-
Computer Networks. 01/2012; 56:745-761.
-
IEEE Trans. Mob. Comput. 01/2009; 8:1384-1396.
-
17th International Workshop on Quality of Service, IWQoS 2009, Charleston, South Carolina, USA, 13-15 July 2009.; 01/2009
-
[show abstract]
[hide abstract]
ABSTRACT: The definition of TCP friendliness has been evolved over time from the traditional one for congestion control protocols to the recent ones for admission control protocols. All of them can effectively prevent the Internet from congestion collapse and TCP starvation, while enabling a wide variety of traffic control protocols other than TCP. However, the current TCP-friendly admission control protocols are designed to be TCP friendly only on fairly long time scales. That is, it is likely that a group of TCP users all experience persistent poor performance during their transmission, which then leads to dissatisfaction of TCP users. In this paper, we first present a new definition of TCP friendliness, called Stochastic TCP Friendliness, with which we study the time scale of TCP-friendly admission control protocols. Second, we develop a new traffic control protocol, called Stochastically TCP- Friendly Admission Control (STFAC), which is stochastically TCP friendly not only on a long time scale but also on a short time scale. Finally, we present very encouraging simulation results showing that STFAC can considerably improve the performance of UDP users and TCP users on both a long time scale and a short time scale, when compared with the traditional TCP- friendly congestion control protocols.
Communications, 2008. ICC '08. IEEE International Conference on; 06/2008
-
Operating Systems Review. 01/2008; 42:64-74.
-
Proceedings of the 16th annual IEEE International Conference on Network Protocols, 2008. ICNP 2008, Orlando, Florida, USA, 19-22 October 2008; 01/2008
-
[show abstract]
[hide abstract]
ABSTRACT: Window growth function for congestion control is a strong determinant of protocol behaviors, especially its second and higher-order behaviors associated with the distribution of transmission rates, its variances, and protocol stability. This paper presents a new stochastic tool, called convex ordering, that provides an ordering of any convex function of transmission rates of two protocols and valuable insights into high order behaviors of protocols. As the ordering determined by this tool is consistent with any convex function of rates, it can be applied to any unknown metric for protocol performance that consists of some high-order moments of transmission rates, as well as those already known such as rate variance. Using the tool, it is analyzed that a protocol with a growth function that starts off with a concave function and then switches to a convex function (e.g., an odd order function such as x<sup>3</sup> and x<sup>5</sup>) around the maximum window size in the previous loss epoch, gives the smallest rate variation under a variety of network conditions. Among existing protocols, BIC and CUBIC have this window growth function. Experimental and simulation results confirm the analytical findings.
INFOCOM 2007. 26th IEEE International Conference on Computer Communications. IEEE; 06/2007
-
IEEE/ACM Trans. Netw. 01/2007; 15:852-865.
-
Proceedings of the 7th ACM Interational Symposium on Mobile Ad Hoc Networking and Computing, MobiHoc 2006, Florence, Italy, May 22-25, 2006; 01/2006
-
Proceedings of the ACM SIGCOMM 2005 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications, Philadelphia, Pennsylvania, USA, August 22-26, 2005; 01/2005
-
[show abstract]
[hide abstract]
ABSTRACT: High-speed networks with large delays present a unique environment where TCP may have a problem utilizing the full bandwidth. Several congestion control proposals have been suggested to remedy this problem. The existing protocols consider mainly two properties: TCP friendliness and bandwidth scalability. That is, a protocol should not take away too much bandwidth from standard TCP flows while utilizing the full bandwidth of high-speed networks. This work presents another important constraint, namely, RTT (round trip time) unfairness where competing flows with different RTTs may consume vastly unfair bandwidth shares. Existing schemes have a severe RTT unfairness problem because the congestion window increase rate gets larger as the window grows ironically the very reason that makes them more scalable. RTT unfairness for high-speed networks occurs distinctly with drop tail routers for flows with large congestion windows where packet loss can be highly synchronized. After identifying the RTT unfairness problem of existing protocols, This work presents a new congestion control scheme that alleviates RTT unfairness while supporting TCP friendliness and bandwidth scalability. The proposed congestion control algorithm uses two window size control policies called additive increase and binary search increase. When the congestion window is large, additive increase with a large increment ensures square RTT unfairness as well as good scalability. Under small congestion windows, binary search increase supports TCP friendliness. The simulation results confirm these properties of the protocol.
