• 제목/요약/키워드: Multi-Agent Technology

검색결과 246건 처리시간 0.025초

다중 에이전트 기반 가상 생산 운영 시스템에 관한 연구 (A Study on the Multi-Agent based VM Operating System)

  • 김선;공상훈;김기범;한영근;이교일
    • 한국정밀공학회:학술대회논문집
    • /
    • 한국정밀공학회 1997년도 추계학술대회 논문집
    • /
    • pp.201-205
    • /
    • 1997
  • As manufacturing system have become complex and globalized, rapid development and production of products are essentially requisites for competitiveness. The importance of agility in manufacturing is being emphasized and a new paradigm is necessary for reduction of the time and expenses related to planning, product development and production. To meet such requirements, virtual manufacturing (VM) environment was suggested. In this paper, Multi-agent system is adopted into VM operating system. Because our system is flexible due to agent technology, agents can be added or deleted with ease. VM unit modules which were defined as DEVS models execute independent simulation of other modules in unit level and compose one VM system with other modules. They also execute simulation in system level. This research can contribute to usefulness of VM environment due to flexibility and extensibility of this system.

  • PDF

다중크로스셀링 기반의 개인 상품 추천 시스템의 설계 (A Design of Goods Recommendation System based on Multi-crossselling)

  • 윤종찬;김종진;윤성대
    • 한국멀티미디어학회논문지
    • /
    • 제9권9호
    • /
    • pp.1095-1106
    • /
    • 2006
  • 전자상거래시스템의 효율적인 운영과 관리를 위해서 더욱 많은 노력이 요구되고 있으며 고객의 요구에 대해서 가장 적절한 상품 정보를 제공함으로서 만족을 극대화할 수 있어야 한다. 이를 위해서 많은 지능형 에이전트기술을 사용한 전자상거래시스템이 도입되고 있다. 본 논문에서는 전자상거래시스템에서 개인 상품 추천 지원을 위한 사례기반추론기법과 다중크로스 셀링기법(Multi-Crossselling)을 기반으로 한 상품 추천시스템을 제안하였다. 제안한 시스템은 다중크로스셀링 기법을 통해 고객패턴의 유사값에 가까운 여러 상품을 추출하고 사례기반추론기법을 통해 특정 조건에서 고객의 요구에 대해 적절한 상품 정보를 제공하고자 한다.

  • PDF

유비쿼터스 시스템을 위한 시맨틱 다중 에이전트 (Semantic Multi-agents Framework for Ubiquitous Systems)

  • 최정화;박영택
    • 한국정보과학회논문지:소프트웨어및응용
    • /
    • 제32권3호
    • /
    • pp.192-201
    • /
    • 2005
  • 지난 10여년 동안 유비쿼터스 컴퓨팅 연구는 '언제나, 어디에서나, 어느 것이나 컴퓨팅 환경'이라는 신기술 체계의 확립을 목표로 진행되었다. 이를 통하여 칩의 소형화 기술, 장치기술, 네트워킹 기술, 인간 중심의 인터페이스 기술, 응용기술 등의 기술혁신의 필요성을 알게 되었다. 본 논문에서는 인간중심의 인터페이스 기술 측면에서 인간과 에이전트와의 상호작용 및 에이전트 스스로 인간이 원하는 서비스를 처리하고 제공하기 위하여, 다음 네 가지 단계를 제안한다. 첫째, 유비쿼터스 서비스를 사용자 요구에 맞게 서비스하기 위하여 정보자원 간에 의미적 연관성을 고려한 시맨틱 웹 기술을 이용한다. 둘째, 시맨틱 웹 기술 개발에 핵심이 되는 온톨로지를 구축하여 컴퓨터가 웹 문서의 내용을 인식할 수 있도록 한다. 셋째, W3C에서 표준화 작업 중인 차세대 웹 OWL 온톨로지 언어를 이용하여 컴퓨터와 컴퓨터 간에 메시지를 교환한다. 넷째, 컴퓨터로 전송된 메시지 분석 및 정보 수집을 위하여 FIPA의 JADE를 이용하여 다중 에이전트를 기능별로 구축한다. 본 논문에서 제안하는 시맨틱 다중 에이전트는 온톨로지 기반의 시맨틱 웹 기술을 적용하여 시맨틱 상황을 추론한다. 다중 에이전트가 OWL 온톨로지 언어를 이용하여 커뮤니케이션함으로써 같은 상황이더라도 사용자에 따라서 제공되는 서비스가 다르게 추론된다. 따라서 기존의 상황 정보 시스템보다 에이전트에게 보다 의미 있는 정보의 예측을 가능하게 하였다.

