• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.1
• /
• pp.73-82
• /
• 2004

As a new service category to better support TCP traffic in ATM networks, the Guaranteed Frame Rate (GFR) service category aims to support minimum cell rate guarantee, fairly distribute available bandwidth while keeping the simplicity of Unspecified Bit Rate (UBR). In this paper, we proposed a buffer management scheme which uses the per-VC accounting of single FWO queue and capable of supporting both GFR.1 and GFR.2 conformance definition. The proposed buffer management deal with GFR.1 and GFR.2 conformance definitions differentially by controlling the number of CLP=0 cell and CLP=1 cell which are occupying buffer space. The simulation results show that our proposed scheme satisfies the requirements of GFR services as well as improves total fairness index and each conformance definition fairness index.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.313-315
• /
• 2012

SSD(Solid State Drives)에서는 쓰기 버퍼를 활용해 쓰기 연산의 횟수를 줄임으로써 입출력 성능향상을 가져오고, 부가적으로 삭제 연산이 줄어들어 수명 향상의 효과를 얻고 있다. 하지만 지금까지의 쓰기 버퍼 관련 연구에서는 SSD의 컨트롤러 구조를 모두 고려하지 못하고 있다. 이 논문에서는 쓰기 버퍼의 데이터 히트(HIT)율을 높이기 위한 방법으로 지금까지 고려하지 못했던 SSD 컨트롤러 구조 내 명령 큐(Command Queue)의 정보를 통해 가까운 미래에 도착할 쓰기 명령을 예측하고, 이를 기존 버퍼 관리 기법에 적용하는 방안을 연구한다.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.4
• /
• pp.91-105
• /
• 2019

Discrete-time Queueing models are frequently utilized to analyze the performance of computing and communication systems. The length of busy period is one of important performance measures for such systems. In this paper, we consider the busy period of the Geo/Geo/1/K queue with a single vacation. We derive the moments of the length of the busy (idle) period, the number of customers who arrive and enter the system during the busy (idle) period and the number of customers who arrive but are lost due to no vacancies in the system for both early arrival system (EAS) and late arrival system (LAS). In order to do this, recursive equations for the joint probability generating function of the busy period of the Geo/Geo/1/K queue starting with n, 1 ≤ n ≤ K, customers, the number of customers who arrive and enter the system, and arrive but are lost during that busy period are constructed. Using the result of the busy period analysis, we also numerically study differences of various performance measures between EAS and LAS. This numerical study shows that the performance gap between EAS and LAS increases as the system capacity K decrease, and the arrival rate (probability) approaches the service rate (probability). This performance gap also decreases as the vacation rate (probability) decrease, but it does not shrink to zero.

• Journal of information and communication convergence engineering
• /
• v.9 no.5
• /
• pp.530-538
• /
• 2011

Performance of TCP can be severely degraded in Mobile IP-based wireless networks where packet losses not related to network congestion occur frequently during inter-subnetwork handoffs by user mobility. To solve such a problem in the networks using Mobile IP, the packet buffering method at a base station(BS) recovers those packets dropped during handoff by forwarding the buffered packets at the old BS to the mobile users. But, when the mobile user moves to a congested BS in a new foreign subnetwork, those buffered packets forwarded by the old BS are dropped and TCP transmission performance of a mobile user degrades severely. In this paper, we propose a Modified BLUE(MBLUE) buffer required at a BS to increase TCP throughput in Mobile IP-based networks. When a queue length exceed a threshold and congestion grows, MBLUE increases its packet drop probability. But, when a TCP connection is added at new BS by a handoff, the old BS marks the buffered packets. And new BS receives the marked packets without dropping. Simulation results show that MBLUE buffer reduces congestion during handoffs and increases TCP throughputs.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.7
• /
• pp.63-73
• /
• 2004

This paper proposes an efficient centralized sin91e buffer management algorithm to arbitrate access contention mon processors on the multi-processor system for high-speed Packet filtering and proves that the algorithm provides reasonable performance by implementing it and applying it to a real multi-processor system. The multi-processor system for parallel packet filtering is modeled based on a network processor to distribute the packet filtering rules throughout the processors to speed up the filtering. In this paper we changed the number of processors and the processing time of the filtering rules as variables and measured the packet transfer rates to investigate the performance of the proposed algorithm.

