• IE interfaces
• /
• v.14 no.4
• /
• pp.341-347
• /
• 2001

This paper describes a real-time manufacturing scheduling system on Internet using DBR(Drum-Buffer-Rope) scheduling method. We intend to change company-oriented manufacturing scheduling, which has been used at most manufacturing companies, to customer-oriented manufacturing scheduling. Customers can not only choose product kinds, quantities and order due dates, but also evaluate optimum order due date by themselves in real-time through internet and then the results will be converted into practical manufacturing scheduling. If the company cannot meet the customer order due date, it will offer reliable and accurate information to the customers by suggesting the earliest order due date. To evaluate the customer order due date in real time, companies should be able to estimate their accurate production capacity. This research uses Goldratt's DBR scheduling method to realize that function. The DBR scheduling does not recognize the production capacity of the whole company, but only of the constraint resources which have a great effect on the company throughput. Thus, it can improve the customer service level as well as the profit by performing more dynamic and reliable scheduling through Internet.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.6
• /
• pp.738-747
• /
• 1999

본 논문에서는 분산 실시간 시스템의 특징인 분산 처리 과정의 신뢰성을 지원하기 위한 동적 트랜잭션 처리 구조를 연구하였다. 실시간 분산 처리 환경에서 동적으로 발생하는 실시간 분산 트랜잭션 처리를 위하여 트랜잭션 내에 필수적인 3가지 언어적 특성들을 제시하였다. 첫째는 트랜잭션 내에 실시간 시스템의 가장 중요한 특징인 시간적인 제약 조건들을 정의 할 수 있는 방안을 제시하고, 둘째는 비동기적인 처리 성격을 지닌 실시간 특성을 고려한 비동기적 트랜잭션 처리 방법을 제시한다. 또한, 분산 처리 과정에서 발생되는 예외 사항들을 처리하기 위하여 긴급성을 고려한 다중레벨 우선순위 스케줄링 (Multi-Level Priotiry Scheduling)이라 부르는 트랜잭션 스케줄링 방안을 제시한다. 그리고, 제시한 실시간 분산 트랜잭션 처리 구조의 타당성 및 가능성을 입증하기 위한 실시간 트랜잭션 처리 과정을 시물레이션을 통하여 제시한 언어적 특성에 대한 고려 사항들을 보여준다.Abstract We propose a dynamic transaction processing model that supports a reliability for distributed real-time processing. For the dynamic processing in distributed real-time transaction systems, we suggest three features that are defined in programming language. First, we propose a specification model to explicitly define the time constraints, needs in real-time distributed processing. Second, we describe an asynchronous transaction processing mechanism based on the real-time characteristics. So, we suggest three communication primitives to support asynchronous transaction processing. Lastly, a scheduling policy based on urgent transaction is suggested to manage the exception occurred during the distributed processing. This scheduling policy is called multi-level priotiry scheduling (MPLS). Based on three features and scheduling policy, we describe a direction to manage a dynamic transaction processing in distributed real-time systems.

• International Journal of CAD/CAM
• /
• v.9 no.1
• /
• pp.111-120
• /
• 2010

In this paper, we propose a volume rendering method using grid computing for large-scale volume data. Grid computing is attractive because medical institutions and research facilities often have a large number of idle computers. A large-scale volume data is divided into sub-volumes and the sub-volumes are rendered using grid computing. When using grid computing, different computers rarely have the same processor speeds. Thus the return order of results rarely matches the sending order. However order is vital when combining results to create a final image. Job-Scheduling is important in grid computing for volume rendering, so we use an obstacle-flag which changes priorities dynamically to manage sub-volume results. Obstacle-Flags manage visibility of each sub-volume when line of sight from the view point is obscured by other subvolumes. The proposed Dynamic Job-Scheduling based on visibility substantially increases efficiency. Our Dynamic Job-Scheduling method was implemented on our university's campus grid and we conducted comparative experiments, which showed that the proposed method provides significant improvements in efficiency for large-scale volume rendering.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.9
• /
• pp.433-444
• /
• 2005

In video-on-demand(VOD) systems, a broadcast-based scheduling mechanism is known to be a very efficient technique for disseminating popular videos to very large client populations. The main motivations of broadcasting scheduling mechanisms are that they scale up extremely well and they have very modest bandwidth requirements. This paper proposes a new dynamic broadcasting scheduling mechanism, named FDBS (fast dynamic broadcasting scheme), and proves its correctness. This paper also evaluates the performance of FDBS on the basis of a simulation approach. The simulation results indicate that FDBS shows a superior performance over UD, CBHD, and NPB in terms of the average response time with very reasonable bandwidth requirements.