전자시장 환경에서의 금융중개를 위한 소프트웨어 에이전트 개발에 대한 연구 (Software Agent for Financial Cybermediaries in Electronic Marketspace)

  • 정철용;서용무
    • 한국전자거래학회지
    • /
    • 제4권3호
    • /
    • pp.119-137
    • /
    • 1999
  • The World Wide Web(WWW) has provided multi-media cyberspace for electronic markets where suppliers and demanders can do global electronic business with each other directly and conveniently. There are two contradictory views on the roles of intermediaries in electronic markets. One says we may not need intermediaries in doing business because suppliers and demanders can contact with each other directly in electronic markets. The other thinks that the intermediary function may be vertically decomposed from the company's internal value chain because it can be done more efficiently through networks by external intermediaries. Intelligent software agent is a new emerging technology in the field of computer science. An intelligent agent can support and do actions on behalf of users on computer networks. We think that this technology can be utilized to implement more efficient cybermediaries for electronic commerce. This paper proposes an XML-based framework for financial software agent, which selects financial products best fitted for the customer's needs in electronic market environment.

  • PDF

User-Centric Broadcasting Environment U sing Intelligent Agents

  • Jin, Sung-Ho;Bae, Tae-Meon;Cho, Jun-Ho;Ro, Yong-Man;Kang, Kyeong-Ok
    • 한국멀티미디어학회논문지
    • /
    • 제8권6호
    • /
    • pp.814-826
    • /
    • 2005
  • The user-centric broadcasting environment includes the agent system and personalized broadcasting services for user-adaptive TV watching. In this paper, we propose broadcasting environment consisting of personalized broadcasting services and a multi-agent broadcasting system for the services. The proposed system employs the intelligent agent technology of the Foundation for Intelligent Physical Agents (FIPA) as well as metadata technology of MPEG-7 and TV-Anytime Forum (TVAF). To verify the usefulness of the proposed environment, we implemented a test-bed and demonstrated the proposed agent system with three services including intelligent user-information management service, information mobility service, and content retrieval service.

  • PDF

Deep reinforcement learning for a multi-objective operation in a nuclear power plant

  • Junyong Bae;Jae Min Kim;Seung Jun Lee
    • Nuclear Engineering and Technology
    • /
    • 제55권9호
    • /
    • pp.3277-3290
    • /
    • 2023
  • Nuclear power plant (NPP) operations with multiple objectives and devices are still performed manually by operators despite the potential for human error. These operations could be automated to reduce the burden on operators; however, classical approaches may not be suitable for these multi-objective tasks. An alternative approach is deep reinforcement learning (DRL), which has been successful in automating various complex tasks and has been applied in automation of certain operations in NPPs. But despite the recent progress, previous studies using DRL for NPP operations have limitations to handle complex multi-objective operations with multiple devices efficiently. This study proposes a novel DRL-based approach that addresses these limitations by employing a continuous action space and straightforward binary rewards supported by the adoption of a soft actor-critic and hindsight experience replay. The feasibility of the proposed approach was evaluated for controlling the pressure and volume of the reactor coolant while heating the coolant during NPP startup. The results show that the proposed approach can train the agent with a proper strategy for effectively achieving multiple objectives through the control of multiple devices. Moreover, hands-on testing results demonstrate that the trained agent is capable of handling untrained objectives, such as cooldown, with substantial success.

