TCP for High-Speed Networks

2008 ◽  
pp. 626-632
Author(s):  
Nelson Luís Saldanha da Fonseca ◽  
Neila Fernanda Michel
Keyword(s):  
Congestion Control ◽  
High Speed ◽  
Transmission Control Protocol ◽  
Window Size ◽  
Transport Layer ◽  
The Internet ◽  
Congestion Window ◽  
High Speed Networks ◽  
Congestion Control Mechanism ◽  
Tcp Reno

In response to a series of collapses due to congestion on the Internet in the mid-’80s, congestion control was added to the transmission control protocol (TCP) (Jacobson, 1988), thus allowing individual connections to control the amount of traffic they inject into the network. This control involves regulating the size of the congestion window (cwnd) to impose a limit on the size of the transmission window. In the most deployed TCP variant on the Internet, TCP Reno (Allman, Floyd, & Partridge, 2002), changes in congestion window size are driven by the loss of segments. Congestion window size is increased by 1/cwnd for each acknowledgement (ack) received, and reduced to half for the loss of a segment in a pattern known as additive increase multiplicative decrease (AIMD). Although this congestion control mechanism was derived at a time when the line speed was of the order of 56 kbs, it has performed remarkably well given that the speed, size, load, and connectivity of the Internet have increased by approximately six orders of magnitude in the past 15 years. However, the AIMD pattern of window growth seriously limits efficienct operation of TCP-Reno over high-capacity links, so that the transport layer is the network bottleneck. This text explains the major challenges involved in using TCP for high-speed networks and briefly describes some of the variations of TCP designed to overcome these challenges.

scholarly journals Performance Evaluation of TCP Vegas over TCP Reno and TCP NewReno over TCP Reno

2019 ◽  
Vol 3 (3) ◽  
Author(s):  
Tanjia Chowdhury ◽  
Mohammad Jahangir Alam
Keyword(s):  
Congestion Control ◽  
Error Detection ◽  
Transmission Control Protocol ◽  
Control Flow ◽  
Transport Layer ◽  
Control Mechanisms ◽  
Bottleneck Link ◽  
Tcp Vegas ◽  
Congestion Control Mechanism ◽  
Tcp Reno

In the Transport layer, there are two types of Internet Protocol are worked, namely- Transmission Control Protocol (TCP) and User datagram protocol (UDP). TCP provides connection oriented service and it can handle congestion control, flow control, and error detection whereas UDP does not provide any of service. TCP has several congestion control mechanisms such as TCP Reno, TCP Vegas, TCP New Reno, TCP Tahoe, etc. In this paper, we have focused on the behavior performance between TCP Reno and TCP Vegas, TCP New Reno over TCP Reno, when they share the same bottleneck link at the router. For instigating this situation, we used drop-tail and RED algorithm at the router and used NS-2 simulator for simulation. From the simulation results, we have observed that the performance of TCP Reno and TCP Vegas is different in two cases. In drop tail algorithm, TCP Reno achieves better Performance and throughput and act more an aggressive than Vegas. In Random Early Detection (RED) algorithm, both of congestion control mechanism provides better fair service when they coexist at the same link. TCP NewReno provides better performance than TCP Reno.

scholarly journals Enhanced Multistream Fast TCP: Rapid Bandwidth Utilization after Fast-Recovery Phase

2019 ◽  
Vol 9 (21) ◽  
pp. 4698
Author(s):  
Sarfraz Ahmad ◽  
Muhammad Junaid Arshad
Keyword(s):  
Congestion Control ◽  
High Speed ◽  
Recovery Phase ◽  
Transport Layer ◽  
Convergence Time ◽  
Transmission Protocol ◽  
Fast Recovery ◽  
Congestion Window ◽  
Fast Tcp ◽  
Network Bandwidth

The purpose of this study is to enhance the performance of Multistream Fast Transmission Control Protocol (TCP) keeping in view the recent web-based applications that are being deployed on long-range, high-speed, and high-bandwidth networks. To achieve the objective of the research study, a congestion control after fast-recovery module for congestion control scheme of Multistream Fast TCP is proposed. The module optimized the performance of the protocol by reducing the time that is required to consume the available bandwidth after a fast-recovery phase. The module is designed after studying additive-increase, multiplicative-decrease and rate-based congestion window management schemes of related transport protocols. The module adjusts the congestion window on receipt of each individual acknowledgment instead of each round trip time after the fast-recovery phase until it consumes vacant bandwidth of the network link. The module is implemented by using Network Simulator 2. Convergence time, throughput, fairness index, and goodput are the parameters used to assess the performance of proposed module. The results indicate that Enhanced Multistream Fast TCP with congestion control after fast recovery recovers its congestion window in a shorter time period as compared to multistream Fast TCP, Fast TCP, TCP New Reno, and Stream Control Transmission Protocol. Consequently, Enhanced Multistream Fast TCP consumes the available network bandwidth in lesser time and increases the throughput and goodput. The proposed module enhanced the performance of the transport layer protocol. Our findings demonstrate the performance impact in the form of a decrease in the convergence time to consume the available network bandwidth and the increase in the throughput and the goodput.

