Computing research

Classical Transmission Control Protocol (TCP) designs have never considered the identity of the competing transport protocol as useful information to TCP sources in congestion control mechanisms. When competing against a TCP flow on a bottleneck link, a User Datagram Protocol (UDP) flow can unfairly occupy the entire link bandwidth and suffocate all TCP flows on the link. If it were possible for a TCP source to know the type of transport protocol that deprives it of link access, perhaps it would be better for the TCP source to react in a way which prevents total starvation. In this paper, we use coefficient of variation and power spectral density of throughput traces to identify the presence of UDP transport protocols that compete against TCP flows on bottleneck links. Our results show clear traits that differentiate the presence of competing UDP flows from TCP flows independent of round-trip times variations. Signatures that we identified include an increase in coefficient of variation whenever a competing UDP flow joins the bottleneck link for the first time, noisy spectral density representation of a TCP flow when competing against a UDP flow in the bottleneck link, and a dominant frequency with outstanding power in the presence of TCP competition only. In addition, the results show that signatures for congestion caused by competing UDP flows are different from signatures due to congestion caused by competing TCP flows regardless of their round-trip times. The results in this paper present the first steps towards development of more ’intelligent’ congestion control algorithms with added capability of knowing the identity of aggressor protocols against TCP, and subsequently using this additional information for rate control.

The transmission control protocol (TCP) is one of the most important Internet protocols. It provides reliable transport services between two end-hosts. Since TCP performance affects overall network performance, many studies have been done to model TCP performance in the steady state. However, recent researches have shown that most TCP flows are short-lived. Therefore, it is more meaningful to model TCP performance in relation to the initial stage of short-lived flows. In addition, the next-generation Internet will be an unified all-IP network that includes both wireless and wired networks integrated together. In short, modelling short-lived TCP flows in wireless networks constitutes an important axis of research. In this paper, we propose simple wireless TCP models for short-lived flows that extend the existing analytical model proposed in [IEEE Commun. Lett. 2002; 6(2):85–88]. In terms of wireless TCP, we categorized wireless TCP schemes into three types: end-to-end scheme, split connection scheme, and local retransmission scheme, which is similar to the classification proposed in [IEEE/ACM Trans. Networking 1997; 756–769]. To validate the proposed models, we performed ns-2 simulations. The average differences between the session completion time calculated using the proposed model and the simulation result for three schemes are less than 9, 16, and 7 ms, respectively. Consequently, the proposed model provides a satisfactory means of modelling the TCP performance of short-lived wireless TCP flows. Copyright © 2005 John Wiley & Sons, Ltd.

Long distance high bandwidth networks are spanning several continents and many remote Healthcare centers are centralizing their data centers for economic reasons. For the best performance of their data centers, TCP (Transmission Control Protocol) performance and data security are the main critical issues in these network scenarios. TCP performance is directly related to its congestion control mechanism which is responsible for detecting and reacting to the overload traffic on the network. Data security is related to the security mechanism being used by sender and receiver nodes during communication. Linux users, which have rapidly increased in the last five years and most of the Healthcare data centers are being deployed on the Linux operating system, focus the researchers to work on Linux to enhance its performance and security accordingly. The Linux operating system uses TCP CUBIC as a congestion control mechanism with TCP during communication. TCP CUBIC became the default congestion control mechanism of Linux in 2006 after kernel 2.6.18. TCP CUBIC is fundamentally a loss based TCP congestion control mechanism and at each packet loss detection, it reduces its Congestion Window ( $cwnd$ c w n d ) size 20 percent instead of 50 percent as in trademark congestion control mechanism Standard TCP. The aim of this paper is to design a new security mechanism that will work with TCP CUBIC to achieve the maximum possible performance and security over the network link. In this paper, Network Simulator 2 (NS-2) is used to compare the performance of TCP CUBIC with state-of-the-art mechanisms in long and short Round Trip Time (RTT), high bandwidth network scenarios. Results show that when new security mechanism is used with TCP CUBIC, overall better performance in the form of protocol fairness, TCP friendliness, goodput, and convergence time is achieved over the network link.

