• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제11권1호
• /
• pp.62-68
• /
• 2005

본 논문은 다중처리기 상에서 고정 우선순위 스케줄링 알고리즘의 성능을 향상시키는 기법을 제시한다. 이 기법은 여유시간(laxity)이 0인 작업(job)에 가장 높은 우선순위를 부여하고 다른 작업들보다 우선적으로 스케줄 한다. 이 기법을 적용한 고정 우선순위 알고리즘은 원래의 알고리즘을 strictly dominate한다. 즉, 원래의 고정 우선순위 알고리즘이 스케줄 할 수 있는 모든 태스크 집합(task set)을 스케줄 할 수 있으며, 원래의 고정 우선순위 알고리즘이 스케줄하지 못하는 일부 태스크 집합을 스케줄 할 수 있다. 또한 모의실험을 통하여 제안한 기법을 적용한 알고리즘이 스케줄 가능한 태스크 집합의 수와 스케줄 보장 이용률(schedulable utilization bound) 측면에서 원래의 알고리즘보다 우수함을 보인다

• Journal of Information Processing Systems
• /
• 제13권6호
• /
• pp.1459-1466
• /
• 2017

Recently, the development of the smart home field provides a range of services to install and keep the smart home appliance in a user's residential environment pleasantly. However, the conventional system method is not convenient enough to use properly because users have to select a device and manually operate the device on their own. In this paper, we propose a system to set the priority of the devices selected by the user and proceed with the task. When a user selects a device, the system recommends an optimal device associated with the device. The system compares and sets the priority of each device, carrying out the task one by one according to the set priority. Therefore, the proposed system is expected to provide users with increased convenience and more efficient task management.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4103-4121
• /
• 2018

Quality of Service (QoS) awareness is recognized as a key point for the success of Internet of Things (IOT).Realizing the full potential of the Internet of Things requires, a real-time task scheduling algorithm must be designed to meet the QoS need. In order to schedule tasks with diverse QoS requirements in cloud environment efficiently, we propose a task scheduling strategy based on dynamic priority and load balancing (DPLB) in this paper. The dynamic priority consisted of task value density and the urgency of the task execution, the priority is increased over time to insure that each task can be implemented in time. The scheduling decision variable is composed of time attractiveness considered earliest completion time (ECT) and load brightness considered load status information which by obtain from each virtual machine by topic-based publish/subscribe mechanism. Then sorting tasks by priority and first schedule the task with highest priority to the virtual machine in feasible VMs group which satisfy the QoS requirements of task with maximal. Finally, after this patch tasks are scheduled over, the task migration manager will start work to reduce the load balancing degree.The experimental results show that, compared with the Min-Min, Max-Min, WRR, GAs, and HBB-LB algorithm, the DPLB is more effective, it reduces the Makespan, balances the load of VMs, augments the success completed ratio of tasks before deadline and raises the profit of cloud service per second.

• 제어로봇시스템학회논문지
• /
• 제10권10호
• /
• pp.855-868
• /
• 2004

There are several types of singularities in controlling robotic manipulators: kinematic singularity, algorithmic singularity, semi-kinematic singularity, semi-algorithmic singularity, and representation singularity. The kinematic and algorithmic singularities have been investigated intensively because they are not predictable or difficult to avoid. The problem with these singularities is an unnecessary performance reduction in non-singular region and the difficulty in performance tuning. Tn this paper, we propose a method of avoiding kinematic and algorithmic singularities by applying a task reconstruction approach while maximizing the task performance by calculating singularity measures. The proposed method is implemented by removing the component approaching the singularity calculated by using singularity measure in real time. The outstanding feature of the proposed task reconstruction method (TR-method) is that it is based on a local task reconstruction as opposed to the local joint reconstruction of many other approaches. And, this method has dynamic task priority assignment feature which ensures the system stability under singular regions owing to the change of task priority. The TR-method enables us to increase the task controller gain to improve the task performance whereas this increase can destabilize the system for the conventional algorithms in real experiments. In addition, the physical meaning of tuning parameters is very straightforward. Hence, we can maximize task performance even near the singular region while simultaneously obtaining the singularity-free motion. The advantage of the proposed method is experimentally tested by using the 7-dof spatial manipulator, and the result shows that the new method improves the performance several times over the existing algorithms.

