• The KIPS Transactions:PartC
• /
• v.12C no.5 s.101
• /
• pp.725-732
• /
• 2005

This paper proposes an implementation methodology of the rate limiting method and the class-based bandwidth management for the gigabit-powered network processor, which are used on general purpose or ASIC systems in order to efficiently manage network bandwidth. Implementation and experiments are done on Intel's IXP1200 network processor. The result shows the accuracy of limited bandwidth and settling time of the estimator against the dynamic traffic rate. Through the results, this paper proves the proposed method and implementation properly work as expected.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.319-321
• /
• 2004

최근 이더넷(Ethernet) 보급과 사용자의 증가 그리고 다양한 응용 서비스들의 등장으로 인하여 점차 네트워크 트래픽이 폭증하고 있다. 이에 따라서 SLA(Service Level Agreement)를 위한 대역폭 조절(Bandwidth의 Regulation)의 중요성은 더욱 높아지고 있다. 그러나 기존에 제시된 대역폭 조절 방식들은 이더넷에 적합하지 않거나 또는 너무 복잡하여, EFM(Ethernet for First Mile)에 적용하기 어려웠다. 그래서 본 논문에서는 이더넷에 적용하기 적합한 간단하면서도 효과적인 대역폭 조절(Bandwidth Regulation) 방법인 속도 계산(Rate Calculation)방식을 제안하며, 제안한 메커니즘에 대한 시뮬레이션을 통한 성능 분석을 수행하였다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.6 s.324
• /
• pp.17-24
• /
• 2004

This paper proposes an efficient technique to protect e-mail server from DDoS attack using the CBQ (Class Based Queuing) algorithm The proposed method classifies incoming trafic to an e-mail server into three classes: 'more important mail traffic', 'less important traffic' and 'unknown traffic' and assigns bandwidths differently to the traffics. By differentiating the bandwidths of classes, normal mail traffic may flow even under DDoS attack in the proposed technique. The proposed technique is implemented on an embedded system which hires a switching processor with the WFHBD(Weighted Fair Hashed Bandwidth Distribution) engine that has been known as an efficient algorithm to distribute a given bandwidth to multiple sources, and it is verified that it can be an efficient way to protect e-mail server from DDoS attack.

• The Journal of the Acoustical Society of Korea
• /
• v.9 no.4
• /
• pp.66-76
• /
• 1990

In this work, the effect of noise and distortion of a telephone channel on the speech recognition is studied, and methods to improve the recognition rate are proposed. Computer simulation is done using the 100-word test data whichwere made by pronouncing ten times 100-phonetically balanced Korean isolated words in a speaker dependent mode. First, a spectral subtraction method is suggested to improve the noisy speech recognition. Then, the effect of bandwidth limiting and channel distortion is studied. It has been found that bandwidth limiting and amplitude distortion lower the recognition rate significantly, but phase distortion affects little. To reduce the channel effect, we modify the reference pattern according to some training data. When both channel noise and distortion exist, the recognition rate without the proposed method is merely 7.7~26.4%, but the recognition rate with the proposed method is drastically increased to 76.2~92.3%.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.12
• /
• pp.149-158
• /
• 2005

This paper proposes a congestion avoidance algorithm which provides stable throughput and transmission rate regardless of buffer size by limiting the TCP congestion window in fixed bandwidth networks. Additive Increase, Multiplicative Decrease (AIMD) is the most commonly used congestion control algorithm. But, the AIMD-based TCP congestion control method causes unnecessary packet losses and retransmissions from the congestion window increment for available bandwidth verification when used in fixed bandwidth networks. In addition, the saw tooth variation of TCP throughput is inappropriate to be adopted for the applications that require low bandwidth variation. We present an algorithm in which congestion window can be limited under appropriate circumstances to avoid congestion losses while still addressing fairness issues. The maximum congestion window is determined from delay information to avoid queueing at the bottleneck node, hence stabilizes the throughput and the transmission rate of the connection without buffer and window control process. Simulations have performed to verify compatibility, steady state throughput, steady state packet loss count, and the variance of congestion window. The proposed algorithm can be easily adopted to the sender and is easy to deploy avoiding changes in network routers and user programs. The proposed algorithm can be applied to enhance the performance of the high-speed access network which is one of the fixed bandwidth networks.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.3
• /
• pp.612-622
• /
• 2017