scholarly journals Dynamic Congestion Control Mechanism in Mobile Adhoc Network: TCP Westwood-DCC

2020 ◽  
Vol 8 (5) ◽  
pp. 4784-4789
Keyword(s):  
Congestion Control ◽  
Control Mechanism ◽  
Transmission Control Protocol ◽  
Link Failure ◽  
Congestion Window ◽  
Slow Start ◽  
Mobile Adhoc Network ◽  
Adhoc Network ◽  
Tcp Westwood ◽  
Congestion Control Mechanism

Transmission control protocol faces a problem of packet loss differentiation in the wireless and mobile adhoc network. Congestion control is not properly done here. It cannot manage the congestion window as per type of loss and it reduces Congestion window unnecessarily and that degrades the performance. TCP Westwood cannot identify congestion or link failure loss, and it cannot manage the congestion window as per available bandwidth. This paper discusses that TCP Westwood performs bandwidth estimation, setting up a congestion window and a slow start threshold. In mobile adhoc network, link failure may happen frequently, and it should be handled properly. Link failure can be detected with the help of retransmission timeout. Once timeout occurs Westwood performs congestion avoidance. Proposed Westwood manages three states of congestion 1) Avoidance 2) congestion and 3) No congestion, it updates congestion window and slow start threshold as per the status of network. It maintains congestion window dynamically. Network status is identified by estimated bandwidth and proportionality ratio. Proposed method is tested on NS2.35 and compared with the existing TCP variants. The proposed Westwood performs optimized link utilization and congestion control mechanism. Hence it gives significant performance for loss recovery.

Fuzzy Logic-Based Round Trip Time Scaling and Scheduling in High Speed TCP Stacks

2015 ◽  
pp. 448-461
Author(s):  
V. Kavidha ◽  
V. Sadasivam
Keyword(s):  
High Speed ◽  
Transmission Control Protocol ◽  
Window Size ◽  
Complex Problem ◽  
Round Trip Time ◽  
Round Trip ◽  
Congestion Window ◽  
Trip Time ◽  
Time Scaling ◽  
End Node

Network management and control is a complex problem that requires intelligent, control methodologies to obtain satisfactory performance. Round trip time (RTT) scaling mechanism has been introduced for changing congestion window and to perform congestion control satisfactorily in all circumstances. This paper presents a fuzzy RTT scaling (FRTTS) scheme that performs RTT scaling and RTT scheduling for different high speed transmission control protocol (TCP) networks. In this scheme, RTT samples are allocated requesting application by using RTT scheduling factor and RTT samples are scaled for an application by using RTT scaling factor. A RTT scaler placed at the end node performs the RTT scheduling as well as RTT scaling. We also apply a FRTTS scheme on different high speed TCP's namely high-TCP (H-TCP) and scalable-TCP(S-TCP) and demonstrates that it provides better performance than non fuzzy scheme. The scheme has been extensively simulated to test the performance in terms of flow rate, RTT flows, packet size and congestion window size. The results show that FRTTS scheme provides better performance than non fuzzy scheme which employs dynamic RTT scheduling and RTT scaling.

scholarly journals Improving Congestion Control of TCP for Constrained IoT Networks

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4774
Author(s):  
Chansook Lim
Keyword(s):  
Congestion Control ◽  
Transmission Control Protocol ◽  
Window Size ◽  
Preliminary Test ◽  
Transport Layer ◽  
Network Simulator ◽  
Duty Cycling ◽  
Hidden Terminal ◽  
Grid Topology ◽  
Retransmission Timeout

For smooth integration with middleboxes on the Internet, TCP (Transmission Control Protocol) is favorably considered as a transport-layer protocol for IoT (Internet of Things) networks. In constrained networks, TCP tends to perform well with a small window size. For example, the uIP (micro IP) TCP/IP stack sets the TCP window size to one segment by default. In such a case, managing the retransmission timer is a primary approach to congestion control. In this paper, we examine the congestion control mechanism of TCP in the uIP stack using grid topology networks. In the preliminary test using the Cooja network simulator, the results show that the original uIP TCP causes lots of retransmissions when a radio duty cycling mechanism such as ContikiMAC is used. One main reason is that, once retransmission is deemed to be necessary, the original uIP TCP sets the retransmission timer based on the fixed RTO (retransmission timeout) before performing a retransmission. Since ContikiMAC may cause large RTT (round-trip time) variations due to the hidden terminal problem, the retransmission timer based on the fixed RTO value may cause lots of retransmissions. To address the problem, we propose a new scheme for managing the retransmission timer which adopts the notion of weak RTT estimation of CoCoA, exponential backoffs with variable limits, and dithering. Simulation results show that our proposed scheme reduces retransmissions while enhancing throughput and fairness when an RDC (radio duty cycling) mechanism is used.

Fairness Evaluation and Comparison of Current Congestion Control Techniques.

