• Journal of Korean Institute of Industrial Engineers
• /
• v.17 no.2
• /
• pp.63-74
• /
• 1991

An expert scheduling system on real time basis for computer-aided manufacturing systems has been developed. In developing expert scheduling system, the most time-consuming job is to obtain rules from expert schedulers. An efficient process of obtaining rules directly form the schedules produced by expert schedulers is proposed. By the process, a set of complete and minimal set of rules is obtained. During a real time scheduling, when given information on possible values of elements, the rules produce possible values of decision elements, where logical explanations of the result may be offered in terms of chaining rules. The learning and scheduling processes have been simulated with an automated manufacturing line engaged in the production of circuit boards.

• IE interfaces
• /
• v.11 no.3
• /
• pp.1-13
• /
• 1998

This paper addresses a scheduling scheme for Flexible Flow Shop(FFS) in the case that a factory is a sub-plant of an electronic device manufacturing plant. Under this environment, job orders for the sub-plants in the production route are generated together with job processing time bucket when the customer places orders for final product. The processing time bucket for each job is a duration from possible release date to permissible due date. A sub-plant modeled FFS should schedule these jobs orders within time bucket. Viewing a Printed Circuit Board(PCB) assembly line as a FFS, the developed scheme schedules an incoming order along with the orders already placed on the scheduled. The scheme consists of the four steps, 1)assigning operation release date and due date to each work cells in the FFS, 2)job grouping, 3)dispatching and 4)machine allocation. Since the FFS scheduling problem is NP-complete, the logics used are heuristic. Using a real case, we tested the scheme and compared it with the John's algorithm and other dispatching rules.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.6
• /
• pp.337-343
• /
• 2006

The Stack Resource Policy (SRP) is a real-time synchronization protocol with some distinct properties. One of such properties is early blocking; the execution of a job is delayed instead of being blocked when requesting shared resources. If SRP is used with dynamic priority scheduling such as Earliest Deadline First (EDF), the early blocking requires that a scheduler should select the highest-priority job among the jobs that will not be blocked, incurring runtime overhead. In this paper, we analyze the runtime overhead of EDF scheduling when SRP is used. We find out that the overhead of job search using the conventional implementations of ready queue and job search algorithms becomes serious as the number of jobs increases. To solve this problem, we propose an alternative data structure for the ready queue and an efficient job-search algorithm with O([log$_2n$]) time complexity.

• IE interfaces
• /
• v.11 no.1
• /
• pp.119-129
• /
• 1998

The relative importance of Logistics in steelworks industry is rather higher among other business activities. The objective of the paper is to propose the methodology for real-time vehicle scheduling for scrap disposal in the steelworks industry. Currently, the rule necessary to assign vehicles to a specific job is strictly fixed. The paper adopts the multi-pass rule selector (MPRS) that suggests a promising rule used for vehicle dispatching for a period of time. The MPRS is regularly invoked if necessary and then evaluates a set of rule candidates to select the best rule with respect to the system performance criteria. The experiment shows that the proposed approach outperforms the current single-pass strategy.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.310-313
• /
• 1996

Mathematical programming method for finding optimal solution of job shop scheduling is inadequate to real situation because fo too much computation time. In contrast, dispatching rule is helpful for reducing compuation time but is not guaranted to find optimal solution. The purpose of this paper is to develop a new dispatching rule and procedure to minimize mean flow time whose result is near the optimal solution for job shop scheduling. First step is to select machine which have shortest finishing operation time among the schedulable operations. Second step is to select operation with regard to estimated remaining operation time. The suggested rule is compared with nondelay and MWKR rule for three examples, and is confirmed to be most effective to minimize mean flow time.

• Journal of the Korea Society for Simulation
• /
• v.28 no.4
• /
• pp.45-56
• /
• 2019

Literatures have considered mathematical model that change the job order of shipper for improving the operation time of yard crane. However, on the real site, it is impossible to change the job order decided according to the shipper's arrival order. Therefore, operation managers have been utilized the relatively simple strategy that job control is better but the process time of yard crane is longer due to the growth of yard crane's interference time and empty drive time. This study proposed a new yard-crane scheduling approach that decided the job order before the shipper's truck arrived the yard terminal. We utilize the Container Pre-Information Notice estimating the arrival time of truck. We developed the container terminal simulation model for validation of the effect of proposed scheduling approach. The results show that the proposed scheduling reduced the interference delay time and empty moving time of yard crane and shipper's truck delay time.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.05a
• /
• pp.64-66
• /
• 2004

In general, the algorithms for production scheduling are developed with special objective under the special restrictions. Therefore, there is no common algorithm for APS system applied to various kind of production circumstances. The scheduling algorithm for APS system has to solve any problem that comes from any conditions of product kind, process, resource, machine, special rule for scheduling, and so forth. In addition, the algorithm finds solutions quickly because the need for real time based reschedule comes out often. In this paper, I am going to develop a scheduling algorithm using heuristic and genetic algorithm for APS system applied to various kind of production circumstances quickly and flexibly. The developed APS system with the algorithm will be introduced in this paper, also.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.1-8
• /
• 2010

In this paper, we propose a scheduling strategy for grid environment that reduces resource cost. This strategy considers resource cost and job failure rate to efficiently allocate local computing resources. The key idea of our strategy is that we use two-level scheduling using remote and local scheduler. The remote scheduler determines the expected total execution times of jobs using the current network and local system status maintained in its resource database and allocates jobs with minimum total execution time to local systems. The local scheduler recalculates the waiting time and execution time of allocated job and uses it to determine whether the job can be processed within the specified deadline. If it cannot finish in time, the job is migrated other local systems, through simulation, we show that it is more effective to reduce the resource cost than the previous Greedy strategy. We also show that the proposed strategy improves the performance compared to previous Greedy strategy.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.467-475
• /
• 1999

This paper presents an algorithm for scheduling jobs in soft real-time systems. To simplify the scheduling for soft real-time systems, we introduce two-level deadline scheme. Each job in the system has two deadlines, which we call first-level and second-level deadlines, respectively. The first-level deadline is the same as the deadline in traditional real-time systems. The second-level deadline is later than the first-level deadline, and defines the latest point in time when the result is still acceptable. Partial-credit is given for jobs meeting the second-level deadline but missing the first-level deadline, whereas jobs meeting the latter are given full credit. We heuristically compute priorities of jobs in a dynamic way by combining the first-level adn second-level deadlines with the partial-credit. Simulation results indicate that our two-level scheduling algorithm is a viable approach for dealing with both soft real-time systems and temporary overloaded hard real-time systems.

• 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.