Results 1  10
of
54
FAST TCP: Motivation, Architecture, Algorithms, Performance
, 2004
"... We describe FAST TCP, a new TCP congestion control algorithm for highspeed longlatency networks, from design to implementation. We highlight the approach taken by FAST TCP to address the four difficulties, at both packet and flow levels, which the current TCP implementation has at large windows. W ..."
Abstract

Cited by 369 (18 self)
 Add to MetaCart
(Show Context)
We describe FAST TCP, a new TCP congestion control algorithm for highspeed longlatency networks, from design to implementation. We highlight the approach taken by FAST TCP to address the four difficulties, at both packet and flow levels, which the current TCP implementation has at large windows. We describe the architecture and characterize the equilibrium and stability properties of FAST TCP. We present experimental results comparing our first Linux prototype with TCP Reno, HSTCP, and STCP in terms of throughput, fairness, stability, and responsiveness. FAST TCP aims to rapidly stabilize highspeed longlatency networks into steady, efficient and fair operating points, in dynamic sharing environments, and the preliminary results are promising.
The impact of imperfect scheduling on crosslayer congestion control in wireless networks
, 2005
"... In this paper, we study crosslayer design for congestion control in multihop wireless networks. In previous work, we have developed an optimal crosslayer congestion control scheme that jointly computes both the rate allocation and the stabilizing schedule that controls the resources at the under ..."
Abstract

Cited by 349 (32 self)
 Add to MetaCart
In this paper, we study crosslayer design for congestion control in multihop wireless networks. In previous work, we have developed an optimal crosslayer congestion control scheme that jointly computes both the rate allocation and the stabilizing schedule that controls the resources at the underlying layers. However, the scheduling component in this optimal crosslayer congestion control scheme has to solve a complex global optimization problem at each time, and is hence too computationally expensive for online implementation. In this paper, we study how the performance of crosslayer congestion control will be impacted if the network can only use an imperfect (and potentially distributed) scheduling component that is easier to implement. We study both the case when the number of users in the system is fixed and the case with dynamic arrivals and departures of the users, and we establish performance bounds of crosslayer congestion control with imperfect scheduling. Compared with a layered approach that does not design congestion control and scheduling together, our crosslayer approach has provably better performance bounds, and substantially outperforms the layered approach. The insights drawn from our analyses also enable us to design a fully distributed crosslayer congestion control and scheduling algorithm for a restrictive interference model.
A tutorial on crosslayer optimization in wireless networks
 IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
, 2006
"... This tutorial paper overviews recent developments in optimization based approaches for resource allocation problems in wireless systems. We begin by overviewing important results in the area of opportunistic (channelaware) scheduling for cellular (singlehop) networks, where easily implementable my ..."
Abstract

Cited by 248 (29 self)
 Add to MetaCart
This tutorial paper overviews recent developments in optimization based approaches for resource allocation problems in wireless systems. We begin by overviewing important results in the area of opportunistic (channelaware) scheduling for cellular (singlehop) networks, where easily implementable myopic policies are shown to optimize system performance. We then describe key lessons learned and the main obstacles in extending the work to general resource allocation problems for multihop wireless networks. Towards this end, we show that a cleanslate optimization based approach to the multihop resource allocation problem naturally results in a “loosely coupled” crosslayer solution. That is, the algorithms obtained map to different layers (transport, network, and MAC/PHY) of the protocol stack are coupled through a limited amount of information being passed back and forth. It turns out that the optimal scheduling component at the MAC layer is very complex and thus needs simpler (potentially imperfect) distributed solutions. We demonstrate how to use imperfect scheduling in the crosslayer framework and describe recently developed distributed algorithms along these lines. We conclude by describing a set of open research problems.
Joint rate control and scheduling in multihop wireless networks
 IN PROCEEDINGS OF IEEE CONFERENCE ON DECISION AND CONTROL
, 2004
"... We study the joint problem of allocating data rates and finding a stabilizing scheduling policy in a multihop wireless network. We propose a dual optimization based approach through which the rate control problem and the scheduling problem can be decomposed. We demonstrate via both analytical and n ..."
Abstract

Cited by 159 (13 self)
 Add to MetaCart
(Show Context)
We study the joint problem of allocating data rates and finding a stabilizing scheduling policy in a multihop wireless network. We propose a dual optimization based approach through which the rate control problem and the scheduling problem can be decomposed. We demonstrate via both analytical and numerical results that the proposed mechanism can fully utilize the capacity of the network, maintain fairness, and improve the quality of service to the users.
Layering as optimization decomposition
 PROCEEDINGS OF THE IEEE
, 2007
"... Network protocols in layered architectures have historically been obtained on an ad hoc basis, and many of the recent crosslayer designs are conducted through piecemeal approaches. They may instead be holistically analyzed and systematically designed as distributed solutions to some global optimiza ..."
Abstract

Cited by 63 (23 self)
 Add to MetaCart
Network protocols in layered architectures have historically been obtained on an ad hoc basis, and many of the recent crosslayer designs are conducted through piecemeal approaches. They may instead be holistically analyzed and systematically designed as distributed solutions to some global optimization problems. This paper presents a survey of the recent efforts towards a systematic understanding of “layering ” as “optimization decomposition”, where the overall communication network is modeled by a generalized Network Utility Maximization (NUM) problem, each layer corresponds to a decomposed subproblem, and the interfaces among layers are quantified as functions of the optimization variables coordinating the subproblems. There can be many alternative decompositions, each leading to a different layering architecture. This paper summarizes the current status of horizontal decomposition into distributed computation and vertical decomposition into functional modules such as congestion control, routing, scheduling, random access, power control, and channel coding. Key messages and methods arising from many recent work are listed, and open issues discussed. Through case studies, it is illustrated how “Layering as Optimization Decomposition” provides a common language to think
Fast tcp: From theory to experiments
 IEEE Network
, 2005
"... he congestion control algorithm in the current TCP has performed remarkably well and is generally believed to have prevented severe congestion as the Internet scaled up by six orders of magnitude in size, speed, load, and connectivity in the last 15 years. It is also well known, however, that as ban ..."
Abstract

