• Journal of Korean Institute of Industrial Engineers
• /
• 제30권1호
• /
• pp.1-10
• /
• 2004

Advance in Internet technology has changed traditional production planning and control methods. In particular, collaborations between participants in supply chains are being increasingly addressed in industry for enhancing chain-wide productivity. A representative paradigm that emphasizes collaboration in production planning and control is CPFR(Collaborative Planning, Forecasting and Replenishment). In this paper, we present a multi-agent system architecture that supports the collaborations specified in CPFR. The multi-agent system architecture consists of event manager, data view agent, business rule agent, and collaboration agent. The collaboration agent systematically controls negotiation between supplier and buyer with the aid of collaboration protocol and blackboard. The multi-agent system has been implemented with EJB(Enterprise Java Beans).

• Journal of KIISE:Computing Practices and Letters
• /
• 제7권5호
• /
• 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.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• 제56권12호
• /
• pp.2072-2077
• /
• 2007

The primary objective of all power systems is to maintain the reliability and to minimize outage time for fault or the others. The frequency relaying algorithm perceives a variation of system frequency and thereafter detects the unbalance between generation and load. A multi-agent system is composed of multiple interacting computing elements that are known as agents. In this paper, frequency relaying algorithm is designed by multi-agent system and is implemented by EMTP-MODELS. To verify performance of the frequency relaying algorithm based on multi-agent system, simulations by EMTP have been carried out.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2003년도 하계학술대회 논문집 A
• /
• pp.299-301
• /
• 2003

In this paper, a protection system using Multi-Agent concept for power distribution network is proposed. Multi agent system consist of Feeder agent, OCR(Over Current Relay) agent, Recloser agent and Switch agent. An agent calculates and corrects its parameter by itself through communication with neighboring agents and its own intelligence algorithm. Simulations in a simple distribution network show the effectiveness of the suggested protection system. Multi-Agent System, protection of distribution network, Communication.

• KIISE Transactions on Computing Practices
• /
• 제21권4호
• /
• pp.290-298
• /
• 2015

This paper suggests a multi-agent message transport architecture based on the message-oriented middleware ZeroMQ. Compared with the other middlewares such as CORBA, Ice, and Thrift, ZeroMQ receives a good score in the evaluation of performance, QoS (Quality of Service), patterns, user friendliness, and resources. The suggested message transfer architecture borrowed many basic concepts like agent platform, AMS (Agent Management System), and MTS (Message Transfer System) from FIPA (Foundation for Intelligent Physical Agents) standard multi-agent specifications, and the architecture inherited the strength of the architecture from the multi-agent framework SMAF (Smart Multi-Agent Framework). The architecture suggested in this paper is a novel peer-to-peer architecture which is not known to the ZeroMQ community. In the suggested architecture, every MTS agent uses only one ZeroMQ router socket to support peer-to-peer communication among MTS agents. The suggested architecture can support closely collaborating software areas such as intelligent robots as well as the traditional application areas of multi-agent architecture. The suggested architecture has interoperability and scalability with the ZeroMQ devices and patterns.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• 제52권9호
• /
• pp.506-512
• /
• 2003

In this paper, a communication module between Relay agents in a multi-agent system based power distribution network protection system is realized using DNP3.0(Distributed Network Protocol), which is the standard communication protocol of distribution automation system in KEPCO. The key words for agent communication in the multi-agent based protection system are defined and represented by use of DNP application function code. The communication module developed based on the proposed communication scheme is tested by use of the Communication Test Harness, a test tool for DNP protocol, then used to the multi-agent system based power distribution net work protection system.

• International Journal of Control, Automation, and Systems
• /
• 제5권3호
• /
• pp.295-306
• /
• 2007

It is well known that mathematical solutions for multi-agent planning problems are very difficult to obtain due to the complexity of mutual interactions among multi-agents. Most of the past research results are thus based on the probabilistic completeness. However, the practicality and effectiveness of the solution from the probabilistic completeness is significantly reduced by heavy computational burden. In this paper, we propose a practically applicable solution technique for multi-agent planning problems, which assures a reasonable computation time and a real world application for more than 3 multi-agents, for the case of general shaped paths in agent movement. First, to reduce the computation time, an extended collision map is developed and utilized for detecting potential collisions and obtaining collision-free solutions for multi-agents. Second, a priority for multi-agents is considered for successive and interactive modifications of the agent movements with lower priority. Various solutions using speed reduction and time delay of the relevant agents are investigated and compared in terms of the computation time. A practical implementation is finally provided for three different types of agents to emphasize the effectiveness of the proposed interactive approach to multi-agent planning problems.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• 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.

• Proceedings of the KAIS Fall Conference
• /
• 한국산학기술학회 2003년도 Proceeding
• /
• pp.35-41
• /
• 2003

A multi-agent technology has emerged as a new paradigm that can flexibly and promptly cope with various environmental changes and complex problems. Accordingly, many researches are being made to establish multi-agent systems in an effort to solve dynamic problems in many fields. However, most previous researches on the multi-agent frameworks aimed at, on behalf of a user, exchanging and sharing information between agents, reusing agents, and suggesting job cooperation in order to integrate and assimilate heterogeneous agents. That is to say, their frameworks mainly focused on the basic functions of general multi-agent. Therefore, they are not suitable to the development of the proper system for a specific field such ,.s a negotiation. In an effort to solve this problem, this research has tried to design a multi-agent framework-base negotiation system, so that for the sake of a user it can evaluate the negotiation messages, manage the negotiation messages, and quickly and exactly exchange messages between negotiation agents. First of all, we have made research on the basic functions hat are necessary in the development of a negotiation system, and then have analyzed the limitations of existing multi-agent frameworks when trying to apply them to a negotiation system. After these efforts, this study suggests a design of multi-agent framework to develop a negotiation system.

• The KIPS Transactions:PartB
• /
• 제8B권6호
• /
• 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.