Congestion Control Protocol Research Articles

Congestion Control With Multipacket Feedback

Many congestion control protocols use explicit feedback from the network to achieve high performance. Most of these either require more bits for feedback than are available in the IP header or incur performance limitations due to inaccurate congestion feedback. There has been recent interest in protocols that obtain high-resolution estimates of congestion by combining the explicit congestion notification (ECN) marks of multiple packets, and using this to guide multiplicative increase, additive increase, multiplicative decrease (MI-AI-MD) window adaptation. This paper studies the potential of such approaches, both analytically and by simulation. The evaluation focuses on a new protocol called Binary Marking Congestion Control (BMCC). It is shown that these schemes can quickly acquire unused capacity, quickly approach a fair rate distribution, and have relatively smooth sending rates, even on high bandwidth-delay product networks. This is achieved while maintaining low average queue length and negligible packet loss. Using extensive simulations, we show that BMCC outperforms XCP, VCP, MLCP, CUBIC, CTCP, SACK, and in some cases RCP, in terms of average flow completion times. Suggestions are also given for the incremental deployment of BMCC.

An Energy Efficient and Cooperative Congestion Control Protocol in MANET

ABSTRAC This paper presents an energy efficient and cooperative congestion control protocol to control the congestion in mobile adhoc networks (MANETs). The proposed scheme overcomes the disadvantages of existing multicast congestion control protocols which depend on individual receivers to detect congestion and adjust their receiving rates. In the first phase of the proposed protocol, it builds a cooperative multicast tree rooted at the source, by including the nodes with higher residual energy towards the receivers. In the second phase of the proposed protocol, it proposes an admission control scheme in which a cooperative multicast flow is admitted or rejected depending upon on the output queue size. In the third phase of the proposed protocol, it proposes a scheme which tests whether the relay node has the potential path to the required destination, if not then choose the another node which has the second most highest residual energy as a new relay node. That is more generally introduction of cooperativeness and making it. In the fourth phase, we propose a scheme which adjusts the multicast traffic rate at each bottleneck of a multicast tree. Because of the on-the-spot information collection and rate control, this scheme has very limited control traffic overhead and delay. Moreover, the proposed scheme does not impose any significant changes on the queuing, scheduling or forwarding policies of existing networks. Simulation results shows that the proposed protocol has better delivery ratio and throughput with less delay and energy consumption when compared with existing protocol.

Robust and fair Multicast Congestion Control (M2C)

Since 1995 and the Receiver-driven Layered Multicast (RLM) protocol, numerous multicast congestion control protocols have been proposed, such as RLC, FLID-SL, FLID-DL and finally the WEBRC protocol. However these protocols suffer from some limitations and have not been extensively experimented on a wide range of network conditions. This article presents the Multicast Congestion Control (M2C) protocol, which is based on a dynamic layer mechanism and a congestion window mechanism for each receiver. M2C is designed to be TCP-friendly and to fairly share the bandwidth when competing with unicast and multicast streams.To reduce simulation approximations and to carry out extensive evaluations over the Internet we implemented M2C and several other multicast congestion control protocols. The experiments reveal interesting network behaviors, such as the join time latency problem, that simulations and local testbeds had not revealed before. We evaluated the impact of this latency on the state of the art protocols. Focusing on WEBRC and M2C, we have then defined and run a validation benchmark to qualify their behavior in terms of fairness and convergence time. These experiments show M2C robustness and good behavior for the mentioned metrics and its improvements compared to WEBRC. Furthermore, we have analyzed the signaling overhead of these protocols.Thus, M2C is an efficient multicast congestion control with an open source implementation which is easily usable by multicast applications, such as file transfer or video streaming.

