Tcp

This paper provides an overview of cellular networks and wireless Internet. It focuses on the problems of providing multimedia services over these networks, and highlights the latest developments in the area. This is done by providing brief descriptions, and providing a wealth of pointers to where the relevant information can be obtained. The paper consists of four main sections corresponding to protocol layering: wireless data link layer for cellular systems and the supporting of multimedia in these environments; wireless network layer, namely Mobile IP needed to support mobility in a wireless Internet; wireless transport layer, namely the extensions to Internet's TCP; wireless application layer. Regarding cellular systems, we present an overview of multiple access techniques, transmission aspects, and quality of service issues in the data link layer of these systems. The section on wireless network layer provides a brief introduction to the Internet technologies, then it illustrates the deficiencies of the current Internet Protocol (IP) for supporting wireless/mobile applications and shows how the new Mobile IP protocol overcomes these deficiencies, and how mobility is handled in these wireless Internets. The next section tackles the problem of reliable communication in wireless Internet, and the related problems of TCP over Mobile IP. The final section focuses on application layer issues in wireless data, namely handover and developing Web applications for mobile computers.

Stored fast ion beams in atomic and molecular collision experiments are discussed with an emphasis on electron-ion interactions at low relative energies. Recent progress was obtained in electron collision spectroscopy using an electroncooled stored ion beam and a separate electron target in the same storage ring; from a cryogenic photocathode, electron beams with internal temperatures of 5 to 10 K were produced. Results are presented for dielectronic recombination resonances, resolving the hyperfine structure of stored lithiumlike scandium ions and obtaining precise results for the fine structure splitting of these ions, and for ro-vibrational resonances in the recombination of electrons with hydrogen molecular ions, revealing sharp structures down to 2 meV. An overview of the cryogenic storage ring (CSR) project in Heidelberg is given.

Data centers provide resources for a broad range of services, such as web search, email, web sites, etc., each with different delay requirements. For example, web search should cater to users' requests quickly, while data backup has no special requirement on completion time. Different applications also introduce flows with very different properties (e.g., size and duration).

Most of future digital services for home and office users will be deployed and delivered through the Internet and wireless connectivity. However, employing regular access points (APs) and protocols will not allow an efficient coexistence among heterogeneous application flows. Indeed, real-time and elastic applications are (and will be) supported by different protocols and featured with different performance requirements: low perpacket delay for the former and high throughput for the latter. In this work, we present a work-in-progress evaluation of a new AP prototype able to guarantee a fast and smooth data delivery for real-time streams while maintaining a high throughput for TCP-based applications. Our approach is based on a userspace modification of the AP's code based on OpenWRT operating system so as to appropriately shape transiting network traffic. Preliminary experimental results confirm that our solution represents an optimal candidate to become the center of future wireless in-home scenarios.

LTE (Long Term Evolution) networks have been introduced in 3GPP (Third Generation Partnership Project) release 8 specifications, with an objective of high-data-rate, low latency
and packet-optimized radio access technology. This paper analyses the possibilities, capabilities and features of EstiNet Network Simulator and Emulator that can be used for modelling and analysing the behaviour of LTE networks. It also illustrates a simple scenario where one or several LTE User Equipment (UEs) are connected to Internet, and evaluates the throughput performance for TCP and UDP traffic in downlink direction. Some important LTE network parameters are also specified for this performance evaluation. Finally it will be concluded that EstiNet is a suitable simulation and emulation tool for modelling and analysing the behaviour of LTE networks.

Traditional analysis on the TCP performance attributes the overhead of TCP mainly on these aspects: many times of memory access and copy, much data transmission on bus and a large number of CPU cycles required by the protocol processing. Compared to TCP, the main advantage of RDMA lies in its single memory access which brings a higher data transmission bandwidth and lower CPU utilization.

