• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.202-204
• /
• 2003

경성 실시간 시스템(Hard Real-Time System)어서는 주기 태스크들의 엄격한 마감시간(Deadline) 보장이 시스템의 성능을 좌우한다. 본 논문에서는 CPU의 이용률(Utilization)이 높아 비율단조 정책으로는 마감시간을 보장 할 수 없는 주기 태스크들을 위해 확장된 스케줄 가능성 검사를 통해 수행할 태스크들의 공통 주기(L.C.M : Least Common Multiple)내에서 EDF(Earliest-Deadline First) 정책을 기반으로 마감시간 보장 수행패턴(Feasible Pattern)을 찾고, 이를 참조하여 우선순위를 고려하지 않고 태스크들을 강제 수행할 수 있게 하는 비율단조 기반의 스케쥴링 기법을 제안한다. EDF를 기반으로 생성된 패턴은 EDF 정책의 특성에 따라 CPU의 이용률을 100% 까지 가능하게 하며 패턴을 참조하여 강제 수행함으로써 EDF 정책이 갖는 실행시간 스케쥴링 오버헤드를 없앨 수 있다.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.639-648
• /
• 1997

As the areas of computer application are expanded, the real-time applicition enviroments that must process as many transactions as possible within their deadlines have been increased recently. Conventional disk based databaes system is not appropriate in real-time transaction processing due to delying time for disk I/O processing. When the system is overloaede, the performance of transaction scheduling technique using earliest deadline first deteriorates rapidly because it can assign the highest priority ot a transaction that has already missed or is about to miss tis deadline. Therfore, the performance of suggested transaction secheduling technique is made to improved by propos-ing the doule locking mechanism based on priority. Finally, in order to evaluate the performance of the proposed priority-based double locking techniques under single proessor and main memory database system environments, the simulation model was developed using the SLAM II language.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2011.06a
• /
• pp.326-328
• /
• 2011

광역보정시스템의 국제 표준 메시지는 정지궤도위성을 통해 250bps의 속도로 방송되며, 하나의 메시지가 250bit를 차지하기 때문에 1초에 하나의 메시지만 방송된다. 이 중에서 메시지 헤더 등을 제외한 실제 데이터는 212bit를 이루고 있고 제한된 데이터 전송률로 인하여 광역보정표준메시지의 효율적인 방송이 필요하다. 광역보정표준메시지는 30개에 가까운 메시지 타입이 있다. 각 메시지 타입마다 방송되어야 하는 주기가 다르고, 사용자 무결성을 보장하기 위하여 긴급 메시지 등이 발생하였을 때에는 방송되어야 하는 메시지의 우선 순위가 달라지게 된다. 본 논문에서는 광역보정표준메시지의 메시지별 전송간격 요구조건을 만족시키면서 사용자의 정확성 및 무결성을 최대한 향상시키기 위한 메시지 스케쥴링 기법을 설명하고 이를 이용한 시뮬레이션 결과를 보여준다.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.11
• /
• pp.2973-2979
• /
• 1998

As this paper is a scheduling algorithm for the synthesis of a pipelined datapath under resource constraints in high level synthesis, the proposed heuristic algorithm uses a priority function based on the collision count of resourecs. In order to schedule the pipelined datapath under resource constraints, we define the collision count and the priority function based on the collision count, a number of resource, and the mobility of operations to resolve a resource collision. The proposed algorithm supports chaining, multicycling, and structural pipelining to design the realistic hardware. The evaluation of the Performance is compared with other systems using the results of the synthesis for a 16point FIR filter and a 5th order elliptic wave filter, where in most cases, the optimal solution is obtained.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.8
• /
• pp.343-348
• /
• 2013

We proposes a power-aware fixed-priority real-time scheduling algorithm for multimedia service, called static voltage scaling algorithm with multi-granularity resource reservation (STATIC-MULTIRSV). The multi-granularity resource reservation was introduced to deliver higher system utilization and better temporal isolation than the traditional approaches in [2]. Based on this, our STATIC-MULTIRSV is designed to reduce the power consumptions while guaranteeing that all I-frames of each video stream meet their deadlines. We implemented the proposed algorithm on top of ChronOS Real-time Linux [6]. We experimentally compared STATIC-MULTIRSV with other existing methods which showed that STATIC-MULTIRSV reduce power consumption by maximum 15% compared to its experimental counterparts.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.95-97
• /
• 2000

