• Journal of Digital Contents Society
• /
• v.16 no.3
• /
• pp.381-388
• /
• 2015

TCP, which performs congestion control in congestion condition, is able to help a reliable transmission. However, packet loss can be increased because congestion window is increased by the time the packet is dropped in the process of congestion avoidance. In this paper, to solve the above problem, we propose a new congestion estimation based TCP congestion control scheme using the weighted average value of the RTT. After measuring a SRTT, which means the weighted average value of RTTs, at this point of time when a buffer overflow is occurred by an overloaded packet, the proposed scheme estimates the time, when the same SRTT is made in packet transmission, as a congestion time and then decreases the congestion window. The simulation results show that the proposed schem has a good performance in terms of packet loss rate and throughput when the packet loss due to buffer overflow is larger than that due to wireless channel.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.7
• /
• pp.1609-1617
• /
• 2013

TFRC(TCP-Friendly Rate Control) has a performance degradation in wireless networks because it performs congestion control by judging all the losses occurred in wireless networks as a congestion indicator. It is also degraded by the increased Round Trip Time(RTT) due to packet retransmission and contention overhead in the link layer. In this paper, we propose an adaptive rate control scheme based on cross-layer to improve the quality of streaming services in the wireless networks. It provides new RTT estimation and loss discrimination methods to improve transmission rate of TFRC. The simulation results show that the proposed scheme can improve the performance of TFRC.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.1
• /
• pp.175-183
• /
• 2008

QoS-support technology in networks is based on measuring QoS metrics which reflect a magnitude of stability and performance. The one-way delay measurement of the QoS metrics especially requires a guarantee of clock synchronization between end-to-end hosts. However, the hosts in networks have a relative or absolute difference in clock time by reason of clock offsets. flock skews and clock adjustments. In this paper, we present a theorem, methods and simulation results of one-way delay and clock offset estimations between end-to-end hosts. The proposed theorem is a relationship between one-way delay, one-way delay variation and round-trip time And we show that the estimation error is mathematically smaller than a quarter of round-trip time.

• The KIPS Transactions:PartC
• /
• v.13C no.3 s.106
• /
• pp.353-358
• /
• 2006

Unlike TCP Reno, TCP Vegas recognizes network congestion through the measuring of RTT (Round Trip Time) and decides the main congestion control parameters, such as Windows size. But, congestion avoidance scheme of Vegas poorly reflects asymmetric characteristics of packet path because TCP Vegas uses the measuring of RTT that reflects forward/backward packet transmission delay as a forward delay. The RTT can't infer the forward/backward transmission delay variation because it only measures the packet's turn around time. In this paper, We have designed and implemented a new Vegas congestion control algorithm that can distinguish forward/backward network congestion. We have modified the source codes of TCP Vegas in Linux 2.6 kernel and verified their performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.5B
• /
• pp.509-516
• /
• 2009

The Stream Control Transmission Protocol(SCTP) is a reliable transport layer protocol that provides several features. Multihoming is the one of the features and allows an association(SCTP's term for a connection) between two endpoints to use multiple paths. One of the paths, called a primary path, is used for initial data transmission and in the case of retransmission an alternate path is used. SCTP's current retransmission policy attempts to improve the chance of success by sending all retransmissions to an alternate destination address. However, SCTP's current retransmission policy has been shown to actually degrade performance in many circumstances. It is because that, due to Karn's algorithm, successful retransmissions on the alternate path cannot be used to update RTT(Round-Trip Time) estimation for the alternate path. In this paper we propose a scheme to avoid such performance degradation. We utilize 2bits which is not used in the flag field of DATA and SACK chunks to disambiguate original transmissions from retransmissions and to keep RTT and RTO(Retransmission Time-Out) values more accurate.