Data centers provide resources for a broad range of services, such as web search, email, web sites, etc., each with different delay requirements. For example, web search should cater to users' requests quickly, while data backup has no special requirement on completion time. Different applications also introduce flows with very different properties (e.g., size and duration). The default method of transport in data centers, namely TCP, treats flows equally, forcing equal share of the bottleneck network bandwidth. This fairness property leads to poor outcomes for time-sensitive applications. A better solution is to allocate more bandwidth to time-sensitive applications. However, the state-ofthe-art approaches that do this all require forklift changes to data center networking gear. In some cases, substantial changes need to be made to end-system stacks and applications as well. In this paper, we argue that a simple modification to TCP can help better meet the requirements of latency-sensitive applications in the data center. No modification to end-systems, applications or networking gear is necessary. We motivate our Adaptive TCP (ATCP) design using measurements of real data center traffic. We analytically derive the parameters to use in our proposed modification to TCP. Finally, we use extensive simulations in NS2 to show the benefits of ATCP.

TCP is the most widely used transport protocol on the Internet today. Over the years, especially recently, due to requirements of high bandwidth transmission, various approaches have been proposed to improve TCP performance. The Linux 2.6 kernel is now preemptible. It can be interrupted mid-task, making the system more responsive and interactive. However, we have noticed that Linux kernel preemption can interact badly with the performance of the networking subsystem. In this paper we investigate the performance bottleneck in Linux TCP. We systematically describe the trip of a TCP packet from its ingress into a Linux network end system to its final delivery to the application; we study the performance bottleneck in Linux TCP through mathematical modeling and practical experiments; finally we propose and test one possible solution to resolve this performance bottleneck in Linux TCP.

The past decade has seen the rapid development of new strategies for the design of biodegradable macromolecular compounds, with properly suited architecture and tailored properties, functioning as temporary support for the engineering of living constructs in tissue regeneration applications. The purpose of this paper is to review recent research in the interdisciplinary field of tissue engineering, with particular regard to bone and cartilage tissues, aimed at the design, synthesis, evaluation and characterization of bioactive polymeric scaffolds guiding and promoting new tissue ingrowth. Current strategies in scaffold-guided tissue engineering approach, involving the most employed biodegradable polymers, either of natural or synthetic origin, will be reported underlying the role played by both material structure-property relationship and scaffold architecture. While there are many polymeric materials that may be employed for the regeneration of bone and cartilage tissue, we will focus specifically on those that have been more extensively applied, showing promising outcomes. Commonly exploited and innovative processing techniques for the fabrication of advanced tissue engineering scaffolds will be explored, highlighting theoretical principles and their potential in creating micro-nanostructures suitable for tissue regeneration applications.

Titanium and its alloys are widely used as implant materials. Their integration in the bone is in general very good without fibrous interface layer. However, titanium and its alloys have certain limitations. Metal ions are released from the implant alloy and have been detected in tissues close to titanium implants. The release of these elements, even in small amounts, may cause local irritation of the tissues surrounding the implant. Cell and tissue responses are affected not only by the chemical properties of the implant surface, but also by the surface topography or roughness of the implants. To overcome the problem of ion release and to improve the biological, chemical, and mechanical properties, many surface treatment techniques are used. Any surface treatment that would elicit favorable response from tissues can be applied to enhance the usefulness of the implants. In view of this, the current review describes surface modification of titanium and titanium alloys by ion beam implantation.

Replacing malfunctioning tissues with titanium-based implants has become a widespread practice spurred by population aging. Advances in biomaterials, technology and implantation protocols have led to increasing expectations on the applicability and durability of implants. The field has recently moved from a bioinert to a bioactive paradigm due to surface modifications that trigger specific responses on the surrounding tissues. Biopolymeric surface coatings have taken up a central role in these developments. The use of these and other biomimetic strategies on implants provides greater control over material-cell interactions and it is aimed at improving long-term clinical results by replicating some of the structures and mechanisms of living tissues. This review summarizes the state of the art of biomimetic implants and discusses the main directions and challenges of this field toward a more predictable and successful implant osseointegration.

