• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.289-293
• /
• 2000

We propose two new algorithms for parallelism-independent scheduling. The machine code generated from the compiler using these algorithms in its scheduling phase is parallelism-independent code, executable in minimum time regardless of the number of the processors in the parallel computer. Our new algorithms have the following phases: finding the minimum number of processors on which the program can be executed in minimal time, scheduling by an heuristic algorithm for this predefined number of processors, and serialization of the parallel schedule according to the earliest start time of the tasks. At run time tasks are taken from the serialized schedule and assigned to the processor which allows the earliest start time of the task. The order of the tasks decided at compile time is not changed at run time regardless of the number of the available processors which means there is no out-of-order issue and execution. The scheduling is done predominantly at compile time and dynamic scheduling is minimized and diminished to allocation of the tasks to the processors. We evaluate the proposed algorithms by comparing them in terms of schedule length to the CP/MISF algorithm. For performance evaluation we use both randomly generated DAGs (directed acyclic graphs) and DACs representing real applications. From practical point of view, the algorithms we propose can be successfully used for scheduling programs for in-order superscalar processors and shared memory multiprocessor systems. Superscalar processors with any number of functional units can execute the parallelism-independent code in minimum time without necessity for dynamic scheduling and out-of-order issue hardware. This means that the use of our algorithms will lead to reducing the complexity of the hardware of the processors and the run-time overhead related to the dynamic scheduling.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.6
• /
• pp.2406-2412
• /
• 2015

Multi-user multi-input multi-output (MU-MIMO) system has attracted the 4^th generation wireless network as one of core technique for performance enrichment. In this system rate control is a challenging problem and another problem is optimization. Proper scheduling can resolve these problems by deciding which set of user and at which rate the users send their data. This paper proposes a new multi-parameter based scheduling (MPS) for downlink multi-user multiple-input multiple-output (MU-MIMO) system under space-time block coding (STBC) transmissions. Goal of this MPS scheme is to offer improved link level performance in terms of a low average bit error rate (BER), high packet delivery ratio (PDR) with improved resource utilization and service fairness among the user. This scheme allows the set of users to send data based on their channel quality and their demand rates. Simulation compares the MPS performance with other scheduling scheme such as fair scheduling (FS), normalized priority scheduling (NPS) and threshold based fair scheduling (TFS). The results obtained prove that MPS has significant improvement in average BER performance with improved resource utilization and fairness as compared to the other scheduling scheme.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.3
• /
• pp.55-65
• /
• 2005

In recent manufacturing systems, most jobs may have several process plans, such as alternative sequence of operations, alternative machine etc. A few researches have addressed the necessity for the integration of process planning and scheduling function for efficient use of manufacturing resources. But the integration problem is very difficult and complex. Many prior researches considered them separately or sequentially. It introduces overlapping or partial duplications in solution efforts. In this paper, Integration problem of jobs with multiple process plans in a job shop environment Is addressed. In order to achieve an efficient integration between process planning and scheduling by taking advantage of the flexibility that alternative process plans offer, we designed GA(Genetic Algorithm)-based scheduling method. The performance of proposed GA is evaluated through comparing integrated scheduling with separated scheduling in real world company with alternative machines and sequences of operations. Also, a couple of benchmark problems are used to evaluate performance. The integrated scheduling method in this research can be effectively epplied to the real case.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5B
• /
• pp.270-276
• /
• 2007

The proposed LDS(Link-status Dependent Scheduling) algorithm in HR-WPAN(High Rate-Wireless Personal Area Network) up to now aims at doing only throughput elevation of the whole network, when the crucial device is connected with worst-link relatively, throughput of this device becomes aggravation. The proposed the WGS(Worst-case Guaranteed Scheduling) algorithm in this paper guarantees throughput of the device which is connected with worst-link in a certain degree as maintaining throughput of all devices identically even if a link-status changes, decreases delay of the whole network more than current LDS algorithm. Therefore proposed WGS algorithm in this paper will be useful in case of guaranteeing throughput of a device which is connected worst-link in a certain degree in a design of HR-WPAN hereafter.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.1
• /
• pp.14-23
• /
• 1996

Scheduling jobs effectively under consideration of actual loads on machines is one of the most complicated tasks in production control. The complexity of the finite capacity scheduling often makes the conventional methods of industrial engineering fail. As an alternative, Knowledge-based approaches to job-shop scheduling have been evolved recently. This paper presents a blackboard- based scheduling expert system which combines knowledge-based scheduling with interactive scheduling. It is shown to be possible to generate the feasible schedule within a reasonable time. Flexible reaction management is also possible while keeping the changes in the generated schedule to the minimal and adjusting the schedule to tardy operations or working environmental changes. The system is equipped with a rule base with heuristics for handling conflicted event. A case study applying the implemented system is described.

