• The KIPS Transactions:PartC
• /
• v.8C no.3
• /
• pp.335-344
• /
• 2001

최근 인터넷 환경이 반도체, 광통신 그리고 차세대 인터넷 기술의 발달로 고성능화 되어가고 있다. 따라서 고성능 인터넷을 위한 TCP의 성능 향상 연구가 매우 중요해졌다. 그러나 기존 TCP는 수신위도 버퍼의 물리적 크기에 의하여 최대 전송 성능과 대역폭 탐색 기능이 제한을 받는 구조적인 문제점을 갖고 있다. 본 논문에서는 이를 해결하기 위하여 수신 호스트에 가상 윈도 개념을 도입하였다. 이는 송신 호스트가 RTT 동안 균일하게 세그먼트를 분산시켜서 패킷을 전송할 때 세그먼트 간격 시간 동안 수신 호스트의 처리 능력을 가상윈도로 나타내는 것이다. 따라서 가상 윈도의 크기는 수신 호스트의 성능에 비례하기 때문에 수신 호스트가 고성능일 경우 TCP의 전송 능력 성능이 더 높아질 수 있다. 초고속 인터넷일 경우 제안 알고리즘이 기존 TCP보다 전송능력에 있어 1.5∼5배 개선되는 것을 네트워크 시뮬레이션인 NS2를 이용하여 확인하였다.

• The KIPS Transactions:PartC
• /
• v.11C no.6 s.95
• /
• pp.787-798
• /
• 2004

High performance net재rking is one of key factors to provide support for data intensive applications in the Internet. Extended frame size has a major impact on end to-end performance with increasing effective TCP throughput and decreasing system overhead. Most of the research about extended frames has focused on local area network performance and the impact that extended frame size has on the system elements including memory, network interface card and so forth. In the paper, we analyse the effects of the extended frames to the other traffic flows sharing Internet paths for the wide area performance of TCP by conducting various network simulations. Results show that securing available bandwidth in no loss and low delay networks is indispensable to exploit the efficiency of extended frames.

• Journal of Communications and Networks
• /
• v.8 no.4
• /
• pp.391-400
• /
• 2006

With the on-going wireless access technologies, the Internet has become accessible anytime anywhere. In wireless networks, link errors significantly degrade the performance of the transmission control protocol (TCP). To cope with this issue, this paper improves the recently-proposed terrestrial REFWA (T-REFWA) scheme by adding a new error recovery mechanism to its original design. In the T-REFWA scheme, senders are acknowledged with appropriate sending rates at which an efficient and fair utilization of network resources can be achieved. As the feedback values are computed independently of link errors, senders can keep transmitting data at high rates even in case of link error occurrences. Using this feature, the proposed error recovery mechanism can achieve high throughput in environments with high bit error rates. The throughput is further improved by disabling the exponential back-off algorithm of TCP so that long idle times are avoided in case of link errors. We show through simulations that the proposed method improves TCP performance in high bit error rates. Compared with several TCP variants, the proposed error recovery scheme exhibits higher link utilization and guarantees system fairness for different bit error rates.

• Journal of KIISE:Information Networking
• /
• v.30 no.6
• /
• pp.743-754
• /
• 2003

TFRC(TCP-Friendly Rate Control) is proposed to satisfy the demands of multimedia applications while being reasonably fair when competing for bandwidth with TCP flows[1-3]. However, TFRC has a shortcoming that the fairness and throughput are degraded when the mobile host using TFRC experiences handoffs. This paper proposes a new control mechanism based on TFRC, which deals with the congestion caused by handoffs as well as the losses caused during the handoffs. The simulation results show that our mechanism achieves better throughput and fairness compared to TFRC for repeated handoffs.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.9A
• /
• pp.790-795
• /
• 2011

The need for broadband wireless data networks such as IEEE 802.16e WiMAX systems increases as a variety of wireless information devices like smart phones are adopted rapidly in everyday life. Since most of mobile applications employ TCP as their transport layer protocol, the performance improvement of TCP in WiMAX systems is crucial. This paper proposes an efficient method to transmit uplink piggyback ACK packets by exploiting the uplink packet buffering which happens because of the resource allocation scheme of the WiMAX systems. The proposed method can support not only the ACK filtering but also the merging of the piggyback ACK packets. As a result, the bandwidth reduction in the piggyback ACK packet transmission leads to the improvement of the downlink throughput. The simulation results show that the bandwidth for the ACK packets reduces more than 90%, and the downlink throughput increases at least 30%.