Q-learning for intersection traffic flow Control based on agents

  • 주선;정길도
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
    • /
    • pp.94-96
    • /
    • 2009
  • In this paper, we present the Q-learning method for adaptive traffic signal control on the basis of multi-agent technology. The structure is composed of sixphase agents and one intersection agent. Wireless communication network provides the possibility of the cooperation of agents. As one kind of reinforcement learning, Q-learning is adopted as the algorithm of the control mechanism, which can acquire optical control strategies from delayed reward; furthermore, we adopt dynamic learning method instead of static method, which is more practical. Simulation result indicates that it is more effective than traditional signal system.

  • PDF

Hi-FA(유동성 및 점성 개질제)를 이용한 지반보강 및 기존 교량기초 보강공법에 대한 실용화 연구 (Field Application Study for Soil Improvement and Existing Foundation Protection Work by Hi-FA(High performance and Multi functional Agent))

  • 김명학;박명득;윤태국;이용준;박민철
    • 한국지반공학회:학술대회논문집
    • /
    • 한국지반공학회 2010년도 추계 학술발표회
    • /
    • pp.664-675
    • /
    • 2010
  • Recently environment-friendly construction method is major trend in both domestic and world constrction fields. In this paper High Functional Performance Agent(Hi-FA) which has various improved engineering characteristics different with conventional Portland cement grouting, such as high viscosity, liquidity, void filling ability, early hardening, and separation resistance, was analyzed by field and laboratory test. Also soil improvement and existing deep foundation protection works were performed and analyzed using Hi-FA.

  • PDF

작동하는 복합환경조절장치 및 녹색기반시설로서 조경 - 국립해양생물자원관 옥외공간 설계 - (Constructing Landscape as an Operational Multi-Environmental Control Utility and Green Infrastructure - Landscape Design for National Marine Biology Resource Institute -)

  • 성종상
    • 한국환경복원기술학회지
    • /
    • 제15권2호
    • /
    • pp.41-56
    • /
    • 2012
  • Landscape space can and should play as a multi-functional agent : healing contaminated soil, reducing natural hazards, supporting living things, making comfortable environment for human, and appealing to human aesthetics, etc. This article aims to show the possibility and role of landscape space as such agent. In landscape design for National Marine Biology Resource Institute, distributed rain water treatment system and rain gardens are introduced to replace a mono-functioning large detention pond which was suggested by disaster impact assesment. Phytoremediation and vegetation filtering system with muti-cell wetlands are also adapted to heal the contaminated soil. This kind of landscape as a 'living machine' which can play as an operational control utility of multi-environment and thus can be combined effectively into green infrastructure is important for post-industrial city, especially in an era of climate change.

AGV의 분산제어를 위한 에이전트 기반의 제어시스템 (Agent-based control systemfordistributed control of AGVs)

  • 오승진;정무영
    • 한국경영과학회:학술대회논문집
    • /
    • 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
    • /
    • pp.1117-1123
    • /
    • 2005
  • This paper deals with a new automated guided vehicle (AGV) control system for distributed control. Proposed AGV control system adapts the multi-agent technology. The system is composed of two types of controller: routing and order. The order controller is in charge of assignment of orders to AGVs. Through the bidding-based negotiation with routing controllers, the order controller assigns a new order to the proper AGV. The order controller announces order information to the routing controllers. Then the routing controllers generate a routing schedule for the order and make a bid according to the routing schedule. If the routing schedule conflicts with other AGV's one, the routing controller makes an alternative through negotiation with other routing controllers. The order controller finally evaluates bids and selects one. Each controller consists of a set of agents: negotiation agent, decision making agent and communication agent. We focus on the agent architecture and negotiation-based AGV scheduling algorithm. Proposed system is validated through an exemplary scenario.

  • PDF