An Energy Efficient and Cooperative Congestion Control Protocol in MANET

MANET is collection of mobile devices form a self-creating, self-organizing and self-administering wireless networks. Due to mobility of nodes it is not possible to establish fixed paths for message delivery through the network. Hence, congestion is happening and it is the key problem for MANET. Many routing protocols have been proposed to overcome the congestion in MANET. One of the popular routing protocol is AODV, but it depends on individual receivers to detect congestion and adjust their receiving rates. Another common routing protocol is EERCCP, which is better than AODV but sometimes it fails when link failure happens to relay node or if relay node moves from its current group to another group then there is no other mechanism to select an alternative relay nodes i.e. lack of cooperativeness. Consequently, we proposed a routing protocol named as EECCCP, which utilizes user cooperation to reduce congestion. The proposed energy efficient and cooperative congestion control routing protocol (EECCCP), performs well better than both the AODV and EERCCP. The proposed scheme encorporates the benefits of energy efficiency and cooperativeness which in turn reduces the congestion effectively. It also overcomes the disadvantages of existing multicast congestion control protocol. Moreover, the proposed scheme does not impose any significant changes on the queuing, scheduling or forwarding policies of existing network protocols. The simulation results have shown that our proposed protocol EECCCP has the about 95% better delivery ratio and throughput with about 85 % less delay and energy consumption when compared with the existing protocol AODV. It also has the about 65% better delivery ratio and throughput with about 60 % less delay and energy consumption when compared with the existing protocol EERCCP.

OLMRP: Hierarchical Outflow Load-balancing Multicast Routing Protocol for congestion control in Ad hoc Networks

This paper, proposes a new multicast routing protocol for mobile ad hoc networks that handles the congestion to improve the Quality of routing service. Part of the proposed protocol introduced a MAC layer level solution called Group Level Multicasting (GLM) that effectively handles the multicasting at one hop level mesh or tree. The proposed model controls the congestion in hierarchical order to minimize the resource utilization. Limited bandwidth and a high degree of mobility require that routing protocols for ad hoc networks be adaptive, trouble-free, and energy saving. This paper proposed a new Hierarchical Outflow Loadbalancing Multicast Routing Protocol (OLMRP) for Ad hoc networks, which handles congestion state. OLMR is capable to adapt a mesh or tree structure with enhanced similar resilience against mobility. OLMRP utilizes GLM to reduce the overhead of route failure recovery, improve route efficiency and reduce data transmissions. The simulation results show that OLMR handles congestion with reduced control overhead in various environments,also the improved packet delivery ratio.

Comparison of High Speed Congestion Control Protocols

Congestion control limits the quantity of information input at a rate less important than that of the transmission one to ensure good performance as well as protect against overload and blocking of the network. Researchers have done a great deal of work on improving congestion control protocols, especially on high speed networks. In this paper, we will be studying the congestion control alongside low and high speed congestion control protocols. We will be also simulating, evaluating, and comparing eight of high speed congestion control protocols : Bic TCP, Cubic TCP, Hamilton TCP, HighSpeed TCP, Illinois TCP, Scalable TCP, Compound TCP and YeAH TCP, with multiple flows.

Finishing flows quickly with preemptive scheduling

Today's data centers face extreme challenges in providing low latency. However, fair sharing, a principle commonly adopted in current congestion control protocols, is far from optimal for satisfying latency requirements. We propose Preemptive Distributed Quick ( PDQ ) flow scheduling, a protocol designed to complete flows quickly and meet flow deadlines. PDQ enables flow preemption to approximate a range of scheduling disciplines. For example, PDQ can emulate a shortest job first algorithm to give priority to the short flows by pausing the contending flows. PDQ borrows ideas from centralized scheduling disciplines and implements them in a fully distributed manner, making it scalable to today's data centers. Further, we develop a multipath version of PDQ to exploit path diversity. Through extensive packet-level and flow-level simulation, we demonstrate that PDQ significantly outperforms TCP, RCP and D 3 in data center environments. We further show that PDQ is stable, resilient to packet loss, and preserves nearly all its performance gains even given inaccurate flow information.

An ergodic AIMD algorithm with application to high-speed networks

In this article we propose a version of the Additive-Increase Multiplicative-Decrease (AIMD) algorithm that provides a suitable basis to develop congestion control protocols that can be deployed in both conventional and high-speed communication networks. Our algorithm retains many of the properties of the standard AIMD algorithm. However, unlike other non-standard AIMD algorithms, our scheme can be shown to be ergodic under very general assumptions.

A DCCP Variant for High Speed Networks

The Datagram Congestion Control Protocol (DCCP) protocol was proposed to provide a great variety of functionality to real-time applications. Its congestion control mechanisms were defined to be friendly to the TCP-Reno, which makes its operation inappropriate to high speed networks. In this paper, a variant of the DCCP, called FAST DCCP, is proposed to overcome such deficiency. As evidenced by experimental evaluation as well as by simulation, the new protocol scales with the increase of network capacity.