• Korean Management Science Review
• /
• v.20 no.2
• /
• pp.33-43
• /
• 2003

In this paper we applied dynamic programming to determining work schedule type. In dynamic programming formulation, each day during a planning horizon represents a stage for which a decision is made. The alternatives are given by work schedule types that combine regular time, overtime, additional shift, and so on. In this case, their associated return function is labor cost. The state is defined as the amount of work time allocated to stage 1, stage 2,…, and current stage. A case study for a real manufacturing company was performed to apply dynamic programming to scheduling daily work hours during a week. The case study showed that total cost of our solution derived from dynamic programming decreased by about 6％ as compared with the solution obtained from the previous method.

• Journal of Information Processing Systems
• /
• v.5 no.3
• /
• pp.135-144
• /
• 2009

Most of the tasks in wireless sensor networks (WSN) are requested to run in a real-time way. Neither EDF nor FIFO can ensure real-time scheduling in WSN. A real-time scheduling strategy (RTS) is proposed in this paper. All tasks are divided into two layers and endued diverse priorities. RTS utilizes a preemptive way to ensure hard real-time scheduling. The experimental results indicate that RTS has a good performance both in communication throughput and over-load.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.7
• /
• pp.22-28
• /
• 2009

As multiprocessors have been widely adopted in embedded systems, task computation energy consumption should be minimized with several low power techniques supported by the multiprocessors. This paper proposes an energy-aware task scheduling algorithm that adopts both dynamic voltage scaling and power shutdown in multiprocessor environments. Considering the timing and energy overhead of power shutdown, the proposed algorithm performs an iterative task assignment and task ordering for multiprocessor systems. In this case, the iterative priority-based task scheduling is adopted to obtain the best solution with the minimized total energy consumption. Total energy consumption is calculated by considering a linear programming model and threshold time of power shutdown. By analyzing experimental results for standard task graphs based on real applications, the resource and timing limitations were analyzed to maximize energy savings. Considering the experimental results, the proposed energy-aware task scheduling provided meaningful performance enhancements over the existing priority-based task scheduling approaches.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.6 no.4
• /
• pp.369-375
• /
• 2001

This paper proposes a dual real-time scheduling design under real-time constraints kernel environments. In this paper, we have designed both the real-time kernel and the general kernel that have their different properties to satisfy these properties, that is, interrupt latency, scheduling precision, and message passing. In real-time tasks, interrupt processing should be run. In general kernel, non real-time tasks or general tasks are run. Also, when tasks conflict, it executed the mixed priority scheduling that non real-time kernel executed static scheduling and real-time kernel executed dynamic priority transformation scheduling, that is, least-laxity-first/minimization preemption scheduling. We have compared the results of this study for performance of the proposal real-time kernel with both RT Linux 0.5a and QNX 4.23A, that is, of interrupt latency scheduling precision and message passing.

• Journal of the Korea Society for Simulation
• /
• v.18 no.2
• /
• pp.29-38
• /
• 2009

In the computing environment with heterogeneous resources, a job scheduling model is necessary for effective resource utilization and high-speed data processing. And, the job scheduling model has to cope with a dynamic change in the condition of resources. There have been lots of researches on resource estimation methods and heuristic algorithms about how to distribute and allocate jobs to heterogeneous resources. But, existing researches have a weakness for system compatibility and scalability because they do not support the standard language. Also, they are impossible to process jobs effectively and deal with a variety of computing situations in which the condition of resources is dynamically changed in real-time. In order to solve the problems of existing researches, this paper proposes a semantic computing-based dynamic job scheduling model that defines various knowledge-based rules for job scheduling methods adaptable to changes in resource condition and allocate a job to the best suited resource through inference. This paper also constructs a resource ontology to manage information about heterogeneous resources without difficulty as using the OWL, the standard ontology language established by W3C. Experimental results shows that the proposed scheduling model outperforms existing scheduling models, in terms of throughput, job loss, and turn around time.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.8
• /
• pp.753-757
• /
• 2008

In this paper, we propose a new scheduling strategy for dynamic programming in Grid environment. The key idea of this scheme is to reduce the execution time of a job by dividing the dynamic table based on the locality of table and allocating jobs to nodes which minimize network latency. This scheme obtains optimal concurrency by constructing the dynamic table using a distributed top down method. Through simulation, we show that the proposed Grid strategy improves the performance of Grid environment compared to previous branch-bound strategies.