• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10a
• /
• pp.444-446
• /
• 1998

실시간 멀티미디어 응용의 등장으로 멀티캐스트와 QoS(Quality of Service)필수적인 망 서비스가 부각되고 있다 이에 ATM 기반의 인터넷에서 IP멀티캐스트의 효율적인 처리를 위하여 MARS(Multicast Address Resolution Server)가 제안되었고, 기존의 최선 서비스 기반의 인터넷에서 QoS(Quality of Service)를 지우너하기위하여 RSVP(Resource Reservation Protocol)가 제안되었다. 본 논문에서는 ATM망에서 QoS 가 지원되는 IP 멀티캐스트 서비스를 제공하기위하여 MARS 구조에서 RSVP를 지원하는 방안을 두 가지 제안하고, 시뮬레이션을 통하여 그 성능을 분석하고자 한다. 제안하는 두 가지 방법은 각각 RSVP 전 홉 논드 방식과 MARS서버 방식이라 명명하였다. RSVP전 홉 노드 방식은 송신원으로부터 ATM 망으로 진입하는 노드와 수신원을 향하여 ATM망을 진출하는 노드 간에 각각 일대일 양방향 VC를 설정하여 멀티캐스트 그룹에 속하는 수신원들이 보내는 자원 예약 메시지를 ATM 망에서 전송하는 방안이다. MARS 서버 방식은 MARS서버가 RSVP자원 예약 메시지를 처리하도록 그 기능을 확장함으로써 ATM 망의 제어 VC를 절약할 수 있는 방안이다. 시뮬레이션을 통하여, RSVP흐름의 휴지기간이 짧으면 RSVP전 홉 노드방식이 VC해제율이 낮아져 병목 현상으로 인한 큐잉 지연에 크게 영향을 받고 있는 MARS방식보다 유리함을 볼 수 있었고 RSVP 흐름의 휴지기간이 길 때는 병목 현상이 완화된 MARS방식이 VC설정 지연 단점이 부각된 RSVP 전 홉 노드 방식보다 유리함을 볼 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10b
• /
• pp.1299-1302
• /
• 2001

인터넷의 폭발적인 증가와 다양한 무선 서비스에 대한 수요 증가에 따라 용량이 크고, 데이터 전송 속도가 빠르며, 멀티미디어를 지원 할 수 있는 무선 인터넷 서비스가 필요하게 되었다. 또한 증가하는 사용자수를 수용하기 위해서 마이크로/피코 셀(micro/pico cell)을 도입하게 되었고, 이로 인하여 빈번한 핸드오프가 발생하게 되었다[1,2]. 이를 해결하기 위해서 MRSVP(Mobile Resource reservation protocol)와 같은 무선 자원예약 프로토콜이 제안되어지고 있다(4). 제안된 MRSVP 에서는 자원예약 지역의 불명확성과 지나친 신호부하를 초래하게 되었고, 이를 해결하기 위해서 본 논문에서는 계층적 MRSVP(H-MRSVP)를 이용한 새로운 호 제어기법과 무선 자원 예약 기법에 대해 연구하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.69-72
• /
• 2007

DOCSIS 3.0 Protocol is proposed to make the advance of HFC network. In the DOCSIS based network, the upstream frame is divided into contention section reservation section. CMs to have packets send request messages through the contention section. That two or more CMs sends Request message at the same contention slot makes collison. In this paper, are propose the contention section establlish at algorithm considering of channel-bonding mechanism that is the primary technique of DOCSIS 3.0. Results of simulation display better performance int the number of contention slots and the utilization of contention section.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.2 no.1
• /
• pp.53-59
• /
• 2007

Wimedia UWB(Ultra-Wideband) platform provides data rates up to 480Mbps in WPAN (Wireless Personal Area Network). Wimedia conformant devices access to the channels through superframe concept for communications. As the channel resource is limited, the optimal channel time required for each device needs to be estimated to share the resource efficiently among the devices. In this paper, we propose a scheme to estimate the required channel time in a super frame to satisfy the QoS of the application on a device. The channel time is estimated from the service rate which is computed from the TSPEC of the application. In the process of the estimation, we take the frame overhead for data transmission as well as the overhead due to the acknowledgement scheme, preamble, and MDSU size into consideration. We also analyze and compare the throughputs for different acknowledgement scheme, preamble, and MDSU size situations. The estimated channel time required for a given service rate is allocated in the unit of MAS(Medium Access Slot).

• Journal of Korea Multimedia Society
• /
• v.17 no.12
• /
• pp.1453-1460
• /
• 2014

WFQ (Weighted Fair Queuing) provides not only fairness among traffic flows in using bandwidth but also guarantees the Quality of Service (QoS) that individual flow requires, which is why it has been applied to the resource reservation protocol (RSVP)-capable router. The RSVP allocates an enough resource to satisfy both the rate and end-to-end delay requirements of the flow in the condition of no packet loss, and the WFQ scheduler guarantees those QoS requirements with the allocated resource. In practice, however, most QoS-guaranteed services allow a degree of packet loss, especially from 0.1% to 3% for Voice over IP. This paper discovers that the packet loss rate of each traffic flow is determined by only its time-stamp adjustment value, and then enhances the WFQ to provide a differentiated packet loss guarantee under general traffic conditions in terms of both traffic characteristics and QoS requirements. The performance evaluation showed that the proposed WFQ could increase the utilization of bandwidth by 8~11%.

