TCP - IP - IT Library : ZDNet Asia

Case Studies

Vendor Webcast

Show all content

Title Date Added Company

TCP-ROME: Performance and Fairness in Parallel Downloads for Web and Real Time Multimedia Streaming Applications 2007-07-05 Deutsche Telekom

Parallel download protocols that establish multiple TCP connections to distributed replica servers have the potential to reduce file download time and to improve the quality of realtime multimedia downloads. Unfortunately, parallel download protocols are also inherently unfair towards single-flow downloads. This paper presents TCP-ROME, a parallel download protocol that allows a dynamic mitigation of throughput and fairness. A receiver-based framework allows a dynamic adjustment of the congestion and rate control of each subconnection. TCP-ROME offers two usage modes: a binary mode where the congestion control of each subconnection can be switched between TCP-fair rates (high priority) and at a TCP-LP (low priority) fair rate and a more complex range mode where the aggregated throughput aims at meeting a specified target rate.

Tags: Streaming Media

An Analytical Model for Evaluating Utilization of TCP Reno 2007-07-04 University of Rousse

This paper presents an analytical model for TCP Reno. For this model an algorithm is derived to calculate the utilization and packet drop rate. The accuracy of the model is verified by comparing the calculated results versus simulation results. These results show that the TCP Reno is superior to another version(Tahoe) by having higher percentage of utilization and lower percentage of packet dropping rate.

End-to-end Fairness for TCP Traffic in 802.11e Wireless Mesh Networks Without Coordination 2007-07-03 National University of Ireland, Maynooth

This paper considers end-to-end per-station1 and per-flow fair bandwidth allocations for TCP traffic in 802.11 based multi-radio multi-hop networks. First it shows that TCP ACK packets have to be prioritised using IEEE 802.11e since otherwise congestion losses of ACK packets cause unpredictable performance. Then it proves that prioritising ACK packets alone and ignoring TCP data packets results in per-station max-min fairness. In terms of flow level fairness however, this paper highlights that gross unfairness can exist between competing traffic flows due to this per-station max-min fairness. The use of 802.11e's Transmission Opportunity (TXOP) mechanism to enforce/restore fairness is proposed.

Tags: Mobile - Wireless Communications, Wi-Fi (802.11)

Reducing the TCP Acknowledgment Frequency 2007-07-01 Association for Computing Machinery

Delayed acknowledgments were introduced to conserve network and host resources. Further reduction of the acknowledgment frequency can be motivated in the same way. However, reducing the dependency on frequent acknowledgments in TCP is difficult because acknowledgments support reliable delivery, loss recovery, clock out new segments, and serve as input when determining an appropriate sending rate. The results show that in scenarios where there are no obvious advantages of reducing the acknowledgment frequency, performance can be maintained although fewer acknowledgments are sent.

Hidden Terminal Analysis on TCP Stability Over Multihops Ad Hoc Networks 2007-07-01 Zhongnan University of Economics and Law

The goodput of TCP flow over multihops ad hoc networks varies enormously with the increase of hops number between the sender and receiver. This jitter leads to the TCP instability and impediments the web applications in multihops ad hoc networks. This paper points out and verifies that the TCP instability comes from the hidden terminal problem due to the MAC layer collisions through the analysis of the tracing data in extensive simulations. The hidden terminal will produce large volumes of packet collisions and retransmission failures at MAC layer, which results in packet dropping and consequently destroy s the TCP stability. The formalized description of the TCP instability problem and the hidden terminal ratio estimation are also given for providing TCP sending policy.

Application-Level QoS: Improving Video Conferencing Quality Through Sending the Best Packet Next 2007-06-28 Association for Computing Machinery

In a traditional network stack, data from an application is all transmitted in the order that it is received. This paper proposes an algorithm where information about the priority of packets and expiry times is used by the transport layer to reorder or discard packets to optimise the use of the network. This can be used for video conferencing to prioritise important data. This algorithm is implemented as in interface to the Datagram Congestion Control Protocol (DCCP) and compared to UDP and TCP using synthetic traffic modelled on common video conferencing applications. The results obtained show improvement can be made to video conferencing during periods of congestion.