• Journal of Internet Computing and Services
• /
• v.6 no.2
• /
• pp.25-35
• /
• 2005

The Rate Monotonic(RM) scheduling algorithm and Earliest Deadline First(EDF) scheduling algorithm are normally used in Real-Time scheduling algorithm. In those scheduling algorithm, we could predict the performance possibility with total utilization value of task group. But. it had problems with prediction of the boundedness in individual task when the utilization value was over in temporary task. In this paper, the suggested scheduling algorithm can predict task when the utilization value was over and it suggested the method of predicting scheduling possibility based on the utilization value of individual task as well. it predicted the boundedness of scheduling possibility test through simulation In Real-Time scheduling algorithm and analyzed the result.

• Journal of the Korea Society for Simulation
• /
• v.14 no.3
• /
• pp.91-100
• /
• 2005

Grid computing is widely applicable to various fields of industry including process control and manufacturing, military command and control, transportation management, and so on. In a viewpoint of application area, grid computing can be classified to three aspects that are computational grid, data grid and access grid. This paper focuses on computational grid which handles complex and large-scale computing problems. Computational grid is characterized by system dynamics which handles a variety of processors and jobs on continuous time. To solve problems of system complexity and reliability due to complex system dynamics, computational grid needs scheduling policies that allocate various jobs to proper processors and decide processing orders of allocated jobs. This paper proposes a service prediction-based job scheduling model and present its scheduling algorithm that is applicable for computational grid. The service prediction-based job scheduling model can minimize overall system execution time since the model predicts the next processing time of each processing component and distributes a job to a processing component with minimum processing time. This paper implements the job scheduling model on the DEVS modeling and simulation environment and evaluates its efficiency and reliability. Empirical results, which are compared to conventional scheduling policies, show the usefulness of service prediction-based job scheduling.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.1
• /
• pp.23-32
• /
• 2011

Domestic leading construction companies has been establishing and performing TACT scheduling method, similar to linear scheduling model such as line of balance and repetitive schedule, and etc. in which repetitive construction works are involved like high-rise building. Linear scheduling model has been researched as a visual scheduling method presenting the work space and time information. Likewise scheduling constraints of CPM network such as finish-to-finish, start-to-start, finish-to-start, start-to-start, linear scheduling model also has the relationships constraints, namely boundary conditions, between activities. It is especially necessary to define the boundary conditions of the activities' relationships in order to apply the linear scheduling model to be compatible with the network schedule. Therefore, this research considers the boundary conditions between activities for establishing the linear scheduling model. This paper also applies the proposed boundary conditions to TACT schedule and then deduces the main considerations in order to establish and perform TACT schedule.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.2
• /
• pp.227-233
• /
• 2004

Complex scheduling problems are related to planning, scheduling, constraint satisfaction problems, object-oriented concepts, and agent systems. Human preference-driven scheduling technique was to solve complex scheduling problems using constraint satisfaction problems and object-oriented concepts. We have tried to apply human preference-driven scheduling technique to reservation problems. For customer's satisfaction, we have considered customer's preferences in the reservation scheduling. The technique of reservation scheduling proposed in this thesis is based on object-oriented concepts. 1'o consider the over all satisfaction, the events of every object are alloted to the board along its priority. Constraints to reservation scheduling are classified to global and local. The definition of board and information of every event are global constraints and the preferences to object's board slots are local constraints. We have applied look-ahead technology to reservation scheduling in order to minimize backtracking not to fail the allotment of events.

• Proceedings of the IEEK Conference
• /
• 2004.06b
• /
• pp.459-462
• /
• 2004

In this paper, we present a reducing power consumption of a scheduling for module selection under the time constraint. A a reducing power consumption of a scheduling for module selection under the time constraint execute scheduling and allocation for considering the switching activity. The focus scheduling of this phase adopt Force-Directed Scheduling for low power to existed Force-Directed Scheduling. and it constructs the module selection RT library by in account consideration the mutual correlation of parameters in which the power and the area and delay. when it is, in this paper we formulate the module selection method as a multi-objective optimization and propose a branch and bound approach to explore the large design space of module selection. Therefore, the optimal module selection method proposed to consider power, area, delay parameter at the same time. The comparison experiment analyzed a point of difference between the existed FDS algorithm and a new FDS_RPC algorithm.