• Journal of Communications and Networks
• /
• v.12 no.3
• /
• pp.266-274
• /
• 2010

The efficient network resource management is one of the important topics in a real-time system. In this paper, we present a practical network resource management framework, control-theoretic packet scheduler (CPS) system. Using our framework, an operating system can schedule both input and output streams accurately and efficiently. Our framework adopts very portable feedback control theory for efficiency and accuracy. The CPS system is able to operate independent of the internal network protocol state, and it is designed to schedule packet streams in fine-grained time intervals to meet the resource requirement. This approach simplifies the design of the CPS system, and leads us to obtain the intended output bandwidth. We implemented our prototype system in Linux, and measured the performance of the network resource management system under various network QoS constraints. The distinctive features of our principles are as follows: It is robust and accurate, and its operation is independent of internal network protocols.

• The KIPS Transactions:PartC
• /
• v.12C no.6 s.102
• /
• pp.781-792
• /
• 2005

This study proposes an Architecture for user level End-to-end Quality of Service(QoS) using overlay In Next Generation Network(NGN). Inexisting NGNs, the IMS of a control plane provides user QoS through direct traffic control and resource-reservation over the IP packet transport network of a user plane. Further, a set of torrent studies are ongoing not only to maximize the QoS for users, but also to minimize the quality deterioration for supporting the user End-to-end QoS. Along with that, an extended QoS in user level must be considered, for Instance, differentiating service quality to support users' expectation, providing optimized contents by users' equipments, and so forth. Accordingly, the Overlay Service Network Architecture proposed by this study provides protocol adaptation for maximum throughput on transport layer by using the most efficient transport layer protocol to various network circumstances. Also, the Overlay Service Network Architecture on application layer distributes processing delay from the data transformation process of the user equipment to the network, and it is capable of intermediate processing depending on user service level. application service feature, and equipment circumstance as well. Thus, this study mainly proposes the Overlay Service Network Architecture for user level end-to-end QoS in NGN with the quality control features both on the transport layer and the application layer, an internal component feature, and a service scenario providing the QoS linking with 3GPP.

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.4
• /
• pp.430-440
• /
• 2000

To support Integrated Services in the Internet, the Internet Engineering Task Force(IETF) has developed new mechanisms. These new mechanisms include Resource Reservation Protocol(RSVP) and Integrated Services model. RSVP and Integrated Services are independent of the underlying link layer technologies and it is necessary to define the mapping of RSVP and Integrated Services specifications onto specific link layer technologies. IETF proposed a Subnet Bandwidth Manager(SBM) providing a method for mapping RSVP onto IEEE802 style networks. However, the SBM has several constraints and problems. For solving these constraints and problems, we design and implement a new Ethernet Bandwidth Manager(EBM). This paper discusses (1) new bandwidth management mechanism independent of RSVP, (2) simulation of Ethernet bandwidth to analyze the characteristics of Ethernet and accomplish Ethernet bandwidth management, (3) design and implemetation of EBM that allows Controlled-Load Service, and (4) results of our experiments on EBM.

• The KIPS Transactions:PartC
• /
• v.12C no.7 s.103
• /
• pp.1015-1024
• /
• 2005

A delegation of privileges is one of important processes that empower authority to relevant node to process job that user wants in large-stale distributed environment such as Grid Computing. However, existing delegation methods do not give suitable privilege about Job, and do not atomize range of delegation and exists delegation of access privilege for only resources itself that is not delegation about executing process of job itself. Also, they do not apply about process that needs delegation before and after. execution of job such as reservation of system resources or host access before and after execution. Therefore, this paper proposes a method and specification for restricted delegation in distributed environment. Proposed method separates delegation for job side and privilege side, and express specification and procedure of delegation using XML schema and UML and present restricted delegation scenario in distributed computing environment.

• The KIPS Transactions:PartA
• /
• v.8A no.2
• /
• pp.133-146
• /
• 2001

In a dynamic load distribution policies, each node gathers the current system sates information before making a decision on load balancing. Load balancing policies based on this strategy can suffer from processor thrashing. In this paper, we propose a new algorithm which attempts to decrease the frequency of the processor thrashing, the algorithm is based on the integration of three components. The first, the algorithm of which determine the size of jobs be transferred. The second, negotiation protocol with obtains a mutual agreement between a sender and a receiver on the transferring job size. And the third, a symmetrically-initiated location policy. The algorithm proposed in this paper used Siman IV as simulation tool to prove the improvement of performance. I analyzed the result of simulation, and compared with related works. The mean response time shows that there are no difference with existing policy, but appear a outstanding improvement in high load. The thrashing coefficient that shows the average response time, CPU overhead and the thrashing ratio at both the receiving and sending node has been used in the analysis. A significant improvement in the average response time and the CPU overhead ratio was detected using our algorithm when an overhead occurred in the system over other algorithm. The thrashing coefficient differed in the sending node and the receiving node of the system. Using our algorithm, the thrashing coefficient at the sending node showed more improvement when there was an overhead in the system, proving to be more useful. Therefore, it can be concluded that the thrashing ratio can be reduce by properly setting the maximum and minimum value of the system’s threshold queue.