarios, prioritized traffic, and the trade-off between performance and resilience); and (iv) robust to both topology failures and traffic variations. We implement R3 on Linux using a simple extension of MPLS, called MPLS-ff. We then conduct extensive Emulab experiments and simulations using realistic network topologies and traffic demands. Our results show that R3 achieves near-optimal performance and is at least 50% better than the existing schemes under a wide range of failure scenarios.

Due to recent large-scale deployments of delay and loss-sensitive applications, there are increasingly stringent demands on the monitoring of service level agreement metrics. Although many end-to-end monitoring methods have been proposed, they are mainly based on active probing and thus inject measurement traffic into the network. In this paper, we propose a new scheme for monitoring service level agreement metrics, in particular, delay distribution. Our scheme is passive and therefore will not cause perturbation to real traffic. Using realistic delay and traffic demands, we show that our scheme achieves high accuracy and can detect burst events that will be missed by probing based methods.

Reliability is a critical requirement of the Internet. The availability and resilience of the Internet under failures can have significant global effects. However, in the current Internet routing architecture, achieving the high level of reliability demanded by many mission critical activities can be costly. In this paper, we first propose a novel solution framework called reliability as an interdomain service (REIN) that can be incrementally deployed in the Internet and may improve the redundancy of IP networks at low cost. We then present robust algorithms to efficiently utilize network redundancy to improve reliability. We use real IP network topologies and traffic traces to demonstrate the effectiveness of our framework and algorithms.

Traffic engineering plays a critical role in determining the performance and reliability of a network. A major challenge in traffic engineering is how to cope with dynamic and unpredictable changes in traffic demand. In this paper, we propose COPE, a class of traffic engineering algorithms that optimize for the expected scenarios while providing a worst-case guarantee for unexpected scenarios. Using extensive evaluations based on real topologies and traffic traces, we show that COPE can achieve efficient resource utilization and avoid network congestion in a wide variety of scenarios.

We present a general model of interdomain route selection to study interdomain traffic engineering. In this model, the routing of multiple destinations can be coordinated. Thus the model can capture general traffic engineering behaviors such as load balancing and link capacity constraints. We first identify potential routing instability and inefficiency of interdomain traffic engineering. We then derive a sufficient condition to guarantee convergence. We also show that the constraints on local policies imposed by business considerations in the Internet can guarantee stability without global coordination. Using realistic Internet topology, we evaluate the extent to which routing instability of interdomain traffic engineering can happen when the constraints are violated.

The recent discovery of instability caused by the interaction of local routing policies of multiple ASes has led to extensive research on the subject. However, previous studies analyze stability under a specific route selection algorithm. In this paper, instead of studying a specific route selection algorithm, we study a general class of route selection algorithms which we call rational route selection algorithms. We present a sufficient condition to guarantee routing convergence in a heterogeneous network where each AS runs any rational route selection algorithm. Applying our general results, we study the potential instability of a network where the preference of an AS depends on not only its egress routes to the destinations but also its inbound traffic patterns (i.e., the distribution of incoming traffic from its neighbors). We show that there exist networks which will have persistent route oscillations even when the ASes strictly follow the constraints imposed by business considerations, and adopt any rational route selection algorithms.

Multihoming is a popular method used by large enterprises and stub ISPs to connect to the Internet to reduce cost and improve performance. Recently researchers have studied the potential benefits of multihoming and proposed protocols and algorithms to realize these benefits. They focus on how to dynamically select which ISPs to use for forwarding and receiving packets, and assume that the set of subscribed ISPs is given a priori. In practice, a user often has the freedom to choose which subset of ISPs among all available ISPs to subscribe to. We call the problem of how to choose the optimal set of ISPs the ISP subscription problem. In this paper, We design a dynamic programming algorithm to solve the ISP subscription problem optimally. We also design a more efficient algorithm for a large class of common pricing functions. Using real traffic traces and realistic pricing data, we show that our algorithm reduces users' cost. Next we study how ISPs respond to users' optimal ISP subscription by adjusting their pricing strategies. We call this problem the ISP pricing problem. Using a realistic charging model, we formulate the problem as a non-cooperative game. We first prove that if cost is the only criterion used by a user to determine which subset of ISPs to subscribe to, at any equilibrium all ISPs receive zero revenue. We then study a more practical formulation in which different ISPs provide different levels of reliability and users choose ISPs to both improve reliability and reduce cost. We analyze this problem and show that at any equilibrium an ISP's revenue is positive and determined by its reliability.