• Proceedings of the Korea Contents Association Conference
• /
• 2012.05a
• /
• pp.263-264
• /
• 2012

임베디드 시스템은 특정한 목적을 수행하기 위한 시스템으로써, 자동차, 항공, 조선, 원자력발전소 등 다양한 분야에 사용되고 있는 추세이다. 이러한 임베디드 시스템은 빠른 응답성 및 시간 결정성을 위한 실시간성의 지원여부를 중요시 한다. 하지만 임베디드 시스템에서 사용되고 있는 범용 운영체제인 리눅스의 경우, 실시간성을 제공하지 않는 문제점을 가지고 있기 때문에 실시간성 제공을 위해 RTAI, RT-Linux를 통해 실시간성을 제공하고 있다. 그러나 RTAI는 Hard Real-Time을 제공하지 못하고, RT-Linux는 커널코드를 수정할 때 마다 커널 컴파일을 해야 하는 문제점이 있다. 또한, 사용자가 잘못 구현한 Real-Time 태스크의 오류가 커널에 영향을 미쳐 커널을 멈추게 하는 문제점이 있다. 따라서 리눅스 상에서 실시간성을 제공하면서 개발의 편의성 및 커널의 독립성을 제공할 수 있는 연구가 필요하다. 본 논문에서는 리눅스상의 사용자영역에서의 실시간성을 지원하기 위한 방법을 설계 및 구현을 하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10b
• /
• pp.573-575
• /
• 1998

실시간 내장형 시스템(real-time embedded system)의 반응 동작(reactive behavior)을 정확하게 분석하기 위해서 상태차트(statechart)에 바탕을 둔 객체 지향 모델링 방법론들이 많이 사용되고 있다. 하지만 이들 방법론들은 경성 실시간 시스템(hard real-time system)이라면 반드시 고려해야할 스케줄링 가능성분석(scheduability analysis)에 필요한 시간에 대한 정보와 시간 제약을 정확히 나타내지 못하는 문제점이 있다. 본 논문에서는 최근 OMG(Object Management Group)에서 객체 지향개발의 기준으로 채택된 UML(Unifies Modeling Language) ver1.1을 사용하여 실시간 내장형 시스템의 반응 동작과 시스템의 시제 동작(temporal behavior)을 모델링하여, 모델링된 시스템이 스케줄링 가능성 분석이 효과적으로 이루어지는 방안을 제안한다.

• Proceedings of the IEEK Conference
• /
• 2003.11c
• /
• pp.121-124
• /
• 2003

Passive optical networks (PONs) will be the pervasive choice in the design of next-generation access networks. One possible solution to implementing Passive optical access network is to rely on wavelength-division multiplexing (WDM). In this paper, we solve the problem of providing real-time service to both hard and soft real-time messages in conjunction with a conventional vest-effort service in WDM. we propose an adaptive scheduling algorithm to schedule and manage the message transmissions in the optical access network. Proposed algorithm is MLF-MQF. Also, we suggest dynamic bandwidth algorithm(DBA) in Loop-back WDM-PON (LPB-PON).our mechanism based on bandwidth reservation protocol.

• Journal of Computing Science and Engineering
• /
• v.6 no.1
• /
• pp.12-25
• /
• 2012

For real-time systems it is important to obtain the accurate worst-case execution time (WCET). Furthermore, how to improve the WCET of applications that run on multicore processors is both significant and challenging as the WCET can be largely affected by the possible inter-core interferences in shared resources such as the shared L2 cache. In order to solve this problem, we propose an innovative approach that adopts a code positioning method to reduce the inter-core L2 cache interferences between the different real-time threads that adaptively run in a multi-core processor by using different strategies. The worst-case-oriented strategy is designed to decrease the worst-case WCET among these threads to as low as possible. The other two strategies aim at reducing the WCET of each thread to almost equal percentage or amount. Our experiments indicate that the proposed multicore-aware code positioning approaches, not only improve the worst-case performance of the real-time threads but also make good tradeoffs between efficiency and fairness for threads that run on multicore platforms.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.443-445
• /
• 2002

