• Journal of Korea Game Society
• /
• v.13 no.2
• /
• pp.39-48
• /
• 2013

In MMORPGs(Massively Multi-player Online Role-Playing Games) a large number of players actively interact with one another in a virtual world. Therefore MMORGs must be able to quickly process real-time access requests and process requests from numerous gaming users. A key challenge is that the workload of the game server increases as the number of gaming users increases. To address this workload problem, many developers apply with distributed server architectures which use dynamic map partitioning and load balancing according to the server function. Therefore most MMORPG servers partition a virtual world into zones and each zone runs on multiple game servers. These methods cause of players frequently move between game servers, which imposes high overhead for data updates. In this paper, we propose a new architecture that apply with an arithmetic server dedicated to data operation. This architecture enables the existing game servers to process more access and job requests by reducing the load. Through mathematical modeling and experimental results, we show that our scheme yields higher efficiency than the existing ones.

• Journal of Aerospace System Engineering
• /
• v.13 no.5
• /
• pp.1-8
• /
• 2019

Recently, avionics has been migrating from a federated architecture to an integrated modular architecture based on a multi-core to reduce the number of systems, weight, power consumption, and platform redundancy. The volume of data which must bo provided to the pilot through the display device has increased, because an integrated single device performs multiple functions. For this reason, the volume of data processed by the graphic processor within a fixed operation period has increased. In this paper, we provide a multi-core-based rendering engine in to perform more graphics processing within a fixed operation period. We assume the proposed method uses a multi-core-based partitioning operating system using the AMP (Asymmetric Multi-Processing) architecture.

• Journal of the Society of Naval Architects of Korea
• /
• v.53 no.6
• /
• pp.447-455
• /
• 2016

Precise propulsion shafting alignment of ships is very important to prevent damage of its support bearings due to excessive reaction forces caused by hull deflection, forces acted on propeller and crankshaft, and so forth. In this paper, a new iterative shafting alignment calculation procedure considering the interaction between shaft deflection and oil film pressure of Sterntube Journal Bearing (SJB) bush with single or multiple slopes is proposed. The procedure is based on a pressure analysis to evaluate distributed equivalent support stiffness of SJB by solving Reynolds equation and a deflection analysis of shafting system by a finite element method based on Timoshenko beam theory. SJB is approximated with multi-point biaxial elastic supports equally distributed to its length. Their initial stiffness values are estimated from dynamic reaction force calculated by assuming SJB as single rigid support. Then, the shaft deflection and the support stiffness of SJB are sequentially and iteratively calculated by applying a criteria on deflection variation between sequential calculation results. To demonstrate validity and applicability of the proposed procedure for optimal slope design of SJB, numerical analysis results for a shafting system are described.

• Journal of KIISE:Software and Applications
• /
• v.30 no.10
• /
• pp.955-972
• /
• 2003

As the next significant software abstraction, software agents have generated lots of excitements in recent years because of its promise as a new paradigm for conceptualizing, designing, and implementing software systems. This promise is particularly attractive for creating software that operates in environments that are distributed, open, and complex, such as the Internet. The effort of developing agent systems have, however, suffered from lack of generalized agent architecture because of various properties of an agent and nonexistence of a standard agent architecture. An agent architecture is an important criterion in order to not only identify agents in their domain but also determine the software architecture of the system. The major contribution of the work described here is an object-oriented design of an agent architecture that addresses fundamental properties, which are autonomy and interaction. Object-oriented design method is used for identifying the internal modules of an agent architecture and organizing correlation between the modules are identified.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.3 s.345
• /
• pp.48-58
• /
• 2006

This paper presents 8x8 two dimensional DCT/IDCT processor of adder-based distributed arithmetic architecture without applying ROM units in conventional memories. To reduce hardware cost in the coefficient matrix of DCT and IDCT, an odd part of the coefficient matrix was shared. The proposed architecture uses only 29 adders to compute coefficient operation in the 2-D DCT/IDCT processor, while 1-D DCT processor consists of 18 adders to compute coefficient operation. This architecture reduced 48.6% more than the number of adders in 8x8 1-D DCT NEDA architecture. Also, this paper proposed a form of new transpose network which is different from the conventional transpose memory block. The proposed transpose network block uses 64 registers with reduction of 18% more than the number of transistors in conventional memory architecture. Also, to improve throughput, eight input data receive eight pixels in every clock cycle and accordingly eight pixels are produced at the outputs.

• Proceedings of the Korea Database Society Conference
• /
• 1998.09a
• /
• pp.525-543
• /
• 1998