Many smart healthcare centers are deploying long distance, high bandwidth networks in their computer network infrastructure and operation. Transmission control protocol (TCP) is responsible for reliable and secure communication of data in these medial infrastructure networks. TCP is reliable and secure due to its congestion control mechanism, which is responsible for detecting and reacting to the congestion in the network. Many TCP congestion control mechanisms have been developed previously for different operating systems. TCP CUBIC, TCP Compound, and TCP Fusion are the default congestion control mechanism in Linux, Microsoft Windows, and Sun Solaris operating systems, respectively. The earliest congestion control mechanism Standard TCP acts as the trademark congestion control mechanism. The exponential growth of congestion window ( $cwnd$ ) in slow start phase of the TCP CUBIC causes burst losses of packets, and TCP flows did not share available link bandwidth fairly. The prime aim of this paper is to enhance the performance of TCP CUBIC for long distance, high bandwidth secured networks to achieve better performance in medical infrastructure, concerning packet loss rate, protocol fairness, and convergence time. In this paper, congestion control module for slow start is proposed, which reduces the effect of the exponential growth of $cwnd$ by designing the new limits of $cwnd$ size in slow start phase, which in turn decreases the packet loss rate in healthcare networks. NS-2 is used to simulate the experiments of enhanced TCP CUBIC and state-of-the-art congestion control mechanisms. Results show that the performance of enhanced TCP CUBIC outperforms by 18% as compared with the state-of-the-art congestion control mechanisms.

Due to the development and evolution in Cognitive Radio Networks (CRNs), the performance of Transmission Control Protocol (TCP) over CRN has become a crucial factor. TCP ensures the reliable end-to-end delivery of data, which is very important for the quality of service (QoS) requirements. TCP performance is severely affected by channel switching and channel availability in CRNs. The frequent occurrence of such events is due to CRNs nature which unnecessarily reduces the transmission rate which results in degrading the overall performance. In this paper, the authors investigate the limitations of using TCP NewReno (i.e., standard TCP) over CRNs, and further propose a cross-layer-design protocol based on an interaction between transport layer and lower layers to improve TCP performance over CRNs. The design is called Cross-Layer Design for TCP (TCP-CLD). It primarily aims at improving the TCP performance over CRNs via controlling and adapting a few selected TCP parameters. Specifically, the authors propose freezing the data transmission and re-transmission timeout (RTO) of TCP during the time of channel switching and channel unavailability. In addition, the authors update the size of congestion window (cwnd) of TCP based on the bandwidth and buffer size of relay nodes. Moreover, in the case of channel switching, the authors update the Round Trip Time (RTT) of TCP based on the new route delay. Simulation experiments have been conducted using ns-2 network simulator tool whereas results show that the proposed design achieves a significant performance improvement compared with the standard TCP NewReno protocol and the other known protocol, namely, TCP-CRAHN.

The transmission control protocol (TCP) was designed to provide reliable end-to-end delivery of data over unreliable networks. Most TCP implementations have been carefully optimised to operate in wired networks. Deploying standard TCP in wireless mobile ad hoc networks (MANETs) can lead to poor performance of TCP. The main problem that faces TCP in ad hoc networks is its inability to distinguish between packet losses due to congestion and those due to route failures. In order to adapt TCP to MANET environment, several TCP improvements that differentiate between different types of packet losses using explicit notification messages from lower layers have been proposed. In this paper, we propose a new end-to-end technique that does not require any participation from intermediate nodes within the network. The proposed scheme relies on expanding the retransmission timeout (RTO) interval in order to reduce the number of timeouts that do not result from congestion. Simulation results show that our scheme can improve TCP throughput and delay. It outperformed the standard TCP in detailed simulation experiments.

