• The Journal of the Korea Contents Association
• /
• v.7 no.12
• /
• pp.238-244
• /
• 2007

Guaranteed Frame Rate(GFR), recently approved by the ATM Forum, expects to become an important service category to efficiently support TCP/IP traffic in ATM networks. The GFR service not only guarantees a minimum service rate at the frame level, but also supports a fair share of available bandwidth. We proposed new scheduling scheme for the GFR service. Proposed scheme provides priority to VCs and high priority to a VC which have more untagged cells in buffer. High priority VCs have much more serviced than low priority. Proposed scheme can provide MCR(minimum cell rate) guarantee and fair sharing to GFR VCs. Computer simulation results show that proposed scheduling scheme provide a much better performance in TCP goodput and fairness than previous scheme.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.5C
• /
• pp.361-370
• /
• 2008

NoC is adopted for data communication between processors and IPs in MPSoC system. NoC has an advantage of scalability in that system can be easily expanded just by adding switches. However, as the number of switches increases, chip area increases as well as data transfer latency. This paper proposes an architecture that can reduce the number of switches in the system by sharing network interfaces. To reduce NI area, the modules sharing network interface use a common buffer in network interface. Experimental results show that the chip area has been reduced by 46.5% and data transfer latency by 17.1%, respectively, compared to conventional architecture.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6A
• /
• pp.918-926
• /
• 2000

A huge storage and broad bandwidth are required to provide subscribers with VoD services. Hence, there is a huge amount of cost in establishing networks for VoD services. To determine how to reduce the cost, a number of studies involving such as distributed server systems, multicasting, program caching, stream sharing, are currently in progress. In this paper, a request criterion for multicast service and the ratio of required bandwidth for unicast to multicast are generated. The effect of multicast service on network bandwidth, server bandwidth, and buffer size was analyzed and validated through computer simulation. The results of this study could be applied to efficient designing networks for VoD services.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.11-19
• /
• 2019

Recently, hybrid CDN/P2P video streaming architecture is specially designed and deployed to achieve the scalability of P2P networks and the desired low delay and high throughput of CDNs. In this paper, we propose a cooperative video streaming and active node buffer management technique in hybrid CDN/P2P architecture. The key idea of this streaming strategy is to minimize network latency such as jitter and packet loss and to maximize the QoS(quality of service) by effectively and efficiently utilizing the information sharing of file location in CDN's proxy server which is an end node located close to a user and P2P network. Through simulation, we show that the proposed cooperative video streaming and active node buffer management technique based on CDN and P2P network improves the performance of realtime video streaming compared to previous methods.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.6
• /
• pp.1390-1403
• /
• 1998

Database sharing system (DSS) refers to a system for high performance transaction processing. In DSS, the processing nodes are locally coupled via a high speed network and share a common database at the disk level. Each node has a local memory, a separate copy of operating system, and a DB'\fS. To reduce the number of disk accesses, the node caches database pages in its local memory buffer. However, since multiple nodes may be simultaneously cached a page, cache consistency must be cnsured so that every node can always access the'latest version of pages. In this paper, we propose efficient cache consistency schemes in DSS, where the database is logically partitioned using primary copy authority to reduce locking overhead, The proposed schemes can improve performance by reducing the disk access overhead and the message overhead due to maintaining cache consistency, Furthermore, they can show good performance when database workloads are varied dynamically.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.4
• /
• pp.947-960
• /
• 1996

The primary goal for developing high performance ATM switching systems is to minimized the probability of cell loss, cell delay and deterioration of throughput. ATM switching element that is the most suitable for this purpose is the shared buffer memory switch executed by common random access memory and control logic. Since it is difficult to manufacture VLIS(Very Large Scale Integrated circuit) as the number of input ports increased, the used of switching module method the realizes 32$\times$32, 150 Mb/s switch utilizing 8$\times$8, 600Mb/s os 16$\times$16, 150Mb/s unit switch is latest ATM switching technology for small and large scale. In this paper, buffer capacity satisfying total-memory-reduction effect by buffer sharing in a shared buffer memory switch are analytically evalu ated and simulated by computer with cell loss level at traffic conditions, and also features of switching network utilizing the switching module methods in small and large-capacity ATM switching system is analized. Based on this results, the structure in outline of 32$\times$32(4.9Gb/s throughput), 150Mb/s switches under research in many countries is proposed, and eventually, switching-network structure for ATM switching system of small and large and capacity satisfying with above primary goals is suggested.