자바는 플랫폼 독립성, 보안, 멀티 쓰레드 지원, 가베지 콜렉터 등 많은 장점을 갖고 있는 언어이다. 하지만 현재의 자바 가상 기계(JVM)는 시간 제약 조건을 갖는 주기적인 태스크 수행, 실시간 스케쥴링 등 실시간 응용을 위한 지원이 미흡한 실정이다. 본 논문에서는 실시간 운영체제인 VxWorks와 내장형 JVM인 퍼스널 자바 상에서 실시간 응용 프로그램의 지원을 위한 자바 쓰레드를 설계, 구현한다. 이를 위해 기존의 자바 쓰레드에 시작시간, 주기, 종료시한 등의 시간 속성을 삽입하고, 실시간 자바 쓰레드 API 클래스를 구현한다. 실시간 스케쥴러를 세가지 방식으로 구현한다. 첫째는, JVM을 수정하지 않고 시간 속성에 따라 쓰레드에 우선 순위를 할당하여 스케쥴링하는 방식이고, 둘째는 JVM을 수정하여 시간 속성에 따라 VxWorks 커널 스케쥴러를 통해 스케쥴링하는 방식이며, 셋째는 독립적인 스케쥴링 태스크를 구현하는 방식이다. 쓰레드 생성, 문맥 교환 등의 오버헤드와 스케쥴링 시 종료시한 초과 비율 등의 기준을 통해 각각의 성능을 비교한 결과, VxWorks 커널 스케쥴러를 이용한 방식이 가장 적합하다는 결론을 얻을 수 있었다.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1418-1432
• /
• 1996

In addition t improved availability, replication of data can enhance performance of distributed real-time transaction processing system by allowing transactions initiated at multiple node to be processed concurrently. To satisfy both the consistency and real-time constraints, it is necessary to integrate concurrency control and atomic commitment protocols with time-driven scheduling methods. blocking caused by existing concurrency control protocols is incompatible with time-driven scheduling because they cannot schedule transactions to meet given deadlines. To maintain consistency of replicated data and to provide a high degree of schedulability and predictability , the proposed time-driven scheduling methods integrate optimistic concurrency control protocols that minimize the duration of blocking and produce the serialization by reflecting the priority transactions. The atomicity of transactions is maintained to ensure successful commitment in distributed environment. Specific time-driven scheduling techniqueare discussed, together with an analysis of the performance of this scheduling.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.1015-1016
• /
• 2015

VANET is a technology for building a robust ad-hoc network between mobile vehicles as well as, between vehicles and RSU. Vehicles are moving and they only stay in the RSU area for a short time. When the number of requests is increased, an important challenge is to implement a suitable scheduling algorithm which serves as more requests as possible. $D^*S$ algorithm uses a priority weight, DS_Value, for selection of a request to get service. Priority weight is influenced only by deadline and data size parameters. We propose a packet scheduling using multilevel queue and show that using this idea leads to higher service ratio compare to previous algorithms.

• The KIPS Transactions:PartB
• /
• v.15B no.5
• /
• pp.413-420
• /
• 2008

Network bandwidth is one of the major factors that impact the cost of a video service. In this paper we propose approaches to reducing the bandwidth requirement for transporting MPEG-4 video traffic over wireless LANs while guaranteeing a required level of quality of service(QoS). To support high quality video playbacks, video frames must be transported to the client prior to their playback times. A real-time transmission scheduling is used for this purpose, which transmits each frame assigned with a priority according to its importance. It addresses the challenge for a scheduling algorithm that efficiently handles the changing workloads of MPEG-4 video traffic. The goal of our research is to maximize the number of frames that are transported within their deadlines while minimizing the tardiness of frames that missed their deadlines. The performance of the proposed method is compared with that of similar service mechanisms through extensive simulation experiments.

• The Journal of the Korea Contents Association
• /
• v.5 no.1
• /
• pp.89-99
• /
• 2005

HPI system provides 1-3 Mbps data transmission speed to terminals moving up to 60 km/sec. Since HPI supports rtPS, nrtPS, and BE services requiring different QoS, it needs an efficient scheduling method based on those different QoSs. This paper suggests an uplink scheduling method which gives priority to services in the order of rtPS, nrtPS and BE services but which reserves some bandwidth for the low priority services before it allocates the bandwidth to higher priority services. Simulation results show that it can improve the uplink performance by reserving mean transmission rate to each nrtPS terminal and by reserving bandwidth, which amounts to about 1.5 times the mean transmission rate of the whole BE terminals, to the whole BE terminals.