Long-lived flowed termed as elephant flows in data center networks have a tendency to consume a lot of bandwidth, leaving delay-sensitive short-lived flows referred to as mice flows choked behind them. This results in non-trivial delays for mice flows, eventually degrading application performance running on the network. Therefore, a datacenter network should be able to classify, detect, and visualize elephant flows as well as provide QoS guarantees in real-time. In this paper we aim to focus on: 1) a proposed framework for real-time detection and visualization of elephant flows in SDN using sFlow. This allows to examine elephant flows traversing a switch by double-clicking the switch node in the topology visualization UI; 2) an approach to guarantee QoS that is defined and administered by a SDN controller and specifications offered by OpenFlow. In the scope of this paper, we will focus on the use of rate-limiting (traffic-shaping) classification technique within an SDN network.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.31 no.3
• /
• pp.145-154
• /
• 2006

WiBro (Wireless Broadband Internet) system is going to be 9ot down to commercialization. The high portable internet system is able to be connected to the high-speed internet using 2.3 GHz frequency bandwidth, anytime and anywhere. An effective scheduling for UGS, rtPS, nrtPS and BE requiring different QoS, which are service types of the WiBro, is necessary to increase the efficiency of radio channels that are the limiting resource. This paper researches an uplink scheduling that plays a role in assignment for the radio channels from subscribers to base stations. The suggested scheduling provides priorities with each service type considering QoS of them but reserves some bandwidth for lower priory services. After deciding effective amount of bandwidth for reservation, we suggest analytical result on mean delayed time of packet transmission for each terminal, transmission rate for the data, and capacity for uplink. This research can be used as basic data for the standard in the high portable internet system and as data to predict the capacity of base stations.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.10a
• /
• pp.347-353
• /
• 2005

WiBro (Wireless Broadband Internet) system is going to be commercialized before long. The high portable internet system is abie to be connected to the high-speed internet using 2.3 CHz frequency bandwidth, anytime and anywhere. An effective scheduling for UCS, rtPS. nrtPS and BE requiring different QoS, which are service types of the WiBro, is necessary to increase the efficiency of radio channels that arc the limiting resource. This paper researches an uplink scheduling that plays a role in assignment for the radio channels from subscribers to base stations. The suggested scheduling provides priorities With each service type considering QoS of them but reserves some bandwidth for lower priory services. After deciding effective amount of bandwidth for reservation, we suggest analytical result on mean delayed time of packet transmission for each terminal, transmission rate for the data, and capacity for uplink. This research can be used as basic data for the standard in the high portable internet system and as data to predict the capacity of base stations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.4
• /
• pp.1519-1534
• /
• 2016

In this paper, we study how to optimize the data shuffle phase by leveraging the flow relationship in datacenter networks (DCNs). In most of the clustering computer frameworks, the completion of a transfer (a group of flows that can enable a computation stage to start or complete) is determined by the flow completing last, so that limiting the rate of other flows (not the last one) appropriately can save bandwidth without impacting the performance of any transfer. Furthermore, for the flows enter network late, more bandwidth can be assigned to them to accelerate the completion of the entire transfer. Based on these characteristics, we propose the flow chasing algorithm (FCA) to optimize the completion of the entire transfer. We implement FCA on a real testbed. By evaluation, we find that FCA can not only reduce the completion time of data transfer by 6.24% on average, but also accelerate the completion of data shuffle phase and entire job.

• ETRI Journal
• /
• v.30 no.2
• /
• pp.249-254
• /
• 2008

In this paper, we demonstrate an electrically band-limited carrier-suppressed return-to-zero (EB-CSRZ) signal generator operating up to a 10 Gbps data rate comprising a single-stage Mach-Zehnder modulator and a wideband signal mixer. The wideband signal mixer comprises inverter stages, a mixing stage, and a gain amplifier. It is implemented by using a 0.13 ${\mu}m$ CMOS technology. Its transmission response shows a frequency range from DC to 6.4 GHz, and the isolation response between data and clock signals is about 21 dB at 6.4 GHz. Experimental results show optical spectral narrowing due to incorporating an electrical band-limiting filter and some waveform distortion due to bandwidth limitation by the filter. At 10 Gbps transmission, the chromatic dispersion tolerance of the EB-CSRZ signal is better than that of NRZ-modulated signal in single-mode fiber.