Cited by 48 (9 self)
 Add to MetaCart
(Show Context)
he congestion control algorithm in the current TCP has performed remarkably well and is generally believed to have prevented severe congestion as the Internet scaled up by six orders of magnitude in size, speed, load, and connectivity in the last 15 years. It is also well known, however, that as bandwidthdelay product continues to grow, the current TCP implementation will eventually become a performance bottleneck. In this article we describe a different congestion control algorithm for TCP, called FAST [1]. FAST TCP has three key differences. First, it is an equationbased algorithm and hence eliminates packetlevel oscillations. Second, it uses queuing delay as the primary measure of congestion, which can be more reliably measured by end hosts than loss probability in fast longdistance networks. Third, it has stable flow dynamics and achieves weighted proportional fairness in equilibrium that does not penalize long flows, as the current congestion control algorithm does. Alternative approaches are described in [2–6]. The details of the architecture, algorithms, extensive experimental evaluations of FAST TCP, and comparison with other TCP variants can be found in [1, 7]. In this article we highlight the motivation, background theory, implementation, and our first major experimental results. The scientific community is singular in its urgent need for efficient highspeed data transfer. We explain why this community has been driving the development and deployment of ultrascale networking. The design of FAST TCP builds on an emerging theory that allows us to understand the equilibrium and stability properties of large networks under endtoend control. It provides a framework to understand issues, clarify ideas, and suggest directions, leading to a more robust and better performing design. We summarize this theory and explain FAST TCP. We report the results of our first global experiment and conclude the article.
Impact of stochastic noisy feedback on distributed network utility maximization
 in INFOCOM 2007
, 2007
"... Abstract — The implementation of distributed network utility maximization (NUM) algorithms hinges heavily on information feedback through message passing among network elements. In practical systems the feedback is often obtained using errorprone measurement mechanisms and suffers from random errors ..."
Abstract

Cited by 30 (4 self)
 Add to MetaCart
(Show Context)
Abstract — The implementation of distributed network utility maximization (NUM) algorithms hinges heavily on information feedback through message passing among network elements. In practical systems the feedback is often obtained using errorprone measurement mechanisms and suffers from random errors. In this paper, we investigate the impact of noisy feedback on distributed NUM. We first study the distributed NUM algorithms based on the Lagrangian dual method, and focus on the primaldual (PD) algorithm, which is a single timescale algorithm in the sense that the primal and dual parameters are updated simultaneously. Assuming strong duality, we study both cases when the stochastic gradients are unbiased or biased, and develop a general theory on the stochastic stability of the PD algorithms in the presence of noisy feedback. When the gradient estimators are unbiased,
RateBased versus QueueBased Models of Congestion Control
 in Proceedings of ACM SIGMETRICS
, 2004
"... Mathematical models of congestion control capture the congestion indication mechanism at the router in two different ways: ratebased models, where the queuelength at the router does not explicitly appear in the model, and queuebased models, where the queue length at the router is explicitly a p ..."
Abstract

Cited by 30 (3 self)
 Add to MetaCart
(Show Context)
Mathematical models of congestion control capture the congestion indication mechanism at the router in two different ways: ratebased models, where the queuelength at the router does not explicitly appear in the model, and queuebased models, where the queue length at the router is explicitly a part of the model. Even though most congestion indication mechanisms use the queue length to compute the packet marking or dropping probability to indicate congestion, we argue that, depending upon the choice of the parameters of the AQM scheme, one would obtain a ratebased model or a rateandqueuebased model as the deterministic limit of a stochastic system with a large number of users.
Catching the ‘Network Science’ Bug: Insight and Opportunities for the Operations Researchers
 Operations Research
, 2009
"... Accepted for publication by ..."
(Show Context)
On the stability region of congestion control
 Proceedings of Allerton Conference
, 2004
"... Abstract It is well known that congestion control can be viewed as a distributed iterative algorithm solving a global optimization problem that maximizes the total system utility. In this paper, we study the stability region of a network employing congestion control algorithms derived from such an ..."
Abstract

Cited by 16 (0 self)
 Add to MetaCart
(Show Context)
Abstract It is well known that congestion control can be viewed as a distributed iterative algorithm solving a global optimization problem that maximizes the total system utility. In this paper, we study the stability region of a network employing congestion control algorithms derived from such an optimization framework. Previous work in the literature typically adopts a timescale separation assumption, which assumes that, whenever the number of users in the system changes, the data rates of the users are adjusted instantaneously to the optimal rate allocation computed by the global optimization problem. Under this assumption, it has been shown that such rate allocation policies can achieve the largest possible stability region. However, this timescale separation assumption, although technically convenient, rarely holds in practice. In this paper, we remove this timescale separation assumption and show that the largest possible stability region can still be achieved by a large class of congestion control algorithms derived from the optimization framework. Our result provides new insights on the performance implication of congestion control and on the choices of the parameters of the congestion controller.