This paper proposes a conceptual taxonomy of architectures far workflow management systems. The systematic classification work is based on a framework for workflow architectures. The framework, consisting of generic-level, conceptual-level and implementation-level architectures, provides common architectural principles for designing a workflow management system. We define the taxonomy by considering the possibilities for centralization or distribution of data, control, and execution. That is, we take into account three criteria. How are the major components of a workflow model and system, like activities, roles, actors, and workcases, concretized in workflow architecture？ Which of the components is represented as software modules of the workflow architecture？ And how are they configured and operating in the architecture？ The workflow components might be embodied, as active (processes or threads) modules or as passive (data) modules, in the software architecture of a workflow management system. One or combinations of the components might become software modules in the software architecture. Finally, they might be centralized or distributed. The distribution of the components should be broken into three: Vertically, Horizontally and Fully distributed. Through the combination of these aspects, we can conceptually generate about 64 software Architectures for a workflow management system. That is, it should be possible to comprehend and characterize all kinds of software architectures for workflow management systems including the current existing systems as well as future systems. We believe that this taxonomy is a significant contribution because it adds clarity, completeness, and "global perspective" to workflow architectural discussions. The vocabulary suggested here includes workflow levels and aspects, allowing very different architectures to be discussed, compared, and contrasted. Added clarity is obtained because similar architectures from different vendors that used different terminology and techniques can now be seen to be identical at the higher level. Much of the complexity can be removed by thinking of workflow systems. Therefore, it is used to categorize existing workflow architectures and suggest a plethora of new workflow architectures. Finally, the taxonomy can be used for sorting out gems and stones amongst the architectures possibly generated. Thus, it might be a guideline not only for characterizing the existing workflow management systems, but also for solving the long-term and short-term architectural research issues, such as dynamic changes in workflow, transactional workflow, dynamically evolving workflow, large-scale workflow, etc., that have been proposed in the literature.

• The Journal of Information Technology and Database
• /
• v.5 no.1
• /
• pp.97-108
• /
• 1998

This paper proposes a conceptual taxonomy of architectures for workflow management systems. The systematic classification work is based on a framework for workflow architectures. The framework, consisting of generic-level, conceptual-level and implementation-level architectures, provides common architectural principles for designing a workflow management system. We define the taxonomy by considering the possibilities for centralization or distribution of data, control, and execution. That is, we take into account three criteria. How are the major components of a workflow model and system, like activities, roles, actors, and workcases, concretized in workflow architecture. Which of the components is represented as software modules of the workflow architecture\ulcorner And how are they configured and operating in the architecture\ulcorner The workflow components might be embodied, as active (processes or threads) modules or as passive (data) modules, in the software architecture of a workflow management system. One or combinations of the components might become software modules in the software architecture. Finally, they might be centralized or distributed. The distribution of the components should be broken into three: Vertically, Horizontally and Fully distributed. Through the combination of these aspects, we can conceptually generate about 64 software Architectures for a workflow management system. That is, it should be possible to comprehend and characterize all kinds of software architectures for workflow management systems including the current existing systems as well as future systems. We believe that this taxonomy is a significant contribution because it adds clarity, completeness, and global perspective to workflow architectural discussions. The vocabulary suggested here includes workflow levels and aspects, allowing very different architectures to be discussed, compared, and contrasted. Added clarity is obtained because similar architectures from different vendors that used different terminology and techniques can now be seen to be identical at the higher level. Much of the complexity can be removed by thinking of workflow systems. Therefore, it is used to categorize existing workflow architectures and suggest a plethora of new workflow architectures. Finally, the taxonomy can be used for sorting out gems and stones amongst the architectures possibly generated. Thus, it might be a guideline not only for characterizing the existing workflow management systems, but also for solving the long-term and short-term architectural research issues, such as dynamic changes in workflow, transactional workflow, dynamically evolving workflow, large-scale workflow, etc., that have been proposed in the literature.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.485-492
• /
• 2006

This paper deals with implementation of network for distributed control system of a humanoid robot ISHURO(Inha Semyung Humanoid Robot). A humanoid robot needs much degree of freedom structurally and much data for having flexible movement. To realize such a humanoid robot, distributed control method is preferred to the centralized one since it gives a compactness, modularity and flexibility for the controllers. For organizing distributed control system of a humanoid robot, a control processor on a board is needed to individually control the joint motor and communication technology between the processors is required to transmit its information within control time. The processor is DSP-based processor and includes CAN network on a chip. It shares the computational load such as monitoring the sensor information and controlling the actuator between each of modules. In this paper, the communication architecture is suggested and its message protocol are discussed including message structure, time consumption for transmission, and controller structure at the view of distributed control for a humanoid robot. All of the sequence are simulated with Matlab and then verified with real walking experiment by ISHURO.

• Journal of Internet Computing and Services
• /
• v.3 no.2
• /
• pp.79-85
• /
• 2002

In open communication architecture, application systems consist of objects distributed in lots of computing nodes. To reduce complexity of development. and management of distributed software, to manage efficiently distributed objects and to provide realtime service, the mechanisms for object group management and communication are needed in distributed environment. In this paper we compose object groups and provide reliable group communication mechanism based on CORBA which can adopt a new service without lots of changes on existing system. Group consist of some subgroups that subgroup manager manages for improving the efficiency of group management and message ordering is kept by using sequencer, Communication method among groups uses multicast based on paint to point communication as well as IP multicast and we provide high performance by using selective retransmission of message through message history, We analyze the performance of the proposed mechanism through simulation in distributed environment.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.7
• /
• pp.205-216
• /
• 2022

One of the many tools used for distributed deep learning training is Kubeflow, which runs on Kubernetes, a container orchestration tool. TensorFlow jobs can be managed using the existing operator provided by Kubeflow. However, when considering the distributed deep learning training jobs based on the parameter server architecture, the scheduling policy used by the existing operator does not consider the task affinity of the distributed training job and does not provide the ability to dynamically allocate or release resources. This can lead to long job completion time and low resource utilization rate. Therefore, in this paper we proposes a new operator that efficiently schedules distributed deep learning training jobs to minimize the job completion time and increase resource utilization rate. We implemented the new operator by modifying the existing operator and conducted experiments to evaluate its performance. The experiment results showed that our scheduling policy improved the average job completion time reduction rate of up to 84% and average CPU utilization increase rate of up to 92%.