INFOCOM 2004. Twenty-third AnnualJoint Conference of the IEEE Computer and Communications Societies; 04/2004
-
[show abstract]
[hide abstract]
ABSTRACT: Wavelength-division multiplexing appears to be the solution of
choice for providing a faster networking infrastructure that can meet
the explosive growth of the Internet. Several different technologies
have been developed so far for the transfer of data over WDM. We survey
two new technologies which are still in the experimental stage-optical
packet switching and optical burst switching-and comment on their
suitability for transporting IP traffic
IEEE Communications Magazine 02/2001; · 3.79 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Wavelength-division multiplexing (WDM) appears to be the solution of choice for providing a faster networking infrastructure that can meet the explosive growth of the Internet. Several different technologies have been developed so far for the transfer of data over WDM, with wavelength routing being the most prominent one. In this paper, we survey two new technologies which are still in their experimental stage, namely, optical packet switching and optical burst switching. We also comment on the suitability of these two technologies for transporting IP traffic.
01/2001;
-
[show abstract]
[hide abstract]
ABSTRACT: Optical networks appear to be the solution of choice for providing a faster networking infrastructure that can meet the explosive growth of the Internet. One of the key issues that needs to be addressed is how optical networks can be used to carry IP traffic. In this paper, we survey some of the techniques that have been proposed in the literature for transporting IP traffic over an optical network. Specifically, we survey techniques for IP over SONET, optical packet switch architectures, and optical burst switching. - 2 - 1. Introduction The explosive growth of the Internet has given rise to the need for faster transfer techniques. Optical transport networks appears to be the solution of choice. One of the key issues that needs to be addressed is how can optical networks be used to carry IP traffic. In this paper, we review some of the techniques that have been proposed in the literature for IP over light, that is, for transporting IP traffic over an optical transport network. SON...
02/1970;
-
[show abstract]
[hide abstract]
ABSTRACT: Window growth function for congestion control is a strong determinant of protocol behaviors, especially its second and higher-order behaviors associated with the distribution of transmission rates, its variances, and protocol stability. This paper presents a new stochastic tool, called convex ordering, that provides an ordering of any convex function of transmission rates of two multiplicative-decrease protocols and valuable insights into high-order behaviors of protocols. As the ordering determined by this tool is consistent with any convex function of rates, it can be applied to any unknown metric for protocol performance that consists of some high-order moments of transmission rates, as well as those already known such as rate variance. Using the tool, it is analyzed that a protocol with a growth function that starts off with a concave function and then switches to a convex function (e.g., an odd order function such as x3 and x5) around the maximum window size in the previous loss epoch, gives the smallest rate variation under a variety of network conditions. Among existing protocols, BIC and CUBIC have this window growth function. Experimental and simulation results confirm the analytical findings.
Computer Networks.
-
[show abstract]
[hide abstract]
ABSTRACT: This paper examines the effect of background traffic on the performance of existing high-speed TCP variant protocols, namely BIC-TCP, CUBIC, FAST, HSTCP, H-TCP and Scalable TCP. We demonstrate that the stability, link utilization, convergence speed and fairness of the protocols are clearly affected by the variability of flow sizes and round-trip times (RTTs), and the amount of background flows competing with high-speed flows in a bottleneck router. Our findings include: (1) the presence of background traffic with variable flow sizes and RTTs improves the fairness of most high-speed protocols, (2) all protocols except FAST and HSTCP show good intra-protocol fairness regardless of the types of background traffic, (3) HSTCP needs a larger amount of background traffic and more variable traffic than the other protocols to achieve convergence, (4) H-TCP trades stability for fairness; that is, while its fairness is good independent of background traffic types, larger variance in the flow sizes and RTTs of background flows causes the protocol to induce a higher degree of global loss synchronization among competing flows, lowering link utilization and stability, (5) FAST suffers unfairness and instability in small buffer or long delay networks regardless of background traffic types, and (6) the fairness of high-speed protocols depends more on the amount of competing background traffic rather than its rate variability. We also find that the presence of high-speed flows does not greatly reduce the bandwidth usage of background Web traffic.
Computer Networks.
-
[show abstract]
[hide abstract]
ABSTRACT: A randomized dining philosophers algorithm is presented for a realistic semi-synchronous model where message delays vary within an unknown bound, and clocks may run at a different speed without any synchronization. In order to predict the unknown bounds, the algorithm employs a simple network delay measurement technique. The algorithm has an expected running time and message complexity of ¢ ¡ ¤ £ ¦ ¥ with high probability. £ is the maximum number of contenders for a process in the system (while © , © being the total number of processes). A version of the algorithm, called DRAND, is shown to be used for TDMA scheduling or channel assignment for wireless networks. This algorithm is the first scalable implementation of RAND, a commonly used, centralized channel assignment algorithm. The algorithm can also be used for distributed graph coloring in a semi-synchronous environment. Given any general graph, the algorithm produces a chromatic number up to £ (in this case, £ is the maximum number of edges). Compared to existing algorithms on distributed graph coloring in the PRAM model, the algorithm can generate equal or less number of colors; often, far less than £ . DRAND is implemented in TinyOS and tested in a real wireless sensor network with Mica2 nodes. The experiment shows that DRAND is scalable and robust in a real wireless network setting.
