• The KIPS Transactions:PartC
• /
• v.9C no.4
• /
• pp.513-522
• /
• 2002

Current end-to-end congestion control depends only on the information of end points (using three duplicate ACK packets) and generally responds slowly to the network congestion. This mechanism can't avoid TCP global synchronization which TCP congestion window size is fluctuated during congestion occurred and if RTT (Round Trip Time) is increased, three duplicate ACK packets is not a correct congestion signal because congestion maybe already disappeared and the host may send more packets until receive the three duplicate ACK packets. Recently there is increasing interest in solving end-to-end congestion control using active network frameworks to improve the performance of TCP protocols. ACC (Active congestion control) is a variation of TCP-based congestion control with queue management In addition traffic modifications nay begin at the congested router (active router) so that ACC will respond more quickly to congestion than TCP variants. The advantage of this method is that the host uses the information provided by the active routers as well as the end points in order to relieve congestion and improve throughput. In this paper, we model enhanced ACC, provide its algorithm which control the congestion by using information in core networks and communications between active routers, and finally demonstrate enhanced performance by simulation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10d
• /
• pp.245-248
• /
• 2006

최근 UDP를 이용한 실시간 어플리케이션이 증가하고 있지만, 대부분 혼잡제어를 사용하지 않고 있다. 이러한 문제를 해결하기 위하여 IETF에서는 UDP를 대신하면서 실시간 트래픽 전송을 위하여 혼잡제어 메커니즘을 포함한 DCCP(Datagram Congestion Control Protocol)를 제안하였다. DCCP는 윈도우 기반 흐름제어를 사용하여 실시간 트래픽을 지원하기 위하여 제안된 차세대 전송 프로토콜이다. 본 논문에서는 DCCP의 기본 개념과 혼잡제어 기법을 소개하고, 유선과 무선에서 다양한 전송 프로토콜을 이용하여 DCCP의 성능평가를 한다. DCCP를 기반으로 유선과 무선 네트워크 환경에서 시뮬레이션 성능분석을 위해 Network Simulator 2(NS-2)를 이용한다.

• Journal of KIISE:Information Networking
• /
• v.29 no.3
• /
• pp.233-241
• /
• 2002

In this paper, we proposed a new mechanism that solves the fairness problem between unicast traffic using the TCP and multicast traffic using the UDP, and satisfies the requirement of various receivers fairly in the Internet. The proposed mechanism decentralizes the load of blanket transmission rate control from sender to designated server, and uses the method that talc designated server intercepts the sender's data and controls the transmission rate suitable for it's local network. Therefore, the proposed mechanism not only provides multicast service by accurate estimation of the network status of each receiver, but also realizes both the inter-session fairness and the intra-session fairness problem.

• Annual Conference of KIPS
• /
• 2009.04a
• /
• pp.1348-1351
• /
• 2009

패킷 재배치(packet reodering)는 전송한 패킷의 순서가 처음과 다르게 뒤섞여 수신지에 도착하는 현상을 의미한다. 패킷 재배치는 불필요한 재전송이나 불필요한 혼잡 제어를 수행하여 TCP의 성능을 저하시킨다. 패킷 재배치에 의한 TCP 성능 저하를 막기 위해 다양한 접근 방법이 소개되었다. TCP-DAD는 기존 TCP에서 3으로 고정된 중복 응답 임계값을 동적으로 조절하여, 잘못된 혼잡 제어를 예방하고 있다. 일반적으로 전송한 패킷의 수가 많을 때, 패킷 재배치를 경험할 확률이 높으며, 패킷 재배치에 의해 잘못된 혼잡 제어가 일어날 가능성 많다. 고속 네트워크 환경에서는 혼잡 윈도우 크기 변화의 폭이 매우 크다는 점을 고려할 때, 중복 응답 임계값을 조절하는 TCP-DAD는 한계가 있다. 본 논문에서는 고속 네트워크 환경에서의 패킷 재배치 현상으로 인한 TCP 성능저하를 완화하기 위한 새로운 알고리즘 TCP-DT를 소개한다. 이는 중복 응답 수에 의존하지 않고 타이머를 통해 혼잡 제어를 수행하는 메커니즘 이다. 본 논문은 NS-2를 사용하여 고속 네트워크 환경에서의 시뮬레이션을 통해 제안한 TCP-DT의 성능 향상을 증명하였다.