• Journal of KIISE:Information Networking
• /
• v.32 no.3
• /
• pp.359-369
• /
• 2005

Delay estimation is a difficult Problem in computer networks. Accurate one-way delay estimation is crucial because it serves a very important role in network performance and thus application design. RTT(Round Trip Time) is often used as an approximation of the delay, but because it is a sum of the forward and reverse delays, the actual one-way delay cannot be estimated accurately from RTT. To estimate one-way delay accurately, this paper proposes a new scheme that analytically derives one-way delay, forward and reverse delay respectively. We show that the performance of TCP can improve dramatically in asymmetric networks using our scheme. A key contribution of this paper is that our one-way deiay estimation is much more accurate than RTT estimation so that TCP can quickly find the network capacity in the slow start phase. Since RTT is the sum of the forward and reverse delays, our scheme can be applied to any protocol that is based on RTT.

• Journal of KIISE
• /
• v.42 no.9
• /
• pp.1162-1174
• /
• 2015

These days, the networks have exhibited HBDP (High Bandwidth Delay Product) characteristics. The legacy TCP slowly increases the size of the congestion window and drastically decreases the size of a congestion window. The legacy TCP has been found to be unsuitable for HBDP networks. TCP mechanisms for solving the problems of the legacy TCP can be categorized into the loss-based TCP and the delay-based TCP. Most of the TCP mechanisms use the standard slow start phase, which leads to a heavy packet loss event caused by the overshoot. Also, in the case of congestion avoidance, the loss-based TCP has shown problems of wastage in terms of the bandwidth and RTT (Round Trip Time) fairness. The delay-based TCP has shown a slow increase in speed and low occupancy of the bandwidth. In this paper, we propose a new scheme for improving the over shoot, increasing the speed of the bandwidth and overcoming the bandwidth occupancy and RTT fairness issues. By monitoring the buffer condition in the bottleneck link, the proposed scheme does congestion control and solves problems of slow start and congestion avoidance. By evaluating performance, we prove that our proposed scheme offers better performance in HBDP networks compared to the previous TCP mechanisms.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7B
• /
• pp.481-488
• /
• 2005

As the demand on the multimedia application increases, the congestion control algorithm for the multimedia applications becomes an important research issue. The ultimate goal of congestion control is to adapt the trans-mission rate at the sender to the mont of network resource available on the forward path. In general, the congestion control algorithms use the round trip time(RTT) to estimate the network congestion on the forward path. however, since the RTT includes the delay on both forward and backward paths, it is possible for the algorithms using the RTT to make a wrong decision such as deciding the congestion on the forward path due to the congestion built on the backward path. In this paper, we enhance the performance of RRC-OTT(Receiver-based rate control with one-way Trip Time) algorithm, which uses the one-way trip time(OTT) to estimate the network congestion. By separating the estimation mechanism on the forward path from the backward path, the performance of RRC-OTT algorithm is hardly affected by the congestion built on the backward path.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.2 no.1
• /
• pp.10-18
• /
• 2007

In this paper, we extend the multiple time scale control framework to window-based congestion control, in particular, TCP. This is performed by interfacing TCP with a large time scale control module which adjusts the aggressiveness of bandwidth consumption behavior exhibited by TCP as a function of "large time scale" network state. i.e., conformation that exceeds the horizon of the feedback loop as determined by RTT. Performance evaluation of multiple time scale TCP is facilitated by a simulation bench-mark environment which is based on physical modeling of self-similar traffic. If source traffic is not extended exceeding, when RTT is 450ms, in self similar burst environment, performance gain of TCP-SSC is up to 45% for ${\alpha}$=1.05. However, its is acquired only 20% performance gain for ${\alpha}$=1.95 relatively. Therefore we showed that by TCP-MTS at large time scale into a rate-based feedback congestion control, we are able to improve two times performance significantly.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.2
• /
• pp.97-103
• /
• 2009

Improving TCP performance has long been the focus of many research efforts in 802.11 wireless networks study. Hop count and Round Trip Time (RTT) are the critical sources which serious affect the TCP performance on end to end connection. In this paper, we analytical derived the affection and based on the analysis we propose TCP should Change its Expected Value (TCP-CEV) when hop count and RTT change by setting a reasonable CWND change rate to improve the performance. The proposed scheme is applicable to a wide range of transport protocols using the basic TCP mechanism, and the protocol behavior is analytically tractable. We show that our simple strategy improves TCP performance at least over 12% in a chain topology, 4.9% in a grid topology and improve the TCP convergence.