In this paper, we present a novel efficient semaphore implementation scheme which diminishes completion time of high priority tasks and improves reliability of a system. The real-time system is constrained to complete their tasks in time. Especially, the task of a hard real-time system must meet its deadline under unfavorable conditions. In this paper, the number and sort of the locked semaphores, when an event occurred, decide whether the context switch should occur or not, so higher priority tasks diminish in their completion time. The experimental results show that the proposed method gives performance improvements in finish time of high priority tasks of about 11% over the Zuberi.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.57.2-57
• /
• 2001

Timed token protocols inadequately provide periodic communication service, although this is crucial for hard real time systems. We propose an approach to guaranteeing periodic communication service on a timed token protocol network. In this approach, we allocate bandwidth to each node so that the summation of bandwidth allocations is Target Token Rotation Time (TTRT). If a node cannot consume the allocated time, the residual time can be used by other nodes for non-periodic service using a timer which contains the unused time value and is appended to the token. This approach can always guarantee transmission of real-time messages before their deadlines when the network utilization is less than 50%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.687-690
• /
• 2002

In this paper, we present a novel semaphore implementation scheme which shortens finish time of high priority tasks and improves reliability of a system. The real-time systems have time constraints. Especially, the task with hard real-time constraints must meet its deadline. Consequently, managing shared resources is considered guaranteeing mutual exclusion as well as meeting task's deadline under unfavorable condition. According to the number and sort of the locked semaphores under the event occurred, this paper presents the reduction of the finish time of high priority task by decision whether the context switched or not. The experimental results show that the proposed method gives performance improvements in finish time of high priority tasks of about 11% over zuberi[4] method.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.9
• /
• pp.1167-1176
• /
• 2002

In a (hard) real-time system, every time-critical task must meet its timing constraint, which is typically specified in terms of its deadline. Many computer systems, such as those for open system environment or multimedia services, need an efficient schedulability test for on-line real-time admission control of new jobs. Although various polynomial time schedulability tests have been proposed, they often fail to decide the schedulability of the system precisely when the system is heavily loaded. Furthermore, the most of previous studies on on-line real-time schedulability tests are concentrated on periodic task applications. Thus, this paper presents an efficient on-line real-time schedulability check algorithm which can be used for imprecise real-time system predictability before dispatching of on-line imprecise real-time task system consisted of aperiodic and preemptive task sets when the system is overloaded.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.1
• /
• pp.22-32
• /
• 2003

Many of multimedia applications in distributed environments generate the packets which have the real-time characteristics for continuous audio/video data and transmit them according to the teal-time task scheduling theories. In this paper, we model the traffic for continuous media in the distributed multimedia applications based on the high-bandwidth networks and introduce the PDMA algorithm which is the hard real-time task scheduling theory for guaranteeing QoS requested by the clients. Furthermore, we propose the admission control to control the new request not to interfere the current services for maintaining the high quality of services of the applications. Since the proposed admission control is sufficient for the PDMA algorithm, the PDMA algorithm is always able to find the feasible schedule for the set of messages which satisfies it. Therefore, if the set of messages including the new request to generate the new traffic. Otherwise, it rejects the new request. In final, we present the simulation results for showing that the scheduling with the proposed admission control is of practical use.

• Journal of Broadcast Engineering
• /
• v.7 no.2
• /
• pp.79-87
• /
• 2002

The fast advances in digital video processing and multimedia processing technology over the last decade enabled various non-linear video browsing techniques. Based on the machine-understanding of the video content, non-linear video brows ing interfaces such as key-frame based content summarization have been introduced. The key-frame based user interfaces, such as storyboard or table of content, however, are still very hard for conventional TV users to use, and are very hard to implement without the service providers providing additional information for the construction of the key-frame based interfaces. In this paper, non-linear video browsing techniques, which not only overcome previously described drawbacks but also are easy-to-use, and real-time video indexing technology to support the proposed browsing techniques are proposed. The structure-based skipping and skimming help users easily find interesting scene and understand the content in a very short time, using real-time video indexing technology.