• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2003.04a
• /
• pp.5-9
• /
• 2003

Stress and deflection of Active Fiber Composite(AFC) embedded and/or attached composite structures are numerically investigated at the constituent level by the Direct Numerical Simulation(DNS). The DNS approach which models and simulates the fiber and matrix directly using 3D finite elements need to be solved by efficient way. To handle this large scale problem, parallel program for solving piezoelectric behavior was developed and run on the parallel computing environment. Also, the stress result from DNS approach is compared with that from uniform field model.

• Journal of the Korea Society for Simulation
• /
• v.11 no.2
• /
• pp.67-75
• /
• 2002

This paper proposes a parallel simulation algorithm for bounded Petri nets in a single processor, which exploits the SIMD(Single Instruction Multiple Data)-type parallelism. The proposed algorithm is based on a data packing scheme which packs multiple bytes data in a single register, thereby being manipulated simultaneously. The parallelism can reduce simulation time of bounded Petri nets in a single processor environment. The effectiveness of the algorithm is demonstrated by presenting speed-up of simulation time for two bounded Petri nets.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.880-884
• /
• 1995

Manufacturing environment is getting characterized by unstable market demand,short product life cycle and timebased competition. For adapting this environment,machine tools have to be further versatile functionally in order to reduce part's set-up time. Unlike existing manufacturing systems mainly to focus on part flow, it is important to control tool flow using fast tool change device and tool delivery device in parallel machines consisting of versatile machine tools, because complete operations on a part can be performed on one machine tool in a single machine set-up. In this paper, under dynamic tool allocation strategy to share tools among machine tools, we propose a real-time tool allocation and operation esequence model with an objective of minimizing flow time using autonomy and negotiation of agents in parallel machines

• Korean Journal of Computational Design and Engineering
• /
• v.11 no.5
• /
• pp.384-392
• /
• 2006

In this research, the feasibility of distributed finite element analysis system with STEP and CORBA has been investigated. The enabling technologies such as CORBA and Java play key roles in the development of integrated and geographically distributed application software. In addition to the distribution of analysis modules, numerical solution process itself is again divided into parallel processes using multi-frontal method for computational efficiency. In contrast to the specially designed parallel process for specific hardware, CORBA-based parallel process is well suited for heterogeneous platforms over the network. The idea of Web-based distributed analysis system may be applied to the engineering ASP for design and analysis in the product development processes. We believe that the proposed approach for the analysis can be extended to the entire product development process for sharing and utilizing common product data in the distributed engineering environment, thus eventually provide basis for virtual enterprise.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.3
• /
• pp.1132-1136
• /
• 2014

In the context of increasing electric energy consumption in a data center, energy efficiency improvement is strongly emphasized. In a data center, electric energy is largely consumed by DC power supply system, which is based on a rectifier composed by multiple parallel converters. Therefore, rectifier efficiency must be improved for minimizing loss of DC power supply system. Rectifier efficiency can be modulated by load allocation to converters because converter efficiency depends on input AC power. In this paper, we propose a new control method to maximize rectifier efficiency. The method can control load allocation to converters by introducing active power converter control scheme and start-and-stop of converters. In order to illustrate optimal load allocations in a rectifier, a maximization problem of rectifier efficiency is formulated as a nonlinear optimization one. The problem is solved by Lagrangian relaxation method and the computation results provide the validity of proposed method.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.35 no.11
• /
• pp.973-982
• /
• 2007

In this paper, optimal design framework is developed by automatic mesh generation and PSO(Particle Swarm Optimization) algorithm based on parallel computing environment and applied to structural optimal design of satellite adapter module. By applying automatic mesh generation, it became possible to change the structural shape of adapter module. PSO algorithm was merged with parallel computing environment and for maximizing a computing performance, asynchronous PSO algorithm was developed and could reduce the computing time of optimization process. As constraint conditions, eigen-frequency and maximum stress was considered. Finally using optimal design framework, weight reduction of satellite adapter module is derived with satisfaction of structural safety.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1284-1286
• /
• 2003

There is a growing demand on remotely sensed and GIS data services in modern society. However, conventional WEB applications based on client/server pattern can not meet the criteria in the future . Grid computing provides a promising resolution for establishing spatial information system toward future applications. Here, a new architecture of the distributed environment for remotely sensed data processing based on the middleware technology was proposed. In addition, in order to utilize the new environment, a problem had to be algorithmically expressed as comprising a set of concurrently executing sub-problems or tasks. Experiment of the algorithm was implemented, and the results show that the new environmental can achieve high speedups for applications compared with conventional implementation.

• Journal of IKEEE
• /
• v.18 no.3
• /
• pp.398-402
• /
• 2014

In this paper, we propose a parallel processing method of pedestrian detection algorithm based on ROI-CENTRIST. There is a difficulty in the real-time processing of pedestrian detection in the embedded environment, using the conventional pedestrian detection method. This problem can be solved by a parallel processing method of applying the ROI to the conventional algorithm. The proposed parallel processing method of pedestrian detection using ROI-CENTRIST show the result of 5.2 frames per second, which is about 10% improvement over the conventional pedestrian detection method based on CENTRIST.

• Journal of Information Processing Systems
• /
• v.13 no.3
• /
• pp.518-532
• /
• 2017

Due to the rapid growth of the amount of data, research on bigdata processing has been highlighted. For bigdata processing, CUBRID Shard is able to support query processing in parallel way by dividing the database into a number of CUBRID servers. However, CUBRID Shard can answer a user's query only when the query is required to gain accesses to a single CUBRID server, instead of multiple ones. To solve the problem, in this paper we propose a CUBRID based distributed parallel query processing system that can answer a user's query in parallel and distributed manner. Finally, through the performance evaluation, we show that our proposed system provides 2-3 times better performance on query processing time than the existing CUBRID Shard.

• 한국전산유체공학회:학술대회논문집
• /
• 2001.05a
• /
• pp.149-154
• /
• 2001

Parallel performance of a Myrinet based PC-cluster was tested and compared with a conventional Fast-Ethernet system. A preconditioned Navier-Stokes code was parallelized with domain decomposition technique, and used for the parallel performance test. Speed-up ratio was examined as a major performance parameter depending on the number of processor and the network topology. As was expected, Myrinet system shows a superior parallel performance to the Fast-Ethernet system even with a single network adpater for a dual processor SMP machine. A test for the dependency on problem size also shows that network communication speed is a crucial factor for parallelized computational fluid dynamics analysis and the Myrinet system is a plausible candidate for high performance parallel computing system.