Current wireless sensor devices are facing a lot of issues to integrate with the global internet communication networks due to incompatible Application messaging protocols. Currently various heterogeneous application messaging protocols are available like HTTP, MQTT, COAP, DDS, AMQP. Each of this application messaging protocols are designed and implemented as per different application requirements considering the computational resources and available communication bandwidth. These protocols are not suitable for constrained sensor devices due to limitation of computational power and bandwidth. MQTT protocol is designed and implemented for Machine to Machine communication, but still not suitable for low power sensor devices due to complex TCP transport protocol used. More Efficient MQTT-SN protocol is (Message Queue Telemetry Transport-Sensor Network) proposed for sensor devices considering the wireless sensor network characteristics, power constraint and bandwidth limitations. MQTT-SN messages are transported using less over head UDP Transport Protocol. In this paper we are provided the procedure how the MQTT-SN Gateway Integration with Industry standard AWS MQTT-Server and End to End Sensor Data Transmission from Sensor Device to the IOT Application through MQTT-SN Gateway and AWS(Amazon Web Services) MQTT Server.

Designing efficient transmission mechanisms for advanced satellite networks is a demanding task, requiring the definition and the implementation of protocols and architectures well suited to this challenging environment. In particular, transport protocols performance over satellite networks is impaired by the characteristics of the satellite radio link, specifically by the long propagation delay and the possible presence of segment losses due to physical channel errors. The level of impact on performance depends upon the link design (type of constellation, link margin, coding and modulation) and operational conditions (link obstructions, terminal mobility, weather conditions, etc.). To address these critical aspects a number of possible solutions have been presented in the literature, ranging from limited modifications of standard protocols (e.g. TCP, transmission control protocol) to completely alternative protocol and network architectures. However, despite the great number of different proposals (or perhaps also because of it), the general framework appears quite fragmented and there is a compelling need of an integration of the research competences and efforts. This is actually the intent of the transport protocols research line within the European SatNEx (Satellite Network of Excellence) project. Stemming from the authors' work on this project, this paper aims to provide the reader with an updated overview of all the possible approaches that can be pursued to overcome the limitations of current transport protocols and architectures, when applied to satellite communications. In the paper the possible solutions are classified in the following categories: optimization of TCP interactions with lower layers, TCP enhancements, performance enhancement proxies (PEP) and delay tolerant networks (DTN). Advantages and disadvantages of the different approaches, as well as their interactions, are investigated and discussed, taking into account performance improvement, complexity, and compliance to the standard semantics. From this analysis, it emerges that DTN architectures could integrate some of the most efficient solutions from the other categories, by inserting them in a new rigorous framework. These innovative architectures therefore may represent a promising solution for solving some of the important problems posed at the transport layer by satellite networks, at least in a medium-tolong-term perspective.

Transport connections set up in wireless ad hoc networks are plagued by problems such as high bit error rates, frequent route changes, and partitions. If we run transmission control protocol (TCP) over such connections, the throughput of the connection is observed to be extremely poor because TCP treats lost or delayed acknowledgments as congestion. In this paper, we present an approach where we implement a thin layer between Internet protocol and standard TCP that corrects these problems and maintains high end-to-end TCP throughput. We have implemented our protocol in FreeBSD, and in this paper, we present results from extensive experimentation done in an ad hoc network. We show that our solution improves TCPs throughput by a factor of 2-3.

The widely used reliable transport protocol TCP, is an end to end protocol designed for the wireline networks characterized by negligible random packet losses. This paper represents exploratory study of TCP congestion control principles and mechanisms. Modern implementations of TCP contain four intertwined algorithms: slow start, congestion avoidance, fast retransmit, and fast recovery. In addition to the standard algorithms used in common implementations of TCP, this paper also describes some of the more common proposals developed by researchers over the years. We also study, through extensive simulations, the performance characteristics of four representative TCP schemes, namely TCP Tahoe, New Reno and Vegas under the network conditions of bottleneck link capacities for wired network.

