• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.40-48
• /
• 2000

ABR 서비스에서 전송률 제어 방식은 크게 크래딧 방식과 전송률 기반 방식으로 구분되는데, 전송률 기반 방식의 대표적인 스위치 알고리즘인 EPRCA(Enhanced Properties RATE Control Algorithm)를 비롯하여 지금까지 제안된 전송률 기반 폭주제어방법은 대부분 스위치의 평균 큐 길이 Q 에 의한 폭주제어 방식을 사용한다. [2, 6, 8]. 폭주판단방법은 큐 임계치 방식, 부하 임계치 방식, 큐 증가 임계치 방식으로 나눌 수있다. 큐 임게치 만을 사용하는 방법이 가장 일반적이지만, 큐 길이와 큐 임계치의 비교에 따른 지연이 발생하게 된다. 본 논문에서는 큐 길이의 증감 상태를 큐 임계치와 동시에 사용하여 폭주제어를 신속히 할 수 있는 스위치 알고리즘을 제안한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.4
• /
• pp.716-722
• /
• 2001

This paper has defined the 3G and beyond wireless networks as the one that is based on IP network architecture and proposed the congestion control scheme in the access networks. Basically the proposed method is built on the ECN(Explicit Congestion Notification) and utilizing the advantages of the wireless and I networks in broadcasting packet in their access network. Consequently it provides the efficiency in controlling the congestion that can be happened by the mobility support in the future wireless networks.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.11A
• /
• pp.1709-1716
• /
• 2000

ATM 스위치에서 입력 트래픽의 링크 이용의 불확실성과 입력 트래픽에 대한 예측 오류 등으로 인한 폭주가 발생될 가능성을 완전히 배제할 수 없기 때문에 스위치내부에서 폭주 발생을 억제할 수 있는 방법이모새되어야 한다.본 논문에서는 스위치 내부 링크의 대역 사용량을 측정하여 폭주 및 트래픽 제어를 수행하고 링크 이용률을 최대화하기 위한대역 할당 알고리즘을 제안한다. 폭주가 발생한 링크에 대하여 짧은 시간 내에 폭주를 해결하고 폭주가 발생하지 않은 링크에서는 사용하고 남은 여분의 대역을 공평하게 할당함으로서 링크의 이용률을 극대화할 수 있으므로 트래픽 관리를 보다 쉽고 효율적으로 수행할 수 있다.

• The Journal of Engineering Research
• /
• v.6 no.2
• /
• pp.39-46
• /
• 2004

In this paper, we carry out a performance study related to the Broadband Network. For this network, it has been proposed to use the leaky bucket as a way of controlling congestion within the network. On the top of leaky bucket type rate based congestion control scheme for high speed networks, a user will typically operate an error control scheme for retransmitting lost and erroneous packets. We propose a performance model in order to study the interaction between a user's error control scheme and the leaky bucket congestion control scheme for high speed networks. Simulation results show that parameters such as the window size and the token generation rate in the leaky bucket are key factors affecting the end-to-end delay.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.1
• /
• pp.39-43
• /
• 2007

In high speed communication networks, the determination of a transmission rate is critical for the stability of a closed-loop network system with the congestion control scheme. In ATM networks, the available bit rate (ABR) service is based on a feedback mechanism, i.e., the network status is transferred to the ABR source by a resource management (RM) cell. RM cells contain the traffic information of the downstream nodes for the traffic rate control. However, the traffic status of the downstream nodes can not be directly transferred to the source node in the IP based networks. In this paper, a new rate-based congestion control scheme using an exponential weighted moving average algorithm is proposed to build an efficient feedback control law for congestion avoidance in high speed communication networks. The proposed congestion control scheme assures the stability of switch buffers and higher link utilization of the network. Moreover, we note that the proposed congestion scheme can flexibly work along with the increasing number of input sources in the network, which results in an improved scalability.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.4
• /
• pp.112-119
• /
• 2000

In this paper, it aims at two different situation such that a preventive control which means, it never has network information in case of occurring congestion in network, and a reactive control which means, after the congestion simply happens. it is not effective to recover with congestion just because of extensive delay for an electric wave. To solve the problems, threshold is set up with buffer in multiplex system, and executes a congestion control by FBLB which is FeedBack Leaky Bucket Algorithm. As suggested by FBLB Algorithm. the outcome of performance could be compared with Buffered Leaky Bucket Algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.9A
• /
• pp.1299-1305
• /
• 2000