While the transmission control protocol (TCP) generally provides robust performance across many network environments, several researchers have identified the poor end-to-end performance achieved by TCP on asynchronous transfer mode (ATM) networks. The performance problems arise for several reasons: (1) a size mismatch between TCP segments and ATM cells; (2) the simple protocols used for segmentation and reassembly in ATM, and for retransmission in TCP; (3) specific optimizations in TCP, made primarily for low-bandwidth Internet environments which do not work well in high speed ATM networks; (4) features (or misfeatures) in most TCP protocol implementations; and (5) subtle interactions between all of these factors. This paper describes a simulation model that we have constructed to study TCP performance on ATM networks, as well as a set of simulation experiments conducted using the model. The TCP model is detailed enough to recreate many of the performance problems identified by other researchers, as well as to evaluate potential solutions to the performance problems. The TCP model adds to the traffic modeling toolkit available in our existing ATM network simulator, and enables the further study of performance issues in TCP over ATM.

Transmission control protocol (TCP) provides reliable connection-oriented services between any two end systems on the Internet. With TCP congestion control algorithm, multiple TCP connections can share network and link resources simultaneously. These TCP congestion control mechanisms have been operating effectively in wired networks. However, performance of TCP connections degrades rapidly in wireless and lossy networks. To sustain the throughput performance of TCP connections in wireless networks, design modifications may be required accordingly in the TCP flow control algorithm, and potentially, in association with other protocols in other layers for proper adaptations. In this chapter, we explain the limitations of the latest TCP congestion control algorithm, and then review some popular designs for TCP connections to operate effectively in wireless mesh network infrastructure.

The various link adaptation techniques employed by High Speed Downlink Packet Access (HSDPA) in the third generation (3G) networks augment the bandwidth oscillation, which is identified as one of the most important factors resulting in the throughput deterioration of Transmission Control Protocol (TCP). In this paper, we firstly explain why the bandwidth oscillation degrades the TCP performance through a special simulation experiment. Subsequently, a split connection Window Adaptation TCP Proxy is proposed to improve the TCP throughput over HSDPA networks. In this solution, the built-in attributes of HSDAP system are sufficiently utilized. In order to effectively use the precious cellular link resources, the length of the queue connected with it is intentionally kept around the reference value through adjusting the sending window size of TCP proxy based on the dynamic values of varying bandwidth. A discrete-time stochastic state space model is formulated to analyze the system stability. The validity of enhanced scheme is verified through simulation experiments. The performance of TCP proxy is compared with the standard TCP protocol. The numerical results show that our TCP proxy is able to keep the cellular link utilization over 90%, and to improve TCP throughput by 100% under most conditions.

Analytical modeling of TCP flow in wireless LANs

Video streaming services using Transmission Control Protocol (TCP) as a transport layerprotocol---represented by YouTube---are becoming increasingly popular and,accordingly, have come to account for asignificant portion of Internet traffic. TCP is greedy; that is, it tries to exhaust theentire bandwidth.Thus, video streaming over TCP tends to unnecessarilytake bandwidth from competing traffic. In this paper, we first investigate the data transfer mechanisms of the currentvideo streaming services using TCP and showthat they perform data transfer at much higher rates than the video playback rate.We then propose a new transfer mechanism for video streaming over TCP,one that controls the data transfer ratebased on the network congestion level and the amount of buffered video data at the receiver.Simulation results show that the proposed mechanism has two characteristics lacked bycurrent video streaming over TCP, specifically (1) a low frequency of buffer underflow at the receiverand (2) a lack of excessive bandwidth ``stealing'' from competing traffic.

