• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.9B
• /
• pp.591-595
• /
• 2005

In this paper, we propose the fairness improvement leaky bucket (PILB) algorithm as a traffic policing mechanism. In the proposed algorithm, there is a cell buffer for every ATM connection in order to store date cells. Network decides whether an ATM connection obeys the contracted traffic parameter, and stores data cells in the cell buffer if the connection obeys but is considered as violated the contract due to temporary lack of network resource. By using the proposed algorithm, we can obtain the statistical multiplexing gain that is the superiority of packet switching network. Moreover, when a connection tries to transmit more data cells by violating the contracted traffic parameters, the connection is prevented from using excess network resource, which incurs all connections sharing network resource fairly. The performance of the proposed FILB algorithm is investigated by using the simulation. The result shows that the proposed algorithm provides superior performance and all connections within a group share network resource fairly. The proposed algorithm can be applied not only the ATM network but also IP network.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.4
• /
• pp.420-430
• /
• 2000

Several caching schemes for realtime multimedia systems have been proposed, but they focus only on increasing the hit ratio without providing any means to utilize the saved disk bandwidth due to cache hits. One of the most important metrics in multimedia systems is the number of clients that the systems can service simultaneously guaranteeing Quality of Service(QoS). Preemptive but Safe Interval Caching(PSIC) was proposed as a caching scheme which makes it possible to provide deterministic QoS.. However, it has no ability to adapt to the change of system environments since it has no mechanism to change the cache size. In this paper, we present a new caching scheme, Dynamic Interval Caching(DIC), which maximizes the performance, regardless of the change of system environments, providing hiccup-free service, by managing memory buffers dynamically. And it is demonstrated that DIC allocates buffer cache optimally, by comparing with PSIC through trace-driven simulations.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.4C
• /
• pp.342-352
• /
• 2002

In this paper, we compare the performances of RIO and RIO-DC buffer management schemes for DiffServ AF PHB standardized in IETF. For the comparison, we relatively differentiate maximum delay for each Assured Service subclass in Differentiated Services by allocating bandwidth to each subclass differently. In addition, we set the values of RIO and RIO-DC parameters considering the buffer size determined by the network topology and the ratio of bandwidth allocated to each subclass. In this simulation environment, the performances of RIO and RIO-DC schemes are analyzed focusing on the throughput of the In-profile traffic, the link utilization and the fairness. Simulation results show that the performance of RIO-DC scheme is comparable to that of RIO scheme with regard to the throughput of the In-profile traffic and the link utilization. However, under the simulation condition RIO-DC scheme improves the fairness between flows much better than RIO scheme.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.169-176
• /
• 2015

The atomic write technique is a good solution to solve the problem of the double write buffer. The atomic write technique needs modified I/O subsystems (i.e., file system and I/O schedulers) and a special SSD that guarantees the atomicity of the write request. In this paper, we propose the writing unit aligned block allocation technique (for EXT4 file system) and the merge prevention of requests technique for the CFQ scheduler. We also propose an atomic write-supporting SSD which stores the atomicity information in the spare area of the flash memory page. We evaluate the performance of the proposed atomic write scheme in MariaDB using the tpcc-mysql and SysBench benchmarks. The experimental results show that the proposed atomic write technique shows a performance improvement of 1.4~1.5 times compared to the double write buffer technique.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2000.04a
• /
• pp.23-24
• /
• 2000

최근 개인 이동 통신 단말기의 수요와 인터넷 사용자의 증가와 함께, 유선 통신 서비스에서부터 개인 휴대 통신 서비스에 이르기까지 다양한 통신 서비스가 제공되기 시작하면서 이러한 서비스가 결합된 mobile IP의 관심이 높아지고 있다. 기존의 IP에서는 노드가 계속해서 접속을 유지하기 위해서는 접속되는 위치가 반드시 고정적으로 지정되는 것이 필요하며 노드의 위치가 바뀌면 기존의 IP 주소는 사용할 수 없다. 그러나 mobile IP는 인터넷상의 임의의 다른 위치에 접속해 노드가 IP 주소를 바꾸지 않고 인터넷을 사용할 수 있도록 한다. 이동(mobile) 노드가 새로운 셀 지역으로 이동하면, 그 셀에 해당하는 외부(foreign) 에이전트로부터 임시 주소(care-of address)를 할당받아 홈 네트워크에 위치한 홈 에이전트에 등록하고, 홈 에이전트는 송신 노드가 이동노드로 전송한 패킷을 새롭게 등록된 임시 주소로 터널링을 통해 전달한다. 이러한 기본적인 mobile IP 방법은 모든 패킷이 홈 에이전트를 통해 이동 노드로 전송되므로 최적화된 라우팅 방법을 제공하지 못한다. 그러므로 이러한 mobile IP의 단점을 보완한 route optimization mobile IP가 제안되고 있다. Route optimization mobile IP는 이동 노드의 현재 위치와 관련된 정보를 갖는 바인딩을 저장하여 송신 노드가 패킷을 이동 노드의 홈 에이전트를 거치지 않고 이동 노드로 직접 전송하는 기능을 제공한다. 또한 이동 노드가 다른 셀 지역으로 핸드오프가 이루어질 경우, 핸드오프 발생전의 바인딩 정보를 이용하여 송신 노드가 전송한 패킷은 이전 셀 지역에 있는 에이전트가 새로운 셀 지역에 있는 이동 노드로 패킷을 재전송하여 전달하는 smooth 핸드오프 기능을 제공한다. 이전 셀 지역에 속한 외부 에이전트가 바인딩을 갱신하기 전에 송신 노드로부터 이동노드로 전달된 패킷이 있을 경우는 패킷을 저장하여 이후에 이동 노드의 위치 정보에 관한 바인딩 정보가 갱신되면 이러한 바인딩 정보에 따라 패킷을 재전송하는 버퍼기능도 제공한다. route optimization mobile IP는 기본적인 mobile IP에서의 복잡한 라우팅 문제를 해결하고, 핸드오프에서의 패킷 손실률을 최소화 한다.본 논문에서는 컴퓨터 시뮬레이션을 통해 smooth 핸드오프를 이용한 mobile IP의 성능을 분석한다. 일반적으로 데이터 트래픽 특성, 노드의 이동성, 바인딩 갱신시간, 버퍼관리 방법 등은 핸드오프 동안 mobile IP의 성능에 많은 영향을 미친다. 따라서 시뮬레이션 모델을 이용하여 다양한 트래픽 환경에서 위에 언급된 성능 파라미터들의 영향을 분석한다. 마지막으로 시뮬레이션 결과를 이용하여 mobile IP의 성능을 개선시키기 위한 방법을 제시한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.4B
• /
• pp.162-169
• /
• 2005