• Journal of KIISE:Information Networking
• /
• v.27 no.4
• /
• pp.489-497
• /
• 2000

주문형 비디오(Video On Demand)서버의 구현은 현재까지도 많은 부분에 한계를 가지고 있으며 이를 해결하기 위한 연구들이 활발히 진행되고 있다. 주문형 비디오 서비스의 한계는 대부분이 자원(디스크, 버퍼)의 제한 때문에 발생하고 있으며 디스크어레이(Disk Array)나, 메모리 뱅크(Memory Bank)와 같은 특수한 하드웨어를 사용하여 해결하고 있다. 또한 이와 아울러 그룹핑이나 버퍼 공유기법과 같은 소프트웨어적인 방법도 제안되었다. 본논문에서는 주분형 비디오 서버의 한계 중 디스크대역폭과 버퍼공간의 한계점에 의한 문제를 해결하기위하여 개선된 그룹핑 방법과 버퍼 공유 및 관리 방법을 제안한다. 제안하는 그룹핑 방법은 비디오의 인기도에 기반을 둔 방법을 사용하며 버퍼 공유방법은 버퍼의 크기 및 디스크의 대역폭 가용량에 따라 적응적으로 병합 분할하는 방법을 사용한다, 제안하는 병합 분할 방법은 피기백킹(piggy-backing)개념을 도입하였으며 시뮬레이션을 통해 제안하 방법의 우수성을 보였다.

• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1843-1854
• /
• 2010

The utilization of underground space has recently increased with the complication of road, the rise of the land price, and the development of green technology. Underground space ranges from classical excavations to subway, underground cities, and shopping malls where there are crowds of people. At this time, government has spent a lot of money in installing various types of safety facilities for preparations of increasing potential disasters. Therefore, an effective facility management system is required. In this paper, we propose an information retrieval process to effectively extract the facilities' information based on the ontology and spatial analysis in underground space. The ontology-based searching supports hierarchical and associated results as well as knowledge sharing with hierarchy concepts. The spatial analysis based searching has "Buffer" and "Near" functions to operate on a map without understanding any property of the facility information.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.05a
• /
• pp.333-337
• /
• 1998

동일 데이터를 액세스하는 다수 요구간의 시간적 지역성을 고려하여, 인접한 요구간의 시간 간격(interval)을 버퍼에 캐슁하여 공유하면 서버의 응답시간이 향상되고, 디스크 액세스 감소로 인한 대역폭 활용이 높아지며, 따라서 보다 많은 사용자 서비스가 가능해 진다. 본 논문에서는 VOD Server로 들어오는 요구 도착시간에 따라 버퍼 공유 크기를 결정하는 그룹핑(grouping)을 수행하게 하여 인접한 요구들의 공유 데이터 블록이 전체 버퍼를 점유하는 현상을 막고 디스크 액세스율을 감소시켜 대역폭의 활용도를 높일 수 있는 알고리즘을 구축한 후 시뮬레이션을 통하여 그 효율성을 분석한다.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.1
• /
• pp.19-26
• /
• 2002

This paper propose the queue structure of cell buffering in the output buffer of ATM switch for the traffic with the different QoS. The proposed queue structure can minimize the cell loss ratio of bursty traffic, maximize the queue utilization through the sharing of real-time queue and non-real-time queue. To evaluate the proposed queue structure, we compare the CLP and cell average delay of the proposed queue and fixed queue using the bursty traffic patterns.