• 한국컴퓨터정보학회논문지
• /
• 제25권1호
• /
• pp.21-27
• /
• 2020

본 논문에서는 전투관리체계의 QoS를 향상시키기 위해 동적 가중 결손 라운드로빈과 우선 순위 기반의 혼합 스케줄링 알고리즘을 제안한다. 제안된 알고리즘인 DWDRR은 큐의 트래픽과 중요도에 따라 가중치를 동적으로 부여하여 패킷을 전송하는 방법이다. 제안된 알고리즘의 타당성을 분석하기 위해 모의실험을 통해 제안된 알고리즘이 특정구간에서 높은 효율성을 나타내는 것을 증명하였다. 따라서 기존의 알고리즘과 제안된 알고리즘을 혼합하여 사용하는 방법을 제안한다. 또한, 빈번한 기법 전환을 방지하기 위해 히스테리시스 기법을 적용하였다. 제안한 알고리즘은 동일한 트래픽에서 기존 알고리즘보다 낮은 패킷 손실률과 지연 시간을 나타낸다.

• 경영과학
• /
• 제12권2호
• /
• pp.43-62
• /
• 1995

For a complex scheduling system like time table construction, its optimal solution, if exists, is hard to obtain. In this paper, the scheduling environment is reasonably confined as where objects have their own events competing for better slots on boards, and objects have their own board slot preferences and belong to one or more classes of the society which globally constrains them. Here, two phase method is suggested, where the first phase is human-like preference driven and the second phase is for fine tuning by considering all the factors given. Designed and implemented in our system HI-SCHED are dynamic object switching, temporal-constraint-driven intelligent backtracking, case-based revisions, object-based approach, and so on. Some satisfaction degrees are also defined to measure the usefulness of our method. In addition, look-ahead dynamic object switching is considered, and additional global constraints are introduced and processed. A simple scheme is also used to verify the usefulness of the post processing scheme.

• 산업공학
• /
• 제14권4호
• /
• 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 Information Processing Systems
• /
• 제7권4호
• /
• pp.707-716
• /
• 2011

It is important that desktop grids should be able to aggressively deal with the dynamic properties that arise from the volatility and heterogeneity of resources. Therefore, it is required that task scheduling be able to positively consider the execution behavior that is characterized by an individual resource. In this paper, we implement a log analysis system with REST web services, which can analyze the execution behavior by utilizing the actual log data of desktop grid systems. To verify the log analysis system, we conducted simulations and showed that the resource group-based task scheduling, based on the analysis of the execution behavior, offers a faster turnaround time than the existing one even if few resources are used.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권1호
• /
• pp.83-104
• /
• 2011

Mobile grid is a combination of grid computing and mobile computing to build grid systems in a wireless mobile environment. The development of network technology is assisting in realizing mobile grid. Mobile grid based on established grid infrastructures needs effective resource management and reliable job scheduling because mobile grid utilizes not only static grid resources but also dynamic grid resources with mobility. However, mobile devices are considered as unavailable resources in traditional grids. Mobile resources should be integrated into existing grid sites. Therefore, this paper presents a mobile grid middleware interconnecting existing grid infrastructures with mobile resources and a mobile service agent installed on the mobile resources. This paper also proposes a mobile resource reliability-based job scheduling model in order to overcome the unreliability of wireless mobile devices and guarantee stable and reliable job processing. In the proposed job scheduling model, the mobile service agent calculates the mobile resource reliability of each resource by using diverse reliability metrics and predicts it. The mobile grid middleware allocated jobs to mobile resources by predicted mobile resource reliability. We implemented a simulation model that simplifies various functions of the proposed job scheduling model by using the DEVS (Discrete Event System Specification) which is the formalism for modeling and analyzing a general system. We also conducted diverse experiments for performance evaluation. Experimental results demonstrate that the proposed model can assist in improving the performance of mobile grid in comparison with existing job scheduling models.

