Peter Key

PIC: practical Internet coordinates for distance estimation

We introduce PIC, a practical coordinate-based mechanism to estimate Internet network distance (i.e., round-trip delay or network hops). Network distance estimation is important in many applications; for example, network-aware overlay construction and server selection. There are several proposals for distance estimation in the Internet but they all suffer from problems that limit their benefit. Most rely on a small set of infrastructure nodes that are a single point of failure and limit scalability. Others use sets of peers to compute coordinates but these coordinates can be arbitrarily wrong if one of these peers is malicious. While it may be reasonable to secure a small set of infrastructure nodes, it is unreasonable to secure all peers. PIC addresses these problems: it does not rely on infrastructure nodes and it can compute accurate coordinates even when some peers are malicious. We present PICs design, experimental evaluation, and an application to network-aware overlay construction and maintenance.

A decision-theoretic approach to call admission control in ATM networks

This paper describes a simple and robust ATM call admission control, and develops the theoretical background for its analysis. Acceptance decisions are based on whether the current load is less than a precalculated threshold, and Bayesian decision theory provides the framework for the choice of thresholds. This methodology allows an explicit treatment of the trade-off between cell loss and call rejection, and of the consequences of estimation error. Further topics discussed include the robustness of the control to departures from model assumptions, its performance relative to a control possessing precise knowledge of all unknown parameters, the relationship between leaky bucket depths and buffer requirements, and the treatment of multiple call types. >

Distributed admission control

This paper describes a framework for admission control for a packet-based network where the decisions are taken by edge devices or end-systems, rather than resources within the network. The decisions are based on the results of probe packets that the end-systems send through the network, and require only that resources apply a mark to packets in a way that is load dependent. One application example is the Internet, where marking information is fed back via an ECN bit, and we show how this approach allows a rich QoS framework for flows or streams. Our approach allows networks to be explicitly analyzed, and consequently engineered.

Horizon: balancing tcp over multiple paths in wireless mesh network

There has been extensive work on network architectures that support multi-path routing to improve performance in wireless mesh networks. However, previous work uses ad-hoc design principles that cannot guarantee any network-wide performance objectives such as conjointly maximizing resource utilization and improving fairness. In parallel, numerous theoretical results have addressed the issue of optimizing a combined metric of network utilization and fairness using techniques based on back-pressure scheduling, routing and flow control. However, the proposed theoretical algorithms are extremely difficult to implement in practice, especially in the presence of the 802.11 MAC and TCP. We propose Horizon, a novel system design for multi-path forwarding in wireless meshes, based on the theoretical results on back-pressure. Our design works with an unmodified TCP stack and on top of the existing 802.11 MAC. We modified the back-pressure approach to obtain a simple 802.11-compatible packet-forwarding heuristic and a novel, light-weight path estimator, while maintaining global optimality properties. We propose a delayed reordering algorithm that eliminates TCP timeouts while keeping TCP packet reordering to a minimum. We have evaluated our implementation on a 22-node testbed. We have shown that Horizon effectively utilizes available resources (disjoint paths). In contrast to previous work, our design not only avoids bottlenecks but also optimally load-balances traffic across them when needed, improving fairness among competing flows. To our knowledge, Horizon is the first practical wireless system based on back-pressure.

Rethinking Indoor Wireless Mesh Design: Low Power, Low Frequency, Full-Duplex

Existing indoor WiFi networks in the 2.5GHz and 5 GHz use too much transmit power, needed because the high carrier frequency limits signal penetration and connectivity. Instead, we propose a novel indoor wireless mesh design paradigm, based on Low Frequency, using the newly freed white spaces previously used as analogue TV bands, and Low Power - 100 times less power than currently used. Preliminary experiments show that this maintains a similar level of connectivity and performance to existing networks. It also yields more uniform connectivity, thus simplifies MAC and routing protocol design. We also advocate full-duplex networking in a single band, which becomes possible in this setting (because we operate at low frequencies). It potentially doubles the throughput of each link and eliminates hidden terminals.

Path selection and multipath congestion control

In this paper we investigate the potential benefits of coordinated congestion control for multipath data transfers, and contrast with uncoordinated control. For static random path selections, we show the worst-case throughput performance of uncoordinated control behaves as if each user had but a single path (scaling like log(log(N))/log(N) where N is the system size, measured in number of resources). Whereas coordinated control gives a throughput allocation bounded away from zero, improving on both uncoordinated control and on the greedy-least loaded path selection of e.g. Mitzenmacher. We then allow users to change their set of routes and introduce the notion of a Nash equilibrium. We show that with RTT bias (as in TCP Reno), uncoordinated control can lead to inefficient equilibria. With no RTT bias, both uncoordinated or coordinated Nash equilibria correspond to desirable welfare maximising states. Moreover, simple path reselection polices that shift to paths with higher net benefit can find these states.

Optimal Control and Trunk Reservation in Loss Networks

Consider a stochastic loss network, where calls or customer types arrive and have to find a path through the network to a given destination, and where our aim is to maximize the gain (suitably defined) from the network. In general there will be a number of paths available, and when a call arrives the two questions to answer are first, should the call be accepted, and secondly, if it is accepted which route should it take? The answer to the first question is in some sense harder than the second, and all dynamic routing or control policies have some explicit or implicit mechanism for rejecting calls and so answer the question in some way.

Differential QoS and pricing in networks: where flow control meets game theory

This paper looks at ways of providing quality of service (QoS) to users, based on a simple pricing scheme. It is primarily aimed at elastic traffic, and it is users rather than the network who define the flow control schemes. A framework for assessing schemes and algorithms via a distributed game is presented.

Path Selection and Multipath Congestion Control

In this paper we investigate the potential benefits of coordinated congestion control for multipath data transfers, and contrast with uncoordinated control. For static random path selections, we show the worst-case throughput performance of uncoordinated control behaves as if each user had but a single path (scaling like log(log(N))/log(N) where N is the system size, measured in number of resources). Whereas coordinated control gives a throughput allocation bounded away from zero, improving on both uncoordinated control and on the greedy-least loaded path selection of e.g. Mitzenmacher. We then allow users to change their set of routes and introduce the notion of a Nash equilibrium. We show that with RTT bias (as in TCP Reno), uncoordinated control can lead to inefficient equilibria. With no RTT bias, both uncoordinated or coordinated Nash equilibria correspond to desirable welfare maximising states. Moreover, simple path reselection polices that shift to paths with higher net benefit can find these states.

Combining Multipath Routing and Congestion Control for Robustness

Flexible routing schemes mitigate some of the problems associated with uncertain traffic patterns and workloads by making the exact location of capacity less important: if there is available capacity the routing scheme will find it. In this paper we propose a combined multipath routing and congestion control architecture that can provide performance improvements to the end user and simplifies network dimensioning for operators. We describe a flow-level model, able to handle streaming and file transfer traffic, with stochastic arrivals, and look at a fluid limit. We describe a congestion controller and path selection algorithm that automatically balances traffic across the lowest cost paths, and we suggest ways in which just two paths may be used, with a random selection policy. A notable feature of a multipath congestion controller is that it cannot be tuned to a single RTT, hence it differs from standard TCP with respect to RTT bias. We show that under certain conditions the allocation of flows to paths is optimal and independent of the flow control algorithm used. Scalability of the architecture results from implementing the algorithms at end-systems. We illustrate by examples how such an approach can halve response times and double the load that a network can carry.