• Proceedings of the IEEK Conference
• /
• 2000.11a
• /
• pp.221-224
• /
• 2000

The issue of supporting TCP traffic over ATM networks is currently one of the most important issues in the field of data networks. One important part of this issue is congestion control. In general, congestion control uses method such as packet drop to relieve network resource when the network is congested so as to maintain high throughput and low delay. In addition, congestion control is required to ensure fair sharing of resources among all users during congestion. In this paper we propose a new congestion control method using WRED & per-VC accounting mechanism. This packet discard scheme is proposed with the goal to provide both good performance in terms of throughput and fairness in terms of bandwidth exploitation of the output link among all virtual circuits.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.1
• /
• pp.43-47
• /
• 2021

This paper investigates the network throughput of PLC (Power Line Communication) system in the in-building network. The OFDM (Orthogonal Frequency Division Multiplexing) modulation format and adaptive bit loading algorithm is used to minimize the effect of signal loss and noise on transmission performance in the power line channel characterized by frequency selective fading. The network throughput of the PLC system which consists of gateway and CPE（Customer Premise Equipment) PLC modem in the in-building network is measured by network performance measurement tool, iperf and analyzed according to the TCP (Transmission Control Protocol) window size.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.12B
• /
• pp.1106-1114
• /
• 2003

Several analytic models describe transmission control protocol (TCP) performance such as steady-state throughput as an averaged ratio of number of transmissions to latency. For more detailed analysis of TCP latency, the latency during packet losses are recovered should be considered. In this paper, we derive the expected duration of loss recovery latency considering the number of packet losses recovered by retransmissions. Based on the numerical results verified by simulations, TCP using selective acknowledgement (SACK) option is more effective than TCP NewReno from the aspect of loss recovery latency.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.541-543
• /
• 2004

TCP does not distinguish between congestion and packet losses due to route change and link failures, which are prevalent in mobile ad hoc networks. So, TCP does not show satisfactory performance in ad hoc networks since it assumes that all packet losses are due to network congestions. In particular, when a route is reestablished it needs to be adaptively determined CWND according to the new route features. In this paper, we proposed CWND adjustment scheme to improve the TCP performance overad hoc networks. TCP sender effectively adjusts CWND by monitoring the network situation using control packets. Simulation results using NS-2 show that the proposed scheme increases TCP throughput compared with those of general TCP.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.181-183
• /
• 2004

본 논문은 TCP에서 사용되는 혼잡 제어 방식의 문제점인 전송 시간에 대한 전송률 편중 현상을 완화시키기 위한 비례 증가 혼잡 제어 방식을 제안한다. TCP는 네트워크의 혼잡 상황을 제어하기 위하여 ACK 기반의 혼잡 윈도우 조정 방식을 사용한다. 그러나 기존 TCP에서 사용되는 혼잡 제어 방식은 그 자체적으로 네트워크의 혼잡 상황을 유도하며, 전송 시간이 다른 두 개의 TCP 연결이 하나의 병목 지점을 공유할 경우, 전송 시간의 차이에 따라 전송률의 편중 현상이 나타난다. 본 논문에서는 이러한 네트워크 혼잡 상황 유발과 전송 시간의 차이에 따른 전송률 편중 현상을 완화시키기 위한 송신자 기반의 네트워크 대역폭 측정 방법 및 비례 증가 혼잡 제어 알고리즘을 제안하며, 구현 및 실험을 통해 기존 TCP의 문제점을 해결할 수 있음을 보인다.