• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.5
• /
• pp.243-254
• /
• 2005

Soft real-time applications such as multimedia feature highly variable processor requirements and probabilistic guarantees on deadline misses, meaning that each task in the application meets its deadline with a given probability. Thus, for such soft real-time applications, a system designer may want to improve the system utilization by allocating to each task a processor time less than its worst-case requirement, as long as the imposed probabilistic timing constraint is met. In this case, however, we have to address how to schedule jobs of a task that require more than (or, overrun) the allocated processor time to the task. In this paper, to address the overrun problem, we propose an overrun control method, which probabilistically controls the execution of overrunning jobs. The proposed overrun control method probabilistically allows overrunning jobs to complete for better system utilization, and also probabilistically prevents the overrunning jobs from completing so that the required probabilistic timing constraint for each task can be met. In the paper, we show that the proposed method outperforms previous methods proposed in the literature in terms of the overall deadline miss ratio, and that it is possible to synthesize the scheduling parameters of our method so that all tasks can meet the given probabilistic timing constraints.

• The KIPS Transactions:PartD
• /
• v.13D no.3 s.106
• /
• pp.399-404
• /
• 2006

A real-time system is used for various systems from small embedded systems to distributed enterprise systems. Because it has a characteristic that provides a service on time, developers should make efforts to keep this property about time when developing real-time applications. As the result of research about real-time system indicates, TMO model supports various functions for time processing according to the real-time concept. And it guarantees response time which developers defined. So developers need a point of reference to define deadline and check the correctness of time. This paper proposes an improved PS-Block as an infrastructure of analysis tools for TMO to present a point of reference. There is a problem that the existing PS-Block has overhead caused by a policy making duplicated blocks. As such, this paper implements a PS-Block Timing Model to reduce the overhead due to block duplication, and defines a base class for searching in PS-Block. The PS-Block Timing Model, using an improved PS-Block structure, offers a point of reference of deadline and an infrastructure of execution time analysis according to the PS-Block configuration policy. Therefore, TMO developers can easily verify deadline of real-time methods, and improve reliability, and reduce development terms.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.11
• /
• pp.381-394
• /
• 2022

Recently, due to the personalization and customization of data, Internet-based services have increased requirements for real-time processing, such as real-time AI inference and data analysis, which must be handled immediately according to the user's situation or requirement. Real-time tasks have a set deadline from the start of each task to the return of the results, and the guarantee of the deadline is directly linked to the quality of the services. However, traditional container systems are limited in operating real-time tasks because they do not provide the ability to allocate and manage deadlines for tasks executed in containers. In addition, tasks such as AI inference and data analysis basically utilize graphical processing units (GPU), which typically have performance impacts on each other because performance isolation is not provided between containers. And the resource usage of the node alone cannot determine the deadline guarantee rate of each container or whether to deploy a new real-time container. In this paper, we propose a monitoring technique for tracking and managing the execution status of deadlines and real-time GPU tasks in containers to support real-time processing of GPU tasks running on containers, and a node list management technique for container placement on appropriate nodes to ensure deadlines. Furthermore, we demonstrate from experiments that the proposed technique has a very small impact on the system.

• Journal of Computing Science and Engineering
• /
• v.2 no.1
• /
• pp.74-97
• /
• 2008

A scheduling policy or a schedulability test is defined to be sustainable if any task system determined to be schedulable remains so if it behaves "better" than mandated by its system specifications. We provide a formal definition of sustainability, and subject the concept to systematic analysis in the context of the uniprocessor scheduling of periodic and sporadic task systems. We argue that it is, in general, preferable engineering practice to use sustainable tests if possible, and classify common uniprocessor schedulability tests according to whether they are sustainable or not.

• Journal of Korean Institute of Industrial Engineers
• /
• v.15 no.2
• /
• pp.11-22
• /
• 1989

The problem of scheduling n-jobs on m-uniform parallel machines is considered, in which each job has a release time, a deadline, and a processing requirement. The job processing requirements are allocated to the machines so that the maximum of the load differences between time periods is minimized. Based on Federgruen's maximum flow network model to find a feasible schedule, a polynomially bounded algorithm is developed. An example to show the effectiveness of our algorithm is presented.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.9 no.2
• /
• pp.80-84
• /
• 2009

Dynamic voltage and frequency scaling (DVFS) is an effective method to achieve low power design. In our work, we present an analytical DVFS method which judiciously exploits correlation information in runtime distribution while satisfying deadline constraints. The proposed method overcomes the previous distribution-aware DVFS method [2] which has pessimistic assumption on which runtime distributions are independent. Experimental results show the correlation-aware DVFS offers 13.3% energy reduction compared to existing distribution-aware DVFS [2].

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.1531-1535
• /
• 2008

The Tester of Autonomous station control system is a system which can test the main function of Autonomous station control system through the data field. The purpose of this paper is to meet the system requirements and design a main function, menu and user interface using Use-case. The main function is a time-deadline test, a schedule broadcast test, a route control test and a version-up test, etc. The design of Autonomous station control system tester plays a primary role of the important document for the upcoming future system development of the tester.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.5
• /
• pp.650-657
• /
• 1999

In this paper, a real-time communication method using a PICNET-NP(Plant Instrumentation and Control Network for Nuclear Power plant) is proposed with an analysis of the control network requirements of DCS(Distributed Control System) in unclear power plants. The method satisfies deadline in case of worst data traffics by considering aperiodic and periodic real-time data and others.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.797-801
• /
• 2003

In this paper, a real-time communication method using a PICNET-NP (Plant Instrumentation and Control Network for Nuclear Power plant) is proposed with an analysis of the control network requirements of DCS (Distributed Control System) in nuclear power plants. The method satisfies deadline in case of worst data traffics by considering aperiodic and periodic real-time data and others.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.79-80
• /
• 2009

최근 UAV(Unmanned Aerial Vehicle)의 OFP(Operation Flight Program)에 대한 많은 연구가 진행되고 있다. UAV의 OFP는 경성 소프트웨어 일종으로 Time deadline과 수많은 요인으로 인한 Fault에 대하여 소프트웨어의 높은 신뢰성이 요구가 된다. 본 논문에서는 UAV의 OFP에 대하여 STR(Primary-Shadow TMO replication)기반의 fault tolerant Architecture에 대하여 제안을 한다.