Several objectives have been identified in developing the random early drop (RED): decreasing queueing delay, increasing throughput, and increasing fairness between short and long lived connections. It has been believed that indeed the drop probability of a packet in RED does not depend on the size of the file to which it belongs. In this paper we study the fairness properties of RED where fairness is taken with respect to the size of the transferred file. We focus on short lived TCP sessions. Our findings are that (i) in terms of loss probabilities, RED is unfair: it favors short sessions, (ii) RED is fairer in terms of the average throughput of a session (as a function of its size) than in terms of loss probabilities. We study various loading regimes, with various versions of RED.

The new opportunities opened up by wireless technologies are also accompanied with new technical challenges. Principal among the challenges is the fact that wireless medium has limited bandwidth resources when compared with wired equivalent. The convenience brought about by the IEEE 802.11n protocol is also followed by the technical challenge of near average performance of the widely used transport control protocol (TCP) due to limited bandwidth resources of the wireless medium. IEEE 802.11n specifies standard for physical (PHY) and MAC layers of wireless local area networks (WLANs) which is based on the IEEE 802.11-2007 networking reference standard. This work is meant to enhance the efficiency of TCP in IEEE 802.11n network in order to improve per user bandwidth.

Abstract: Audio/Video Streaming services enable us to watch videos or listen to music from anywhere and from any web enabled multimedia device like our personal computers or smart phones. All that the user requires other than a personal computer or a smart device are Internet connection and a user account on the service’s website. This will allow users to enjoy music anytime-while driving a car, taking an evening walk etc.. The need for Multimedia streaming arises from the following factors: First, storage capacities of our devices are limited .It is not possible to store all our favourite music/video files in them. Also new songs/videos are being added to the already existing list of millions of songs/videos on a weekly or monthly basis. Therefore, it is more convenient to stream from a service to our personal computers or smart devices connected to the Internet by logging into our account. Also, the need to frequently update the songs/videos on each device independently is eliminated. This saves time and money. Secondly, we are moving towards high quality audio/video. Streaming enables us to consume high quality audio/video without the need of high end hardware on the consumer side. Thus, it leads to reduced reduce hardware cost. We will discuss in this paper, how streaming works and the protocols and codecs associated with audio/video streaming. An improvement over the currently used model is suggested. Finally, we will discuss the challenges and legal issues related with multimedia streaming.
Keywords: Streaming, protocol, codec, cloud, service, copyright, TCP, UDP, RTSP, RTP, RTCP, P2P.
Title: Multimedia Streaming and Related Issues
Author: Sober Lourembam, Venkatata Rajesh M, Meina Singh
International Journal of Computer Science and Information Technology Research
ISSN 2348-120X (online), ISSN 2348-1196 (print)
Research Publish Journals

Corresponding developments in technology, information access more affordable and easier. Today, more communications media that can be applied as a medium of information access. One way is to use wireless technology or media without cable as the backbone of the communication lines. One of wireless technology is now growing as an access point broadband data communications (Broadband Wireless Access) is a WiMAX. WiMAX stands for Worldwide Interoperability for Microwave Access is nirkbel technology that provides communication with a large bandwidth. WiMAX is the combination between the IEEE 802.16 standard with ETSI HiperMAN standars.

IP spoofing is one of the most common forms of on-line disguise. Hackers have long employed the tactic of disguising their true identity. It exploits the security weaknesses in TCP/IP protocol suite. This paper evaluates basic techniques to exploit vulnerabilities of TCP/IP protocol suite such as initial sequence number prediction and forging the source address. This paper covers certain threats and attack methods that employ IP spoofing and analyze preventive measures such as ingress and egress filtering at routers, authentication and encryption.

This paper introduces and analyzes a class of nonlinear congestion control algorithms called binomial algorithms, motivated in part by the needs of streaming audio and video applications for which a drastic reduction in transmission rate upon each congestion indication (or loss) is problematic. Binomial algorithms generalize TCP-style additive-increase by increasing inversely proportional to a power ¢ of the current window (for TCP, ¢ ¤ £ ¦ ¥ ) ; they generalize TCP-style multiplicative-decrease by decreasing proportional to a power § of the current window (for TCP, § £ ©

Implementing Network File System] protocol for larger block or packet transfer over to Network Attached Storage] from clients. Network Attached Storage scalability is habitually inadequate to the volume of the appliance. Addition of an appliance is reasonably easy, but access to the pooled contents as a mono entity is not. In contrast, Network Attached Storage supports file sharing between multiple peer clients. Network Attached Storage clients can potentially access file shares from anywhere in the organization. Because file access is, typically low volume and less sensitive to response times, predictable performance and distance are less of a concern in Network Attached Storage implementations.

