• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.118-136
• /
• 1997

The multi-agent system is an environment in which applications solve tasks by cooperating with each other. In the multi-agent system, a user can solve complex problems by issuing a single command instead of a series of commands. However, agents depend on the state of other agents for they cooperate with each other. The problem worsens as multi-agent systems are connected to from a group of multi-agent systems. In this paper, we present the termination problem of an agent in a multi-agent system or a group of multi-agent systems. We also give asolution of the problem and present an example through implemented multi-agent systems.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.5
• /
• pp.489-497
• /
• 2001

This paper describe design and implementation of a medical multi-agent system platform called MAMI (Multi-Agent system for Medical Image), which provides intelligent medical information services. The most important component of MAMI is a medical multi-agent system platform that supports a physical environment that medical agents can be deployed. MAMI follows FIPA (Foundation for Intelligent Physical Agent)\`s agent management reference model. In MAMI, COM(Common Object Model) and XML (eXtensibel Markup Language) for encoding ACL (Agent Communication Language) are used for multi-agent communications. In MAMI, a medical staff is conceptualized as an agent and integrated with multi-agent systems. MAMI agent platform provides an infrastructure applicable to share necessary knowledge between human agents and software agents. So MAMI makes intelligent medical information services easier.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.154-154
• /
• 2000

The cooperative strategy for the teleoperated multi-agent system is presented. And this scheme has been applied to the teleoperated robot soccer system that is newly proposed. For the teleoperated robot soccer system, we made mapping functions to control a 2-wheeled mobile robot using a 2 DoF stickcontroller. The simulation with a real stickcontroller has been evaluated the performance of the proposed mapping function. Then, the basic cooperation strategy has been tested between teleoperated robot and autonomous robot It is shown that the multi-agent system for teleoperation can have a good performance for a job Like a scoring a goal

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.4
• /
• pp.660-668
• /
• 2007

In order to improve the efficiency of service restoration function in the current Distribution Automation System (DAS), in this paper it is proposed a more advanced and efficient service restoration approach using Multi-Agent technique based on distributed networks. In the current DAS, communication networks or protocol structures are centralized with communications between the central station and FRTU through 1:1 connection. In order to maintain the current systems and enhance the proposed Multi-Agent based service restoration scheme, a device of communication and intelligence, named MASX, is newly developed to make a FRTU as an agent to cooperate each others. the proposed system applied in a demo system for an distribution automation system and shows 8 times reduction of restoration time in restoration of blackouts.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.8
• /
• pp.365-372
• /
• 2001

This paper presents a new protection concept to achieve the adaptive optimal function by introducing the multi-agent system technology. Making each relay an agent which consists of relay agent module and coordinator module, each agent works autonomously to improve protection capability by cooperating with other agents. It is applied to the overcurrent protection system of the industrial power system in order to show the feasibility of the proposed methodology.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.7-13
• /
• 2009

This paper presents benefits of multi-agent system approach and its application to the distribution automation system. Special attention is devoted to the description of hardware and communication platform used to upgrade the conventional distribution automation system structure. Service restoration of primary distribution system is selected as an example of the multi-agent system application. Application of the algorithm for multi-agent based service restoration technique is disclosed in detail. Real field test in Gochang test center of KEPCO has been performed to establish the feasibility of proposed technique.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.925-926
• /
• 2006

In the multi-agent system for a single task, the action selection can be made for the real-time environment by using the global coordination space, global coordination graph and MAX-PLUS algorithm. However, there are some difficulties in multi-agent system for multi-tasking. In this paper, a real-time decision making method is suggested by using coordination space, coordination graph and dynamic coordinated state of multi-agent system including many agents and multiple tasks. Specifically, we propose locally dynamic coordinated state to effectively use MAX-PLUS algorithm for multiple tasks completion. Our technique is shown to be valid in the box pushing simulation of a multi-agent system.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.587-594
• /
• 2001

Multi-agent system fits to the distributed and open internet environments. In a multi-agent system, agents must cooperate with each other through a coordination procedure, when the conflicts between agents arise. Where those are caused by the point that each action acts for a purpose separately without coordination. But previous researches for coordination methods in multi-agent system have a deficiency that they cannot solve correctly the cooperation problem between agents, which have different goals in dynamic environment. In this paper, we suggest the automatic coordination model for multi-agent system using neural network and reinforcement learning in dynamic environment. We have competitive experiment between multi-agents that have complexity environment and diverse activity. And we analysis and evaluate effect of activity of multi-agents. The results show that the proposed method is proper.

• Journal of Intelligence and Information Systems
• /
• v.9 no.3
• /
• pp.1-21
• /
• 2003

In this research, we developed a Multi-Agent based Negotiation Support System to be able to increase the competitive power of a company in dynamic environment and correspond to various orders of customers by diffusion of electronic commerce. The system uses the agent technology that is being embossed as new paradigm in dynamic environment and flexible system framework. The multi-agent technology is used to solve these problems through cooperation of agent. The system consists of six sub agents: Mediator, manufacturability Analysis Agent, Process Planning Agent, Scheduling Agent, Selection Agent, Negotiation-strategy Building Agent. In this paper, the proposed Multi-Agent based Negotiation Support System takes aim at the automation of transaction process from ordering to manufacturing plan through the automation of negotiation that is the most important in order-taking transaction.

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.308-316
• /
• 2004

This paper proposed mediator agent system that guarantees reciprocity to attendances in bilateral negotiations for electronic commerce that is different from regular commercial transactions. The optimal agreement was supposed to provide the total maximum profits and the minimum difference in profits of both attendances in negotiations. In the mediator agent system, mediator agent conducted the negotiations considering multi attributes of product and Multi Attribute Utility Theory(MAUT) was applied to evaluate the profits of buyer and seller. 1'he negotiation model in mediator agent system was transformed into linear programming according to the information of bargain for attendances in negotiations. In order to compare with mediator agent system under the same conditions of reciprocity, another negotiation agent system was implemented using trade-off mechanism that is an algorithm for agent interactions in negotiation. The negotiation agent system using trade-off mechanism did not guarantee the optimal agreement, whereas mediator agent system provided attendances in negotiations with optimal agreement rapidly in comparison with trade-off mechanism.