• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.211-213
• /
• 2013

TCP는 네트워크에서 손실 없이 데이터를 전송하는 전송 프로토콜이다. TCP는 전송 초기에 대역폭을 알지 못하는 상황에서 혼잡 윈도우의 지수적 증가를 통하여 전송하는 슬로우 스타트 단계를 수행한다. 지수적 증가의 특성으로 말미암아 폭주 가능성이 발생하고, 이는 네트워크의 변동성이 심할수록 가중된다. 본 논문에서는 이러한 문제점을 해결하기 위해 기존의 Hybrid Start 방법을 개선한 통계적 슬로우 스타트 방법을 제안하며 이를 통하여 TCP 성능을 개선한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.8
• /
• pp.597-606
• /
• 2013

The performance of TCP depends on the degree of traffic congestion between the sender and the receiver. The traffic could increase, and this causes congestion which may cause trouble in data transfer. Then, TCP tries to eliminate the trouble by reducing the transfer speed with slowstart scheme. When a mobile node moves over heterogeneous wireless networks, TCP experiences dramatic change of the amount of traffic, and it performs slowstart. In this paper, we propose the efficient scheme of TCP slowstart that should performs after vertical handoff. In this scheme, TCP receiver forces slowstart, which is different form normal schemes. Its performance is better than the normal schemes in that TCP sender experiences traffic congestion and performs slowstart. We perform simulation to measure and to verify the improved performance.

• 대한공업교육학회지
• /
• v.33 no.2
• /
• pp.248-258
• /
• 2008

Current Internet uses HTTP (Hyper Text Transfer Protocol) as an application layer protocol and TCP (Transmission Control Protocol) as a transport layer protocol to provide web service. SCTP (Stream Control Transmission Protocol) is a recently proposed transport protocol with very similar congestion control mechanisms as TCP, except the initial congestion window during the slow start phase. In this paper, we present a mathematical model of object transfer latency during the slow start phase for HTTP over SCTP and compare with the latency of HTTP over TCP. Validation of the model using experimental result shows that the mean object transfer latency for HTTP over SCTP during the slow start phase is less than that for HTTP over TCP by 11%.

• 대한공업교육학회지
• /
• v.32 no.2
• /
• pp.199-216
• /
• 2007

Stream Control Transmission Protocol(SCTP) is a transport layer protocol to support the data transmission. SCTP is similar to Transmission Control Protocol(TCP) in a variety of aspects. However, several features of SCTP including multi-homing and multi-streaming incur the performance difference from TCP. This paper highlights the data transfer during the initial slow start phase in SCTP congestion control composed of slow start phase and congestion avoidance phase. In order to compare the mean transfer time between SCTP and TCP, we experiment with different performance parameters including bandwidth, round trip time, and data length. By varying data length, we also measure the corresponding initial window size, which is one of factors affecting the mean transfer time. For the experiment, we have written server and client applications by C language using SCTP socket API and have measured the transfer time by ethereal program. We transferred data between client and server using round-robin method. Analysis of these experimental results from the testbed implementation shows that larger initial window size of SCTP than that of TCP brings the reduction in the mean transfer time of SCTP compared with TCP by 15 % on average during the initial slow start phase.

• Journal of Internet of Things and Convergence
• /
• v.1 no.1
• /
• pp.1-4
• /
• 2015

This paper aims to present the mathematical model to find the mean web object transfer latency in the slow-start phase of TCP congestion control mechanism, which is one of the main control techniques of Internet. Mean latency is an important service quality measure of end-user in the network. The application area of the proposed latency model is the narrowband environment including multi-hop wireless network and Internet of Things(IoT), where packet loss occurs in the slow-start phase only due to small window. The model finds the latency considering initial window size and the packet loss rate. Our model shows that for a given packet loss rate, round trip time and initial window size mainly affect the mean web object transfer latency. The proposed model can be applied to estimate the mean response time that end user requires in the IoT service applications.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.1 no.2
• /
• pp.64-72
• /
• 2006

The long propagation delay over satellite internet causes degradation of TCP performance in slow start phase. Especially, web traffic performance is greatly reduced by low throughput in slow start phase. To improve web traffic performance, we propose the Dynamic ACK Generation Scheme which generates ACKs and considers sender RTO in PEP (Performance Enhancing Proxy). The Normal ACK generation mechanism improves TCP throughput, and also decreases sender RTO. if PEP stops generating ACKs, TCP performance will be reduced by frequent RTO expiration. To solve this problem, our scheme adjusts RTO using ACK generation interval. And it supports retransmission mechanism for loss recovery in PEP. The results of the performance analysis provide a good evidence to demonstrate the efficiency of our mechanisms over satellite internet.

• Journal of Digital Contents Society
• /
• v.15 no.2
• /
• pp.147-154
• /
• 2014

There have been company researches for TCP-Westwood algorithms in wireless TCP environment with high packet loss rate. Because the TCP-Westwood algorithm adjusts the congestion window according to the ABE(Available Bandwidth Estimation), the algorithm has a problem which the accuracy of ABE decreases as the error rate increases. To solve such a problem, the proposed scheme in this paper adopts the existing packet pattern based algorithm that the ABE is ignored when the arriving interval time of ACK is longer than a given interval time and uses new algorithm that the ABE is reallocated to a given allowable ABE when the ABE is over the allowable range. The proposed scheme shows the simulation result that the ABE is closest to the setting bandwidth for simulation compared to the existing algorithms.