Human microsomes from duodenum and ileum/jejunum were used. The toxic metabolite chlorpyrifos-oxon was the only one formed. 10-fold interindividual variability was observed. Bioactivation was confined in the duodenum, declining toward the distal ileum. Intestinal metabolism could play a role in CPF pre-systemic bioactivation. Available online xxx

a b s t r a c t E341 (tricalcium phosphate) (TCP) is commonly used as a food additive and also as a nutritional supplement. To evaluate the possible developmental effects, female Wistar rats were treated with E341 (TCP) by oral gavage during pregnancy. There were three groups of each containing five rats. Rats in Groups I-III were fed with standard diet, oil and E341 (TCP) 175 mg/kg body weight during gestation days (GD 0-20) respectively. We assessed foetal body lengths and weights and also made morphometric examination of placenta and umbilical cord. The placental weights of E341 (TCP) group (Group III) were found to be decreased statistically. According to skeletal stainings of foetuses, lengths of left ulna (28.3%), right femur (29.8%), left femur (34.9%) and diameter of the skull of y-axis were significantly decreased (12.3%) in E341 (TCP) treatment groups. There was an increase in trans-umbilical diameter in treatment group (14%). This is the first study in which developmental effects of E341 (TCP) have ever evaluated. The results suggest that prenatal development of rats during gestation is sensitive to E341 (TCP) exposure.

This paper describes the design, implementation and performance of an open, high performance, dynamically extensible router under development at Washington University in St. Louis. This router supports the dynamic installation of software and hardware plugins in the data path of application data flows. It provides an experimental platform for research on programmable networks, protocols, router software and hardware design, network management, quality of service and advanced applications. It is designed to be flexible, without sacrificing performance. It supports gigabit links and uses a scalable architecture suitable for supporting hundreds or even thousands of links. The system's flexibility makes it an ideal platform for experimental research on dynamically extensible networks that implement higher level functions in direct support of individual application sessions. 1500 Bytes Packet size © 500 Mb/s Inter-router link rate © 10 Mb/s Access link rate © 0 9 © 9 111© 0

Providing reliable data communications over wireless channels is a challenging task because time-varying wireless channel characteristics often lead to bit errors. These errors result in loss of IP packets and, consequently, TCP segments encapsulated into these packets. Since TCP cannot distinguish packet losses due to bit corruption from those due to network congestion, any packet loss caused by wireless channel impairments leads to unnecessary execution of the TCP congestion control algorithms and, hence, sub-optimal performance. Automatic Repeat reQuest (ARQ) and Forward Error Correction (FEC) try to improve communication reliability and reduce packet losses by detecting and recovering corrupted bits. Most analytical models that studied the effect of ARQ and FEC on TCP performance assumed that the ARQ scheme is perfectly persistent (i.e., completely reliable), thus a frame is always successfully transmitted irrespective of the number of transmission attempts it takes. In this paper, we develop an analytical cross-layer model for a TCP connection running over a wireless channel with a semi-reliable ARQ scheme, where the amount of transmission attempts is limited by some number. The model allows to evaluate the joint effect of stochastic properties of the wireless channel characteristics and various implementation-specific parameters on TCP performance, which makes it suitable for performance optimization studies. The input parameters include the bit error rate, the value of the normalized autocorrelation function of bit error observations at lag 1, the strength of the FEC code, the persistency of ARQ, the size of protocol data units at different layers, the raw data rate of the wireless channel, and the bottleneck link buffer size.