In B-ISDN, to realize ATM, the optimum control method of multi-media traffic must be proposed. Because there is not the traffic model of multi-media to make clear, the realization of optimum ATM congestion control is very difficult. In this paper, the traffic model is assumed to be slowly time-variable non-linear function and for real-time prediction of it, new model which is composed with parallel triple neural networks is proposed. And the simulation to predict assumed ATM traffic is executed. From the result, it's capability is shown that the proposed neural network model can be used in ATM congestion control.

• The KIPS Transactions:PartC
• /
• v.9C no.1
• /
• pp.39-44
• /
• 2002

In this paper, in order to improve the performance of TCP short traffic application services in wireless Internet environments, the Split-ACKs (SPACK) scheme is proposed. In wireless networks, unlike wired networks, packet losses will occur more often due to high bit error rates. Therefore, each packet loss over wireless lints results in congestion control procedure of TCP being invoked at the source. This causes severe end-to-end Performance degradation of TCP. In this paper, to alleviate the TCP Performance, the SPACK method, split acknowledgement Packets in the base station, is proposed. Using computer simulation, the performance of TCP using SPACK is analysed and shows better performance than traditional TCP Protocol.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.6
• /
• pp.1085-1094
• /
• 1994

We propose a traffic flow control scheme of B-NT with temporary cell buffering and selective cell discarding to prevent congestion state of the network nodes in B-ISDN systems to reduce or suppress output cell strams towards T interface. We define the states of the network nodes as normal, pre-congestion, and congestion. In a pre-congestion state, the loss-sensitive traffic is temporarily buffered to slow down the rate of the output traffic streams. In a congestion state, the delay-sensitive traffic is selectively discarded to suppress the output traffic streams as possible in addition to the cell buffering. We model the input cell streams and the states of the network nodes with Interrupted Bernoulli Process and 3-state Markov chain to analyze the performance of the proposed scheme in the B-NT system. The appropriate size of the cell buffer is explored by means of simulation and the influence on the performance of the proposed scheme by the network node state is discussed. As results, more than 2,00 cells of buffer size is needed for the control of medium of lower than the medium, degree of congestion occurrence in the network node while the control of high degree of congestion occurrence is nearly impossible.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10c
• /
• pp.745-747
• /
• 1999

인터넷이 급성장함에 따라 사용자의 더 나은 서비스에 대한 요구 역시 급증하였다. 네트웍 연구가들은 제한된 네트웍 자원 하에서 오류제어, 흐름 제어, 그리고 폭주 제어를 적절히 수행함으로써 전송 품질을 향상시키는 방법들에 대해 연구해 오고 있다. 그러나 인터넷 연구의 가장 큰 난점 중 하나가 인터넷에는 네트웍의 상태를 모니터링할 수 있는 근간이 되는 방법이 기본적으로 지원되고 있지 않다는 점이고 따라서 네트웍의 구조와 상태, 플로우의 흐름 및 통계 등에 대한 기본 자료가 부족한 실정이다. 오류 제어나 흐름 제어, 그리고 폭주제어 기술을 연구할 때 가장 필요한 자료중의 하나가 네트웍 토폴로지이다. 그 중에서도 송신자와 수신자 사이의 거리 정보인 Network Diameter가 있다. 기존 연구에서는 연구자 임의로 이 값을 할당하거나 혹은 특정 실험실에서만 유효한 Network Diameter가 있다. 기존 연구에서는 연구자 임의로 이 값을 할당하거나 혹은 특정 실험에서만 유효한 Network Diameter 값을 제시해오고 있었다. 이 논문에서는 이처럼 비객관적이거나 특수값으로만 사용되어 오던 Internet Diameter를 실효 접속에 근거하여 측정하는 알고리즘을 제안하고, KAIST에서 전세계로 나가는 실측 접속 자료로부터 접속 Hop Count의 분포를 측정하며 이를 통해 타 인터넷 연구에 적절한 자료를 제시한다.