Tags: IP Technologies, Software Engineering

M-TCP+: Using Disconnection Feedback to Improve Performance of TCP in Wired/Wireless Networks 2007-06-28 Simon Fraser University

This paper proposes the M-TCP+ algorithm for heterogeneous wired/wireless networks. The algorithm is a modification of M-TCP that was proposed for deployment in mobile cellular networks. It is recommended that Internet hosts enable the delayed acknowledgement (delayed ACK) option to maximize network bandwidth by reducing the number of ACKs sent to a TCP sender by a TCP receiver. The M-TCP+ algorithm performs best when the TCP delayed ACK option is enabled. The algorithm relies on feedback sent from a wireless host in anticipation of disconnections. The paper compares the performance of the MTCP+ algorithm with the performance of M-TCP, TCP NewReno, and TCP SACK in both the absence and the presence of disconnections for a file transfer protocol (download) application.

Tags: Mobile - Wireless Communications, Wireless

An Extension of the TCP Steady-State Throughput Equation for Parallel TCP Flows 2007-06-27 University of Innsbruck

Almost a decade after its publication in, the steady-state throughput equation of TCP by Padhye et al. remains the most widely used method for calculating the throughput that a TCP sender obtains under certain environment conditions. While there is now a wealth of other models available, many of which are better in some aspect, none of them seems to strike the same balance between precision and ease of use that makes the equation by Padhye et al. the useful tool that it is.

A TCP-Friendly Fuzzy Congestion Controller for Transcoded Video Over the Internet 2007-06-20 University of Essex

Fuzzy logic control of transcoded video streams under UDP offers a flexible congestion response. The paper demonstrates that fuzzy control is compatible with existing TCP-dominated general networks. Simulations across a tight link show that fuzzy control works even when the congestion level feedback signal is not independent of the controlled stream.

Sender Side Intelligence for TCP Throughput Enhancement in Wired-Cum-Wireless Network 2007-06-13 Institute of Electrical and Electronics Engineers

Performance of the TCP Congestion Control Algorithm has been the focus of research over the last decade. This paper proposes modifications to TCP Congestion Control to improve its performance in wired-cum-wireless networks. The key idea to determine the Optimal Congestion Window for a TCP Sender, in a particular network scenario (that corresponds to the fair share of that connection) and keep this congestion window a constant to a point where the fair share in the network has changed considerably from the instance of the calculation of the size of the last window. At this point, the TCP Congestion Window is recalculated according to the nature of new scenario.