• Proceedings of the IEEK Conference
• /
• 2001.06b
• /
• pp.369-372
• /
• 2001

This paper presents the design of high-speed virtual output queue(VOQ) management scheme for high performance cell/packet switch, which has a serial cross bar structure. The proposed VOQ management scheme has been designed for wire-speed routing with a pipelined buffer management. It provides the tolerance of requests and grants data transmission latency between the VOQ manager and central arbiter using a new request control method that is based on a high-speed shifter. The designed VOQ manager has been implemented in a field programmable gate array chip with a 77MHz operating frequency, a 900-pin fine ball grid array package, and 16$\times$16 switch size.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.2
• /
• pp.354-363
• /
• 1994

This paper describes the method that voice traffic is served efficiently in BISDN. Voice is divided into talkspurt and silent period, and it is possible to transmit olny talksurt by the speech activity detection. This paper described the voice traffic control algorithm in the ATM network where cell discarding method is applied to the embedded ADPCM voice data. For traffic control, the cell discarding was used over low priority cells when it overflows the queue threshold. To estimate the efficiency of traffic control algorithm, the computer simuation was performed with cell loss probability, queue length and mean delay as performance parameters. The embedded ADPCM voice coding and cell disscarding resulted in improving the voice cell traffic efficiency and the dynamic control over network congestion.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.5
• /
• pp.1384-1396
• /
• 1998

This paper ivestigates the performance of a relative rate (RR) switch algorithm for the rate-based available bit rate (ABR) flow control in asynchronous transfer mode (ATM) networks. A RR switch may notify the network congestion status to the source by suing the congestion indication (CI) bit or no increase (NI)bit in the backward RM (BRM) cells. A RR switch can be differently implemented according to the congestion detectio and notification methods. In this paper, we propose three implementation schemes for the RR switch with different congestion detection and notification methods, and analyze the allowed cell rate (ACR) of a source and the queue length of a switch in steady state. In addition, we derive the upper and lower bounds for the maximum and minimum queue lengths for each scheme respectively, and evaluate the effects of the ABR parameter values on the queue length. Furthermore, we suggest the range of the rage increase factor (RIF) and rate decrease factor (RDF) parameter values which can prevent buffer overflow and underflow at a switch.

• Journal of Satellite, Information and Communications
• /
• v.12 no.4
• /
• pp.131-140
• /
• 2017

Multipath TCP (MPTCP) is a transport layer protocol that simultaneously transmits data using multiple interfaces. MPTCP is superior to existing TCP in network environment with homogeneous subflows, but it shows worse performance compared to existing TCP in network environment with bufferbloat. If a bufferbloat occurs in one of the MPTCP multipaths, the packet will not arrive at the MPTCP receive buffer due to a sudden increase in delay time, resulting in a HoL blocking phenomenon. It makes the receive window of the other path to be zero. In this paper, we apply Adaptive Random Early Detection (ARED), Controlled Delay (CoDel) and Proportional Integral Controller Enhanced (PIE) among the proposed Active Queue Management (AQM) to limit the delay of bufferbloat path. Experiments were conducted to improve the performance of MPTCP in heterogeneous networks. In order to carry out the experiment, we constructed a Linux-based testbed and compared the MPTCP performance with that of the existing droptail.

• Journal of KIISE:Information Networking
• /
• v.29 no.5
• /
• pp.553-561
• /
• 2002

We present a novel service discipline, called linear service discipline, to serve multiple QoS queues sharing a resource and analyze its properties. The linear server makes the output traffic and the queueing dynamics of individual queues as a linear function of its input traffic. In particular, if input traffic is Gaussian, the distributions of queue length and output traffic are also Gaussian with their mean and variance being a function of input mean and input power spectrum (equivalently, autocorrelation function of input). Important QoS measures including buffer overflow probability and queueing delay distribution are also expressed as a function of input mean and input power spectrum. This study explores a new direction for network-wide traffic management based on linear system theories by letting us view the queueing process at each node as a linear filter.