2016 ◽  
Vol 1 (1) ◽  
pp. 176 ◽  
Author(s):  
Usman Ahmad ◽  
Md Asri Bin Ngadi ◽  
Ismail Fauzi Bin Isnin
Keyword(s):  
Congestion Control ◽  
Data Transmission ◽  
High Speed ◽  
Transmission Control Protocol ◽  
Network Simulator ◽  
Network Resources ◽  
Long Distance ◽  
Control Techniques ◽  
High Bandwidth ◽  
Tcp Reno

Transmission Control Protocol (TCP) is used by many applications on the Internet for the reliable data transmission. TCP does not able to utilize the available link bandwidth quickly and efficiently in High bandwidth short distance (HBSD) and high bandwidth long distance (HBLD) networks. Many congestion control techniques also known as TCP variants are developed to solve these problems in different network environments. In this paper an experimental analysis is done for the performance evaluation of TCP CUBIC, TCP Compound, TCP Reno and High speed TCP in term of Inter and Intra Protocol fairness by using Network Simulator 2 (NS-2). Results show that the performance of TCP CUBIC pathetically down and TCP Compound and TCP Reno shows good performance in term of protocol fairness. However, these congestion control techniques still need more improvement for the utilization of available link bandwidth in HBLD networks and other network resources.

Fuzzy Logic-Based Round Trip Time Scaling and Scheduling in High Speed TCP Stacks

2013 ◽  
Vol 3 (2) ◽  
pp. 71-86
Author(s):  
V. Kavidha ◽  
V. Sadasivam
Keyword(s):  
High Speed ◽  
Transmission Control Protocol ◽  
Window Size ◽  
Complex Problem ◽  
Round Trip Time ◽  
Round Trip ◽  
Congestion Window ◽  
Trip Time ◽  
Time Scaling ◽  
End Node

Network management and control is a complex problem that requires intelligent, control methodologies to obtain satisfactory performance. Round trip time (RTT) scaling mechanism has been introduced for changing congestion window and to perform congestion control satisfactorily in all circumstances. This paper presents a fuzzy RTT scaling (FRTTS) scheme that performs RTT scaling and RTT scheduling for different high speed transmission control protocol (TCP) networks. In this scheme, RTT samples are allocated requesting application by using RTT scheduling factor and RTT samples are scaled for an application by using RTT scaling factor. A RTT scaler placed at the end node performs the RTT scheduling as well as RTT scaling. We also apply a FRTTS scheme on different high speed TCP’s namely high-TCP (H-TCP) and scalable-TCP(S-TCP) and demonstrates that it provides better performance than non fuzzy scheme. The scheme has been extensively simulated to test the performance in terms of flow rate, RTT flows, packet size and congestion window size. The results show that FRTTS scheme provides better performance than non fuzzy scheme which employs dynamic RTT scheduling and RTT scaling.

scholarly journals An Improved Algorithm for Congestion Management in Network Based on Jitter and Time to Live Mechanisms

2020 ◽  
Vol 23 (4) ◽  
pp. 352-356
Author(s):  
Samar Taha Yousif ◽  
Zaid Abass A. Al-Haboobi
Keyword(s):  
Congestion Control ◽  
Control Algorithm ◽  
Transmission Control Protocol ◽  
Congestion Management ◽  
The Internet ◽  
Congestion Window ◽  
Network Utilization ◽  
Congestion Control Algorithm ◽  
Tcp Vegas ◽  
Improved Algorithm

As internet network developed rapidly in the past ten years, and its operating environment is constantly changing along with the development of computer and communication technology, the congestion problem has become more and more serious. Since TCP is the primary protocol for transport layers on the internet, the data transmitted via the transport protocol utilizes Vegas Transmission Control Protocol (TCP) as the congestion control algorithm, where it uses increasing in delay round trip time (RTT) as a signal of network congestion. However, this congestion control algorithm will attempt to fill network buffer, which causes an increase in (RTT) determined by Vegas, thereby reducing the congestion window, and making the transmission slower, Therefore Vegas has not been widely adopted on the Internet. In this paper, an improved algorithm called TCP Vegas-A is proposed consist of two parts: the first part is sending the congestion window used by the algorithm for congestion avoidance along with the TTL (Time To Live) mechanism that limits the lifetime of a packet in the network. While the second part of the algorithm is the priority-based packet sending strategy, and jitter is used as a congestion signal indication. The combination of the two is expected to improve the efficiency of congestion detection. A mathematical model is established, and the analysis of the model shows that the algorithm has better effects on controlling congestion and improving the network throughput, decreasing packet loss rate and increasing network utilization, the simulation is done using NS-2 network simulation platform environment and the results support the theoretical analysis.

Proactive congestion control for high speed networks

2003 ◽  
Vol 43 (6) ◽  
pp. 761-775
Author(s):  
Tamer Dağ ◽  
Ioannis Stavrakakis
Keyword(s):  
Congestion Control ◽  
High Speed ◽  
High Speed Networks
Sign in / Sign up

Export Citation Format

Share Document