Jiayue He

Toward internet-wide multipath routing

The Internet would be more efficient and robust if routers could flexibly divide traffic over multiple paths. Often, having one or two extra paths is sufficient for customizing paths for different applications, improving security, reacting to failures, and balancing load. However, support for Internet-wide multipath routing faces two significant barriers. First, multipath routing could impose significant computational and storage overhead in a network the size of the Internet. Second, the independent networks that comprise the Internet will not relinquish control over the flow of traffic without appropriate incentives. In this article, we survey flexible multipath routing techniques that are both scalable and incentive compatible. Techniques covered include: multihoming, tagging, tunneling, and extensions to existing Internet routing protocols.

Towards Robust Multi-Layer Traffic Engineering: Optimization of Congestion Control and Routing

In the Internet today, traffic engineering is performed assuming that the offered traffic is inelastic. In reality, end hosts adapt their sending rates to network congestion, and network operators adapt the routing to the measured traffic. This raises the question of whether the joint system of congestion control (transport layer) and routing (network layer) is stable and optimal. Using the established optimization models for TCP and traffic engineering as a basis, we find the joint system can be stabilized and often maximizes aggregate user utility. We prove that both stability and optimality of the joint system can be guaranteed for sufficiently elastic traffic simply by tuning the cost function used for traffic engineering. Then, we present a new algorithm that adapts on a smaller timescale to changes in traffic distribution and is more robust to large traffic bursts. Uniting the network and transport layers in a multi-layer approach, this algorithm, distributed adaptive traffic engineering (DATE), jointly optimizes the goals of end users and network operators and reacts quickly to avoid bottlenecks. Simulations demonstrate that DATE converges quickly

Rethinking internet traffic management: from multiple decompositions to a practical protocol

In the Internet today, traffic management spans congestion control (at end hosts), routing protocols (on routers), and traffic engineering (by network operators). Historically, this division of functionality evolved organically. In this paper, we perform a top-down redesign of traffic management using recent innovations in optimization theory. First, we propose an objective function that captures the goals of end users and network operators. Using all known optimization decomposition techniques, we generate four distributed algorithms that divide traffic over multiple paths based on feedback from the network links. Combining the best features of the algorithms, we construct TRUMP: a traffic management protocol that is distributed, adaptive, robust, flexible and easy to manage. Further, TRUMP can operate based on implicit feedback about packet loss and delay. We show that using optimization decompositions as a foundation, simulations as a building block, and human intuition as a guide can be a principled approach to protocol design.

Multipath protocol for delay-sensitive traffic

Delay-sensitive Internet traffic, such as live streaming video, voice over IP, and multimedia teleconferencing, requires low end-to-end delay in order to maintain its interactive and streaming nature. In recent years, the popularity of delay-sensitive applications has been rapidly growing. This paper provides a protocol that minimizes the end-to-end delay experienced by inelastic traffic. We take a known convex optimization formulation of the problem and use an optimization decomposition to derive a simple distributed protocol that provably converges to the optimum. Through the use of multipath routing, our protocol can achieve optimal load balancing as well as increased robustness. By carrying out packet level simulations with realistic topologies, feedback delays, link capacities, and traffic loads, we show that our distributed protocol is adaptive and robust. Our results demonstrate that the protocol performs significantly better than other techniques such as shortest path routing or equal splitting among multiple paths.

TCP/IP Interaction Based on Congestion Price: Stability and Optimality

Despite the large body of work studying congestion control and adaptive routing in isolation, much less attention has been paid to whether these two resource-allocation mechanisms work well together to optimize user performance. Most analysis of congestion control assumes static routing, and most studies of adaptive routing assume that the offered traffic is fixed. In this paper, we analyze the interaction between congestion control and adaptive routing, and study the stability and optimality of the joint system. Previous work has shown that the system can be modelled as a joint optimization problem that naturally leads to a primal-dual algorithm with shortest-path routing using congestion prices as the link weights. In practice, the algorithm is commonly unstable. We consider three alternative timescale separations and examine the stability and optimality of each system. Our analytic characterizations and simulation experiments demonstrate how the step size of the congestion-control algorithm affects the stability of the system, and how the timescale of each control loop and homogeneity of link capacities affect system stability and optimality. The stringent conditions imposed for stability suggests that congestion price would be a poor feedback mechanism in practice.

Don't optimize existing protocols, design optimizable protocols

As networks grow in size and complexity, network management has become an increasingly challenging task. Many protocols have tunable parameters, and optimization is the process of setting these parameters to optimize an objective. In recent years, optimization techniques have been widely applied to network management problems, albeit with mixed success. Realizing that optimization problems in network management are induced by assumptions adopted in protocol design, we argue that instead of optimizing existing protocols, protocols should be designed with optimization in mind from the beginning. Using examples from our past research on traffic management, we present principles that guide how changes to existing protocols and architectures can lead to optimizable protocols. We also discuss the trade-offs between making network optimization easier and the overhead these changes impose.

Design for Optimizability: Traffic Management of a Future Internet

As networks grow in size and complexity, network management has become an increasingly challenging task. Many protocols have tunable parameters, and optimization is the process of setting these parameters to optimize an objective. In recent years, optimization techniques have been widely applied to network management problems, albeit with mixed success. Realizing that optimization problems in network management are induced by assumptions adopted in protocol design, we argue that instead of optimizing existing protocols, protocols should be designed with optimization in mind from the beginning. Using examples from our past research on traffic management, we present principles that guide how changes to existing protocols and architectures can lead to optimizable protocols. We also discuss the trade-offs between making network optimization easier and the overhead these changes impose.

CAM03-3: Can Congestion Control and Traffic Engineering Be at Odds?

In the Internet today, traffic engineering is performed assuming that the offered traffic is inelastic. In reality, end hosts adapt their sending rates to network congestion, and network operators adapt the routing to the measured traffic. This raises the question of whether the joint system of congestion control and routing is stable and optimal. Using established optimization models for TCP and traffic engineering as a basis, we find the joint system is stable and typically maximizes aggregate user utility through simulation. The joint system may deviate from this solution when the topology is not uniform. A modification to the joint system will guarantee stability and optimality for applications that are sufficiently elastic, but at the cost of robustness.