• Industrial Engineering and Management Systems
• /
• 제7권1호
• /
• pp.99-107
• /
• 2008

This paper is concerned with scheduling in Flexible Manufacturing Systems (FMS) using a Fuzzy Logic (FL) approach. Four fuzzy input variables: machine allocated processing time, machine priority, machine available time and transportation priority are defined. The job priority is the output fuzzy variable, showing the priority status of a job to be selected for the next operation on a machine. The model will first select the machines and then assign operations based on a multi-criteria scheduling scheme. System/machine utilization, minimizing mean flow time and balancing machine usage will be covered. Experimental and comparative tests indicate the superiority of this fuzzy based scheduling model over the existing approaches.

• 설비공학논문집
• /
• 제12권11호
• /
• pp.982-993
• /
• 2000

This paper describes an optimal control scheduling of an encapsulated ice storage system with a chiller of nominal chiller 34RT(103,200kcal/hr) and an ice storage tank of 170RT-hrs(514,080 kcal). The optimization technique used in the study is dynamic programing. The objective function is summed cost during a day including charge and discharge periods. Control strategies being used commercially are chiller priority and storage priority control. In chiller priority control, the chiller is allowed to run at full capacity during the day, subject to limitations of the building load, and the ice is only melted when and if the load exceeds the chillers full capacity. In contrast to chiller priority control, the aim in storage priority control is to melt as much as ice as possible during the day time period. The system simulation calculates the operation costs for the three control strategies in the condition of the same cooling load and the same ice storage system. The simulation period is a day, assuming that initially the tank is stored fully and the cooling load is perfectly predicted for the scheduling. Also Final state of the tank is to be charged fully.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권6호
• /
• pp.808-816
• /
• 2016

As the number of CPU/GPU cores and IPs in SOC increases and applications require explosive memory bandwidth, simultaneously achieving good throughput and fairness in the memory system among interfering applications is very challenging. Recent works proposed priority-based thread scheduling and channel partitioning to improve throughput and fairness. However, combining these different approaches leads to performance and fairness degradation. In this paper, we analyze the problems incurred when combining priority-based scheduling and channel partitioning and propose dynamic priority thread scheduling and adaptive channel partitioning method. In addition, we propose dynamic address mapping to further optimize the proposed scheme. Combining proposed methods could enhance weighted speedup and fairness for memory intensive applications by 4.2% and 10.2% over TCM or by 19.7% and 19.9% over FR-FCFS on average whereas the proposed scheme requires space less than TCM by 8%.

• International Journal of Contents
• /
• 제6권3호
• /
• pp.19-24
• /
• 2010

Task scheduling is an integrated component of computing with the emergence of grid computing. In this paper, we address two different task scheduling models, which are static Round-Robin (RR) and dynamic Fastest Site First (FSF) task scheduling method, using extended timed marked graphs, which is a special case of Stochastic Petri Nets (SPN). Stochastic reward nets (SRN) is an extension of SPN and provides compact modeling facilities for system analysis. We build hierarchical SRN models to compare two task scheduling methods. The upper level model simulates task scheduling and the lower level model implements task serving process for different sites with multiple servers. We compare these two models and analyze their performances by giving reward measures in SRN.

• 한국유통학회:학술대회논문집
• /
• 한국유통학회 2003년도 춘계학술대회 발표논문집
• /
• pp.55-70
• /
• 2003

The most transport companies are placing increasing emphasis on powerful new techniques for planning their vehicle operations. They have tried to improve their vehicle control and customer service capability by adopting tile advanced information technology, such as GPS(Global Position System) and Using Digital Map. But researches on the VRSP(vehicle routing St schedule problem) in this situation were very few. The purpose of this research is to develop vehicle scheduling heuristics for making a real-time dynamic VRSP under the situation that GPS and using Digital Map are equipped to the transport company. Modified savings techniques are suggested for the heuristic method and an insertion technique is suggested for the dynamic VRSP. The urgent vehicle schedule is based on the regular vehicle schedule. This study suggest on VRSP system using GPS and Digital Map and the performance of the suggested heuristics is illustrated through an real case example.