The performance of a distributed system is affected by the various functions of its components. The interaction between components such as network nodes, computer systems and system programs is examined with special interest accorded to its effect on system reliability. At affordable time and space costs, the analytic hierarchy process (AHP) is used to determine how the reliability of a distributed system may be controlled by appropriately assigning weights to its components. Illustrative case studies, that display the system structure, the assignment of weights and the AHP handling are presented.

Computer network technologies have been growing explosively. Teaching computer networking principles can be enhanced using simulation through the use of interactive (not statistical based) simulation. The curriculum is based on the theory that through networking simulation programs, students are able to graphically implement the concepts learned in their coursework. With networking simulation tools, students can construct, tune, and analyze network performance while reinforcing their understanding of networking theory. Network simulation tools save money by offering the user a tool to enhance the design and integration of networks. There are many network simulation tools that allow users to model LANs, MANs, and WANs on the market. This paper describes our approach to develop computer network laboratory that enhances the understanding of a computer network course. Different computer network simulation tools have been considered and COMNET III has been selected as the tool of choice. Five labs have been developed. COMNET III is a network simulation tool that allows students and networking professionals to model, tune, and analyze the performance of various types of networks. It fosters what COMNET refers to as a "building-block approach" by utilizing a GUI interface that is comprised of "blocks" or objects representing many of the objects used in real networks. The user has the ability to adjust the objects' parameters using either default, constant, or algebraic values to better model the objects' functions

This paper introduces and analyzes a class of nonlinear congestion control algorithms called binomial algorithms, motivated in part by the needs of streaming audio and video applications for which a drastic reduction in transmission rate upon each congestion indication (or loss) is problematic. Binomial algorithms generalize TCP-style additive-increase by increasing inversely proportional to a power ¢ of the current window (for TCP, ¢ ¤ £ ¦ ¥ ) ; they generalize TCP-style multiplicative-decrease by decreasing proportional to a power § of the current window (for TCP, § £ ©

In this paper an effort has been made to study various Congestion control techniques used for reducing/easing the level of congestion and subsequently avoiding the congestion of the wired communication networks in general and High Speed Networks in particular. Many authors have suggested several congestion control techniques [2], [3], [4], [8], [12], [14], [15], [23], [29], [32] & [33] and studied their behavior under various network conditions, for a range of parameters also under heterogeneous networking environments. A special effort has been made to study the problems associated with the TCP congestion control mechanisms and the several solutions that have been proposed to improve its performance. This analysis tries to study the limitations of the suggested solutions, based on various parameters and propose algorithms to overcome these limitations for the High Speed Networks.

This paper presents a novel mathematical model for the TCP Tragedy of the Commons, using Game Theory concepts. This tragedy may appear in a TCP/IP-based network when hosts do not respect the protocol rules and try to monopolize the shared network resources by using a selfish strategy. Our model quantifies the effects of this evil behavior in a simple and standard network topology and allows to obtain some interesting results which we prove formally. Finally, we validate the model results by comparing its predictions with a set of ...

Current IP-level mobility protocols have difficulties meeting the stringent handover delay requirements of future wireless networks. At the same time they do not give sufficient control to the network to control the handover process. This paper presents an extension to Proxy Mobile IP, which is the favorite IP level mobility protocol for the 3GPP System Architecture Evolution / Long Term Evolution (SAE/LTE). The extension, Fast Proxy Mobile IPv6 (FPMIPv6), aims at solving or reducing the control and handover problem. An elementary analysis shows that FPMIPv6 can significantly reduce the handover latency and the loss of packets during handover, especially if handovers can be predicted a few tens of milliseconds before they occur.

The self-clocking principle (SCP) of Transmission Control Protocol (TCP) had been analyzed for a network implementing a per-flow buffering scheme. The ideal SCP is yet unknown for the Internet which implements a first-in-first-out buffering scheme. This paper derives an ideal SCP for the Internet by formulating the traffic transmission control as a typical control problem and then solving it by a control-theoretic approach. The ideal SCP reveals the defect of the SCP being deployed in the Internet that it is insufficient to avoid congestion by adjusting the packet effective window based on records of the outstanding packets of a single source; instead outstanding packets from other sources also have to be counted. The ideal SCP also reveals the difficulties of developing and implementing an effective self-clocking scheme for congestion control in the Internet.