Asymptotic Stability Analysis of E-speed Start Congestion Control Protocol for TCP

All the proposed window based congestion control protocols use a single slow start algorithm. It has been shown in literature that slow start inefficiently utilizes bandwidth in a network with high bandwidth delay product (BDP). A multiple startup algorithm (E- speed start) was proposed in this work. E-speed start specifies a multiple selectable startup for Transmission Control Protocol (TCP). It is proposed that startup speed for TCP be selectable from n-arry startup algorithms. In E-speed start, a binary start was implemented based on a calculated value β which depends on the available bandwidth and other network conditions. A model for E- speed start was derived using utility maximization theory and the principle of decentralised solution. The model derived was shown to be stable by linear approximation, Laplace transform and by using the concept of Nyquist Stability criterion.

On the quality of VoIP with DCCP for satellite communications

SUMMARYWe present experimental results for the performance of selected voice codecs using Datagram Congestion Control Protocol (DCCP) with CCID4 congestion control over a satellite link. We evaluate the performance of both constant and variable data rate speech codecs for a number of simultaneous calls using the ITU E‐model. We analyse the sources of packet losses and additionally analyse the effect of jitter, which is one of the crucial parameters contributing to Voice over IP (VoIP) quality and has, to the best of our knowledge, not been considered previously in the published DCCP performance results. We propose modifications to the CCID4 algorithm and demonstrate how these improve the VoIP performance, without the need for additional link information other than what is already monitored by CCID4. We also demonstrate the fairness of the proposed modifications to other flows. Although the recently adopted changes to TCP‐Friendly Rate Control specification alleviate some of the performance issues for VoIP on satellite links, we argue that the characteristics of commercial satellite links necessitate consideration of further improvements. We identify the additional benefit of DCCP when used in VoIP admission control mechanisms and draw conclusions about the advantages and disadvantages of the proposed DCCP/CCID4 congestion control mechanism for use with VoIP applications. Copyright © 2012 John Wiley & Sons, Ltd.

Usage of Variable Structure Congestion Control Protocol (VCP) in Buffer Overflow Attack Blocker

In this paper, we proposed the usage of “Variable Structure Congestion Control Protocol” in network communication to avoid Buffer Overflow thereby preventing Buffer Overflow Attacks. In general transferring a signal between connected Clients are done through “Transmission Control Protocol” in which only two states are clearly shown i.e. either “0” or “1”. For successful transmission “1” is represented and for failure transmission “0” is represented during transmission process. In “Variable Structure Congestion Control Protocol “there are four possible states for representing the signal transmission. They are “00, 01, 10, and 11”. Through VCP the signal transmission can be classified as “Low load region”, “High load region” and “Overload region” from which the transmission load can be monitored thereby preventing “Buffer Overflow” in network transmission. Round Trip Time (RTT) and Round Trip Time Timeout (RTO) have been calculated together with VCP to prevent buffer overflow attack during signal transmissions.

Modified Fast Recovery Algorithm for Performance Enhancement of TCP-NewReno

One of the keys to the success of the Internet is relying on using efficient congestion control mechanisms. Congestion control is required not only to prevent congestion collapse in the network, but also to improve network utilization. Without congestion control, a sending node may continue transmitting packets that may be dropped later due to congestion collapse. This paper presents a modified fast recovery algorithm to enhance the performance of the most widespread congestion control protocol; TCP-NewReno. The proposed mechanism is evaluated by using the network simulator NS-2 and compared with both the TCP-NewReno and the TCP-Reno. The simulation results show that the proposed mechanism improves the performance of the TCP-NewReno against throughput and packet delay.

Performance Evaluation of High Speed Congestion Control Protocols

Computer networks are facing several technological and scientific challenges. Among these challenges is congestion control. It limits the quantity of information input at a rate less important than that of the transmission one to ensure good performance as well as protect against overload and blocking of the network. Researchers have done a great deal of work on improving congestion control protocols, especially on high speed networks. In this paper, we will be studying the congestion control alongside low and high speed congestion control protocols. We will be also simulating, evaluating, and comparing seven of high speed congestion control protocols : Bic TCP, Cubic TCP, Hamilton TCP, HighSpeed TCP, Illinois TCP, Scalable TCP and YeAH TCP, with multiple flows.