Tags: Mobile - Wireless Communications

Jump to 1 2 3 4 5 6 7 8 [9] 10

Title	Date Added	Company
TCP-ROME: Performance and Fairness in Parallel Downloads for Web and Real Time Multimedia Streaming Applications	2007-07-05	Deutsche Telekom
Parallel download protocols that establish multiple TCP connections to distributed replica servers have the potential to reduce file download time and to improve the quality of realtime multimedia downloads. Unfortunately, parallel download protocols are also inherently unfair towards single-flow downloads. This paper presents TCP-ROME, a parallel download protocol that allows a dynamic mitigation of throughput and fairness. A receiver-based framework allows a dynamic adjustment of the congestion and rate control of each subconnection. TCP-ROME offers two usage modes: a binary mode where the congestion control of each subconnection can be switched between TCP-fair rates (high priority) and at a TCP-LP (low priority) fair rate and a more complex range mode where the aggregated throughput aims at meeting a specified target rate. Tags: Streaming Media
An Analytical Model for Evaluating Utilization of TCP Reno	2007-07-04	University of Rousse
This paper presents an analytical model for TCP Reno. For this model an algorithm is derived to calculate the utilization and packet drop rate. The accuracy of the model is verified by comparing the calculated results versus simulation results. These results show that the TCP Reno is superior to another version(Tahoe) by having higher percentage of utilization and lower percentage of packet dropping rate.
End-to-end Fairness for TCP Traffic in 802.11e Wireless Mesh Networks Without Coordination	2007-07-03	National University of Ireland, Maynooth
This paper considers end-to-end per-station1 and per-flow fair bandwidth allocations for TCP traffic in 802.11 based multi-radio multi-hop networks. First it shows that TCP ACK packets have to be prioritised using IEEE 802.11e since otherwise congestion losses of ACK packets cause unpredictable performance. Then it proves that prioritising ACK packets alone and ignoring TCP data packets results in per-station max-min fairness. In terms of flow level fairness however, this paper highlights that gross unfairness can exist between competing traffic flows due to this per-station max-min fairness. The use of 802.11e's Transmission Opportunity (TXOP) mechanism to enforce/restore fairness is proposed. Tags: Mobile - Wireless Communications, Wi-Fi (802.11)
Reducing the TCP Acknowledgment Frequency	2007-07-01	Association for Computing Machinery
Delayed acknowledgments were introduced to conserve network and host resources. Further reduction of the acknowledgment frequency can be motivated in the same way. However, reducing the dependency on frequent acknowledgments in TCP is difficult because acknowledgments support reliable delivery, loss recovery, clock out new segments, and serve as input when determining an appropriate sending rate. The results show that in scenarios where there are no obvious advantages of reducing the acknowledgment frequency, performance can be maintained although fewer acknowledgments are sent.
Hidden Terminal Analysis on TCP Stability Over Multihops Ad Hoc Networks	2007-07-01	Zhongnan University of Economics and Law
The goodput of TCP flow over multihops ad hoc networks varies enormously with the increase of hops number between the sender and receiver. This jitter leads to the TCP instability and impediments the web applications in multihops ad hoc networks. This paper points out and verifies that the TCP instability comes from the hidden terminal problem due to the MAC layer collisions through the analysis of the tracing data in extensive simulations. The hidden terminal will produce large volumes of packet collisions and retransmission failures at MAC layer, which results in packet dropping and consequently destroy s the TCP stability. The formalized description of the TCP instability problem and the hidden terminal ratio estimation are also given for providing TCP sending policy.
Application-Level QoS: Improving Video Conferencing Quality Through Sending the Best Packet Next	2007-06-28	Association for Computing Machinery
In a traditional network stack, data from an application is all transmitted in the order that it is received. This paper proposes an algorithm where information about the priority of packets and expiry times is used by the transport layer to reorder or discard packets to optimise the use of the network. This can be used for video conferencing to prioritise important data. This algorithm is implemented as in interface to the Datagram Congestion Control Protocol (DCCP) and compared to UDP and TCP using synthetic traffic modelled on common video conferencing applications. The results obtained show improvement can be made to video conferencing during periods of congestion. Tags: IP Technologies, Software Engineering
M-TCP+: Using Disconnection Feedback to Improve Performance of TCP in Wired/Wireless Networks	2007-06-28	Simon Fraser University
This paper proposes the M-TCP+ algorithm for heterogeneous wired/wireless networks. The algorithm is a modification of M-TCP that was proposed for deployment in mobile cellular networks. It is recommended that Internet hosts enable the delayed acknowledgement (delayed ACK) option to maximize network bandwidth by reducing the number of ACKs sent to a TCP sender by a TCP receiver. The M-TCP+ algorithm performs best when the TCP delayed ACK option is enabled. The algorithm relies on feedback sent from a wireless host in anticipation of disconnections. The paper compares the performance of the MTCP+ algorithm with the performance of M-TCP, TCP NewReno, and TCP SACK in both the absence and the presence of disconnections for a file transfer protocol (download) application. Tags: Mobile - Wireless Communications, Wireless
An Extension of the TCP Steady-State Throughput Equation for Parallel TCP Flows	2007-06-27	University of Innsbruck
Almost a decade after its publication in, the steady-state throughput equation of TCP by Padhye et al. remains the most widely used method for calculating the throughput that a TCP sender obtains under certain environment conditions. While there is now a wealth of other models available, many of which are better in some aspect, none of them seems to strike the same balance between precision and ease of use that makes the equation by Padhye et al. the useful tool that it is.
A TCP-Friendly Fuzzy Congestion Controller for Transcoded Video Over the Internet	2007-06-20	University of Essex
Fuzzy logic control of transcoded video streams under UDP offers a flexible congestion response. The paper demonstrates that fuzzy control is compatible with existing TCP-dominated general networks. Simulations across a tight link show that fuzzy control works even when the congestion level feedback signal is not independent of the controlled stream.
Sender Side Intelligence for TCP Throughput Enhancement in Wired-Cum-Wireless Network	2007-06-13	Institute of Electrical and Electronics Engineers
Performance of the TCP Congestion Control Algorithm has been the focus of research over the last decade. This paper proposes modifications to TCP Congestion Control to improve its performance in wired-cum-wireless networks. The key idea to determine the Optimal Congestion Window for a TCP Sender, in a particular network scenario (that corresponds to the fair share of that connection) and keep this congestion window a constant to a point where the fair share in the network has changed considerably from the instance of the calculation of the size of the last window. At this point, the TCP Congestion Window is recalculated according to the nature of new scenario. Tags: Mobile - Wireless Communications