• Journal of KIISE:Information Networking
• /
• v.32 no.1
• /
• pp.12-19
• /
• 2005

Reliable transport protocols such as TCP are tuned to Perform well in traditional networks where packet losses occur mainly because of congestion. In a wireless network, however, packet losses will occur more often due to reasons such as the high bit error rate and the handoff rather than due to congestion. When using TCP over wireless network, TCP responds to losses due to the high bit error rate and the handoff by invoking congestion control and avoidance algorithms, resulting in the degraded end-to-end performance in the wireless network. There have been several schemes for improving TCP performance over wireless links. Among them, SNOOP Is a very promising scheme because of the localized retransmission. In this thesis, an efficient scheme is proposed by modifying SNOOP scheme. The invocation of congestion control mechanism is now minimized by knowing the cause of packet loss.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.125-133
• /
• 2008

In this paper, we propose active queue management mechanism (Active-WRED) to guarantee quality of the high priority service class in multi-class traffic service environment. In congestion situation, this mechanism increases drop probability of low priority traffic and reduces the drop probability of the high priority traffic, therefore it can improve the quality of the high priority service. In order to analyze the performance of our mechanism we introduce the stochastic analysis of a discrete-time queueing systems for the performance evaluation of the Active Queue Management (AQM) based congestion control mechanism called Weighted Random Early Detection (WRED) using a two-state Markov-Modulated Bernoulli arrival process (MMBP-2) as the traffic source. A two-dimensional discrete-time Harkov chain is introduced to model the Active-WRED mechanism for two traffic classes (Guaranteed Service and Best Effort Service) where each dimension corresponds to a traffic class with its own parameters.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.652-654
• /
• 2005

인터넷에서의 효율적인 스트리밍 서비스(Streaming Service)를 위해서는 안정된 전송률의 보장이 중요하며, 네트워크의 대역폭이 제한적이기 때문에 네트워크를 공유하는 경쟁 트래픽의 형평성에 대한 고려도 필요하다. 이러한 필요성에 따라 멀티미디어 데이터 전송의 주요 프로토콜인 UDP(User Datagram Protocol)에 혼잡제어 메커니즘 적용에 대한 연구가 활발히 진행되고 있으며, 대표적으로 가용대역 폭 측정을 통한 혼잡제어 기법이 있다. 이 기법은 혼잡제어를 하기 위해서 네트워크의 상태에 따라 가변하는 가용대역폭(Available Bandwidth)을 측정하고 이것을 기반으로 전송률을 조절하는 방식을 말한다. 본 논문에서는 네트워크 상태에 따라 혼잡제어를 하기 위해서 가용대역폭을 보다 빠르고 정확하게 측정하고, 이것을 기반으로 스트리밍 서비스에 맞게 전송률을 조절하는 방법을 제안하였다. 실험을 통해 본 논문에서 제안한 방법이 기존의 가용대역폭을 측정하는 스트리밍 프로토콜 보다 성능이 개선이 되었음을 확인할 수 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1194-1201
• /
• 2003

Measurements of network traffic have shown that self-similarity is a ubiquitous phenomenon spanning across diverse network environments. We have advance the framework of multiple time scale congestion control and show its effectiveness at enhancing performance for fast TCP prototype control. In this paper, we extend the fast TCP prototype 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 fast TCP prototype is facilitated by a simulation bench-mark environment which is based on physical modeling of self-similar traffic. We explicate out methodology for discerning and evaluating the impact of changes in transport protocols in the protocol stack under self-similar traffic conditions. We discuss issues arising in comparative performance evaluation under heavy-tailed workload. workload.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.131-138
• /
• 2007

In wired networks, packet losses mostly occur due to congestion. TCP reacts to the congestion by decreasing its congestion window, thus to reduce network utilization. In wireless networks, however, losses may occur due to the high bit-error rate of the transmission medium or due to fading and mobility. Nevertheless, TCP still reacts to packet losses according to its congestion control scheme, thus to reduce the network utilization unnecessarily. This reduction of network utilization causes the performance of TCP to decrease. In this paper, we predict packet loss by using RSS(Received Signal Strengths) on the wireless and suggest adding RSS flag bit in ACK packet of MH. By using RSS flag bit in ACK, the FH(Fixed Host) decides whether it adopt congestion control scheme or not for the maximum throughput. The result of the simulation by NS-2 shows that the proposed mechanism significantly increases sending amount and receiving amount by 40% at maximum.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.544-545
• /
• 2008

무선 통신 기술의 발달로 최근 무선 device 들로 이루어진 ad-hoc network이 주요 issue가 되고 있으며, ad-hoc network에서의 성능이 중요한 관심사가 되고 있다. 그러나 유선망에 최적화되도록 설계된 TCP 는 무선망이 가지는 링크의 불안정함으로 인한 손실을 네트워크 혼잡에 의한 손실로 인식하여 혼잡 제어 메커니즘이 수행함으로써 전송률을 줄이게 되므로 전체적으로 네크웍의 성능이 저하되는 문제점을 가진다. 본 논문에서는 무선망에서 TCP 성능을 향상시키기 위한 새로운 congestion algorithm을 제안하고 그 성능을 평가하였다. 성능 확인 결과 기존 TCP-vegas에 비해 더 나은 성능을 보임을 알 수 있다.