In deep space missions, large-scale deep space information and continuous sensory data are generated, processed, and exchanged over Internet of deep space things (IoDST). Ensuring reliable communication in IoDST requires resolution of challenges engendered by the unique characteristics of IoDST, including long propagation delays, link outages, high error rates, and asymmetric bandwidths. Thus, transmission control protocol (TCP) layer functionalities are crucial for ensuring reliable IoDST communications. However, existing TCP congestion control (CC) protocols present poor performance in IoDST communications, owing to the dependence of traditional window-based CC approaches on pre-configured rules to adjust transmission rate against the aforementioned unique characteristics. In this paper, we propose an intelligent CC scheme called optimistic actor–critic-based TCP congestion control (OAC-TCPCC) to solve the problems of the challenging link conditions in IoDST. OAC-TCPCC dynamically determines optimal congestion window for data transmission over IoDST communication links to maximize the TCP throughput performance and minimize file transfer time. Simulation results reveal that OAC-TCPCC improves the TCP throughput performance by up to 27%, 79%, 92%, 477%, 643%, and 766%; and reduces file transfer time by up to 16%, 37%, 50%, 48%, 58%, and 79%, compared to DRL-CC, TP-Planet, FAST TCP, TCP Peach, TCP BBR, and TCP CUBIC, respectively.

While Transmission Control Protocol (TCP) works well with a low bit error rate (BER), the performance of TCP degrades significantly if the BER rises above a certain level. A study of the performance of TCP with high BER is required for the efficient design and deployment of such systems. In this paper, we address the problem of TCP performance in high BERs and analyze the issues by investigating the effect of BERs on system performance. We consider TCP Reno in our study to explore the system performance using extensive analysis of simulation and modeling. In the analysis, we consider the amount of datagram sent and retransmitted, mean throughput, link-layer overhead, TCP window size, FTP download response time, packet dropping and retransmission, and the TCP congestion avoidance mechanism. We validate simulation results by setting up a virtualized testbed using Linux hosts and a Linux router. The results obtained show that TCP throughput degrades significantly and eventually collapses at the packet drop probability of 10% (BER = 10−5). The FTP download response time is about 32 times longer than that of a perfect channel (no packet dropping). We found that TCP Reno cannot handle such a high BER to operate in wireless environments effectively. Finally, we provide recommendations for network researchers and engineers confronted with the challenge of operating TCP over noisy channels.

Most of the traffic in today's Internet is controlled by the Transmission Control Protocol (TCP). Hence, the performance of TCP has a significant impact on the performance of the overall Internet. TCP is a complex protocol with many user-configurable parameters and a range of different implementations. In addition, research continues to produce new developments in congestion control mechanisms and TCP options, and it is useful to trace the deployment of these new mechanisms in the Internet. As a final concern, the stability and fairness of the current Internet relies on the voluntary use of congestion control mechanisms by end hosts. Therefore it is important to test TCP implementations for conformant end-to-end congestion control. Since web traffic forms the majority of the TCP traffic, TCP implementations in today's web servers are of particular interest. We have developed a tool called TCP Behavior Inference Tool (TBIT) to characterize the TCP behavior of a remote web server. In this paper, we describe TBIT, and present results about the TCP behaviors of major web servers, obtained using this tool. We also describe the use of TBIT to detect bugs and non-compliance in TCP implementations deployed in public web servers.

Transmission Control Protocol (TCP) is still dominant for reliable end-to-end data transmission with congestion control over diverse types of networks although it does not perform well in goodput on lossy networks. To mitigate the goodput degradation of TCP on lossy networks, TCP with Network Coding (TCP/NC) was proposed. But it has not been well deployed because TCP/NC should be implemented in both sides of end-to-end connection; it requires considerable costs and is sometimes difficult in tiny end devices, e.g., with less memory and power. In this paper, to utilize the potential of TCP/NC more practically with no change on end-host TCP, we consider the TCP/NC tunnel that simply conveys end-to-end TCP sessions not only on a single TCP/NC session but also on cascaded TCP/NC sessions traversing a lossy network in the middle without per-session management. The simulation results by Network Simulator 3 clearly show the benefit of the multiply-cascaded TCP/NC tunnel. In congestion scenarios with a wide range of link loss rates, the end-to-end standard TCP with multi-cascaded TCP/NC tunnel can achieve a significantly higher goodput compared to both the end-to-end TCP/NC without tunnel and the end-to-end standard TCP with single TCP/NC tunnel.