• 한국정보과학회논문지:시스템및이론
• /
• 제28권11호
• /
• pp.573-580
• /
• 2001

실시간 시스템에서 태스크가 공유 자원을 사용할 때 제한되지 않은 우선순위 역전이 발생할 수 있다. 이는 실시간 태스크의 스케줄링 가능성 보장을 불가능하게 한다. 따라서 우선순위 역전을 제한하는 자원 접근 프로토콜들이 연구되었으며 주기적 태스크 집합의 스케줄링 가능성 분석을 위한 충분조건이 제시되었다. 본 논문에서는 동적 우선순위 상한 프로토콜을 사용할 경우 개선된 스케줄링 가능성 충분조건을 제시한다. 제시된 방법에서는 높은 우선순위의 태스크들의 마감시간을 놓치지 않는 범위 내에서 낮은 우선순위를 가진 태스크가 계속 수행될 수 있다는 사실을 이용하였다. 이렇게 함으로써 높은 우선순위를 가진 태스크가 낮은 우선순위를 가진 태스크를 위해서 허용해 줄 수 있는 시간은 높은 우선순위를 가진 태스크의 최악 블록킹 시간에서 제외될 수 있다. 태스크의 최악 블록킹 시간이 감소하게 되므로 동적 우선순위 상한 프로토콜의 스케줄링 가능성 충분조건은 개선된다.

• ETRI Journal
• /
• 제30권1호
• /
• pp.1-12
• /
• 2008

In this paper, we propose an efficient single-resource task scheduling algorithm for the Communication, Ocean, and Meteorological Satellite. Among general satellite planning functions such as constraint check, priority check, and task scheduling, this paper focuses on the task scheduling algorithm, which resolves conflict among tasks which have an exclusion relation and the same priority. The goal of the proposed task scheduling algorithm is to maximize the number of tasks that can be scheduled. The rationale of the algorithm is that a discarded task can be scheduled instead of a previously selected one depending on the expected benefit acquired by doing so. The evaluation results show that the proposed algorithm enhances the number of tasks that can be scheduled considerably.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.72-75
• /
• 2004

In this paper, the task assignment strategy considering communication delay and the priority of distributed tasks is proposed for the real-time network system in order to maximize the utilization of the system. For the task assignment strategy, the relationship among priority of tasks in network nodes, the calculation time of each task, and the end-to-end response time including the network delay is formulated firstly. Then, the task assignment strategy using the genetic algorithm is proposed to optimize the utilization of the system considering the LCM(Least Common Multiple) period. The effectiveness of proposed strategy is proven by the simulation for estimating the performance such as the utilization and the response time of the system in case of changing the number of tasks and the number of network nodes.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.747-748
• /
• 2008

In this paper, we propose a new algorithm for task scheduling consisting of subtask partitioning and subtask priority scheduling steps in order to keep the peak power under the system specification. The subtask partitioning stepis performed to minimize the idle operation time for processors by dividing a task into multiple subtasks using the least square method developed with power consumption pattern of tasks. In the subtask priority scheduling step, a priority is assigned to a subtask based on the power requirement and the power variation of subtask so that the peak power violation can be minimized and the task can be completed within the execution time deadline.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2002년도 춘계학술발표논문집 (상)
• /
• 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.

• 한국콘텐츠학회논문지
• /
• 제21권6호
• /
• pp.12-18
• /
• 2021

비례 지분 스케줄러는 각 태스크에 상대적인 CPU 시간을 할당하고 태스크의 지분에 따라 실행할 태스크를 결정한다. 본 논문에서는 대표적인 비례 지분 스케줄러인 리눅스 Completely Fair Scheduler(CFS)에서 애플리케이션의 특징과 태스크 우선순위의 상관관계를 실험한다. 그리고 애플리케이션의 특징에 따라 태스크 우선순위 정밀도를 제어하는 기법을 제안한다. 제안 기법을 리눅스에서 구현하여 유의미한 실험 결과를 확인하였다.