An Improvement on TCP Congestion Control Protocol for Next Generation Networks

An Improvement on TCP Congestion Control Protocol for Next Generation Networks

Fair congestion control over wireless multihop networks

Over wireless multihop networks, the conventional transmission control protocol (TCP) cannot allocate the bandwidth fairly to flows. This is because flows with different locations competing for the same wireless channel may have very different perceptions on congestion in terms of packet delay and packet loss rate. In this study, the authors introduce a new window control algorithm and a new estimation method of congestion, which is called a delay information-based fair congestion control protocol (DFCCP). A new window control algorithm not only supports starved flows, but also allows starved flows to share the bandwidth fairly. Furthermore, since congestion occurs at multiple nodes over wireless multihop networks, the authors detect the level of congestion based on the summation of the average window sizes of multiple flows. The simulation results show that the proposed algorithm supports the starved flows while providing fairness among flows over wireless multihop networks.

Improved video streaming scheme for internet television with broadband wireless access

Internet television video–streaming schemes do not respond well when access is through a broadband wireless link. A simple but effective negative acknowledgment–based scheme has been designed to meet the needs of Internet television. When used with broadband wireless access, simulations show that the scheme has the better features of both raw UDP transport and the standardised Datagram Congestion Control Protocol but does not have those protocols' disadvantages. The delivered video quality is also found to be superior to multiple–connection, congestion–controlled streaming. This is important for mobile video delivery, as video quality is a key determinant of customer choice.

Throughput–smoothness tradeoff in preventing competing TCP from starvation

In this paper, we systematically study and demonstrate a fundamental tradeoff for TCP friendliness: in order for a congestion control protocol to maintain a certain degree of TCP friendliness, the longer its smoothness timescale is, the lower its average rate should be. Specifically, we derive the TCP-friendly rate requirements for three different smoothness timescales (i.e., milliseconds, seconds, and minutes) with flow-level queueing models, and verify the analytical results with extensive packet-level simulation results. Our flow-level queueing models indicate that the fundamental reason of the throughput–smoothness tradeoff is that TCP arrivals have different characteristics on different timescales. Finally, we propose a new TCP-friendly congestion control protocol for applications that prefer a smooth predictable rate on a multi-minute timescale, called Long-Time-Scale TCP-Friendly CBR-Like Rate Control (L-TFCBR).

Stochastic TCP friendliness: Expanding the design space of TCP-friendly traffic control protocols

While the current definition of TCP friendliness has enabled a wide variety of traffic control protocols other than TCP, it still considerably restricts the design space of TCP-friendly traffic control protocols. For example, some multimedia streaming applications prefer a smooth sending rate on a time scale of tens of seconds, however, a UDP flow maintaining such a long smoothness time scale is naturally not TCP friendly by the current definition. In this paper, we propose an innovative method to relatively compare the degrees of TCP friendliness of different traffic control protocols, and use it to define a new class of TCP friendliness definitions, called stochastic TCP friendliness (STF). STF greatly expands the design space of TCP-friendly traffic control protocols, while still effectively maintaining the desired fairness of the Internet. To demonstrate the expanded design space, we also develop a new congestion control protocol, called TCP-friendly CBR-Like Rate Control (TFCBR), for multimedia streaming applications which do not require a high sending rate but prefer a smooth sending rate on a time scale of tens of seconds. TFCBR is stochastically TCP friendly, however, it is not TCP friendly by the current definition.

A New Estimation Scheme for the Effective Number of Users in Internet Congestion Control

Many congestion control protocols have been recently proposed in order to alleviate the problems encountered by TCP in high-speed networks and wireless links. Protocols utilizing an architecture that is in the same spirit as the ABR service in ATM networks require estimates of the effective number of users utilizing each link in the network to maintain stability in the presence of delays. In this paper, we propose a novel estimation algorithm that is based on online parameter identification techniques and is shown through analysis and simulations to converge to the effective number of users utilizing each link. The algorithm does not require maintenance of per-flow states within the network or additional fields in the packet header, and it is shown to outperform previous proposals that were based on pointwise division in time. The estimation scheme is designed independently from the control functions of the protocols and is thus universal in the sense that it operates effectively in a number of congestion control protocols. It can thus be successfully used in the design of new congestion control protocols. In this paper, to illustrate its universality, we use the proposed estimation scheme to design a representative set of Internet congestion control protocols. Using simulations, we demonstrate that these protocols satisfy key design requirements. They guide the network to a stable equilibrium that is characterized by high network utilization, small queue sizes, and max-min fairness. In addition, they are scalable with respect to changing bandwidths, delays, and number of users, and they generate smooth responses that converge quickly to the desired equilibrium.