The current congestion control mechanism used in TCP has difficulty reaching full utilization on high speed links, particularly on wide-area connections. For example, the packet drop rate needed to fill a Gigabit pipe using the present TCP protocol is below the currently achievable fiber optic error rates. HighSpeed TCP was recently proposed as a modification of TCP’s congestion control mechanism to allow it to achieve reasonable performance in high speed wide-area links. In this research, simulation results showing the performance of HighSpeed TCP and the impact of its use on the present implementation of TCP are presented. Network conditions including different degrees of congestion, different levels of loss rate, different degrees of bursty traffic and two distinct router queue management policies were simulated. The performance and fairness of HighSpeed TCP were compared to the existing TCP and solutions for bulk-data transfer using parallel streams.

There is a growing interest in the use of variants of the Transmission Control Protocol (TCP) in high-speed networks. ns-2 has implementations of many of these high-speed TCP variants, as does Linux. ns-2, through an extension, permits the incorporation of Linux TCP code within ns-2 simulations. As these TCP variants become more widely used, users are concerned about how these different variants of TCP might interact in a real network environment -how fair are these protocol variants to each other (in their use of the available capacity) when sharing the same network. Typically, the answer to this question might be sought through simulation and/or by use of an experimental testbed. So, we compare with TCP NewReno the fairness of the congestion control algorithms for 5 high-speed TCP variants -BIC, Cubic, Scalable, High-Speed and Hamilton -on both ns-2 and on an experimental testbed running Linux. In both cases, we use the same TCP code from Linux. We observe some differences between the behaviour of these TCP variants when comparing the testbed results to the results from ns-2, but also note that there is generally good agreement.

In networks with very large delay like satellite IPbased networks, standard TCP is unable to correctly grab the available resources. To overcome this problem, Performance Enhancing Proxies (PEPs), which break the end-to-end connection and simulate a receiver close enough to the sender, can be placed before the links with large delay. Although splitting PEPs does not modify the transport protocol at the end nodes, they prevent the use of security protocols such as IPsec. In this paper, we propose solutions to replace the use of PEPs named SatERN. This proposal, based on Explicit Rate Notification (ERN) protocols over IP, does not split connections and is compliant with IP-in-IP tunneling solutions. Finally, we show that the SatERN solution achieves high satellite link utilization and fairness of the satellite traffic.

Increasingly, multimedia applications need higher bandwidth to provide better quality, for example in multi-party HD video conferencing. This demanding class of interactive applications simultaneously require high bandwidth and low end-to-end latency, a conflicting combination that is poorly supported in existing transports. Conventional wisdom dictates that network applications have a choice of transport protocols between TCP, if a reliable service model is desired, or UDP, if control over timing is required. In this paper we present Paceline, an enhanced transport we have devised to support interactive, high-bandwidth applications. Paceline enhances the transport service model to support application adaptation, through prioritization to provide timely delivery of important data, and cancellation to adapt the application rate to match available bandwidth. However, contrary to conventional wisdom, Paceline has not been implemented over UDP, nor does Paceline propose changes to TCP. We believe that the deployment obstacles and duplication of effort faced by solutions that alter or replace TCP entirely outweigh the challenges of mitigating its impairments. Instead, Paceline employs several mechanisms to support timely priority order delivery and cancellation above TCP: an application-level rate controller to reduce queueing delay due to excessive socket buffering, failover among connections to handle extreme cases of congestion, and message fragmentation to reduce the granularity of preemption. Our evaluation shows that Paceline improves upon conventional end-to-end latency shortcomings of using TCP, by factor of 3 in median latency and a factor of 4 in worst case latency. Meanwhile, Paceline is able to preserve TCP's performance in terms of fairness and utilization. Finally, we compare application performance with Paceline to a representative TCP alternative, Structured Stream Transport (SST), showing Paceline to be highly competitive.