Network traffic measurements show that the data traffic on packet switched networks has the self-similar features which is different from the traditional traffic models such as Poisson distribution or Markovian process model. Most of the call admission control researches have been done on the performance analysis of a single network switch. It is necessary to consider the performance analysis of the proposed admission control scheme under interconnected switch environment because the data traffic transmits through switches in networks. From the simulation results, it is shown that the call admission control scheme may not operate properly on the interconnected switch even though the scheme works well on a single switch. In this parer, we analyze the cell loss probability, utilization and self-similarity of output ports of the interconnected networks switch by using shared buffer memory management schemes and propose the new call admission control scheme considering the interconnected network switches under self-similar traffic environments.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.747-754
• /
• 2004

Database administrators should be aware of performance characteristics of database systems in order to manage database system effectively. The usages of system resources in database systems could be quite different under database workloads. The objective of this paper is to identify and analyze performance characteristics of database systems in different workloads, which could help database tuners tune database systems Under the TPC-C and TPC-W workloads, which represent typical workloads of online transaction processing and electronic commerce respectively, we investigated usage types of resource that are determined by fourteen performance indicator, and are behaved in response to changes of four tuning parameters (data buffer, private memory, I/O process, shared memory). Eight out of the fourteen performance indicators cleary show the performance differences under the workloads. Changes of data buffer parameter give a influences to database system. The tuning parameter that affects the system performance significantly is the database buffer size in the both workloads.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.6
• /
• pp.1490-1500
• /
• 1996

One of the important issues for multimedia communications over ATM netowrks is efficient use of net-work resources since transmitting video at low cost requires high utilization of channel bandwidth. In this paper, we propose an effective bandwidth estimation scheme for MPEG sources in ATM networks. It has been known difficult to allocate effective transmission bandwidth to MPEG sources due to its bursty charactersitics. The MPEG traffic stream can bemodeled using five traffic parameters:service rate, burst load ratio, interburst load ratio, burst period, and interburst period. Using these parameters, a transmission bandwidth for each source can be estimated, and the estimated bandwidth is applied synchronously to reduce the queue size in a buffer. For a simple network modelof a high speed link that multiplexes a number of virtual-circuit connections, simulations on adaptive bandwidth allocation were performed, and the results show that the queueing delay is significantly reduced, when compared to a fixed bandwidth allocation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.5
• /
• pp.2305-2310
• /
• 2011

Recently, communication industry based on data and voice and broadcasting industry centering around images have been rapidly blended. Thereupon, this article aims to suggest a multi-approach method which minimizes the use of network bandwidth allowing multimedia streaming transmission to secure IP-based continuity and let users get multimedia services of one channel or several simultaneously. Also, this study intends to design a buffering strategy that can absorb network delay and an object model to assign and maintain stable channel bandwidth.

• The KIPS Transactions:PartA
• /
• v.12A no.3 s.93
• /
• pp.197-204
• /
• 2005

In this paper, we consider the transmission or variable bit rate (VBR) stored video for the distributed video streaming service over Internet. In streaming service, users often suffer from the discontinuity in playback due to the decrease in bandwidth during transmission according to bandwidth renegotiation protocol. We propose a novel transmission technique to overcome this problem for stored variable bit rate video. This scheme uses a priori information of stored VBR video to continue streaming without playback discontinuity. In addition, an approximation scheme for the buffer-bandwidth relation is proposed in order to facilitate the admission control under the proposed scheme.