• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.04a
• /
• pp.334-339
• /
• 2000

본 연구의 목적은 국내 전자상거래 시장의 활성화에 기여할 수 있는 정책지향 매칭 에이전트(policy-oriented matching agent) 시스템을 개발하는 데 있다. 이 시스템은 판매자가 다양한 마케팅 정책을 손쉽게 구현할 수 있는 일종의 커머스 서버 시스템으로서 본 논문에서는 룰기반 매칭(rule-based matching)에서 진화된 정책지향 매칭 에이전트를 제안하였다. 정책지향 매칭 에이전트 분야에서 본 연구는 정책과 공간을 뚜렷이 구분함으로써 인터넷 솔루션에서 진정한 마케팅 중심의 솔루션 개념을 분명히 하였다. 정책지향 매칭 에이전트는 편집자 기반(Editor-based)의 반자동화 에이전트로 분류될 수 있다.

• Journal of the Korea Society for Simulation
• /
• v.22 no.4
• /
• pp.49-55
• /
• 2013

Recently the CGF/SAF (Computer Generated Force / Semi-Automated Force) technology has been getting attention to deal with the increasing complexity in a DM&S(Defence Modeling and Simulation) environment. OneSAF is one of well-known CGF/SAF systems, however, it is not able to support the DEVS framework which is an advanced discrete event based modeling and simulation environment. Especially, most DM&S systems in Korea has been developed on the basis of the DEVS framework. In this paper, we have proposed the agent-based SAF design methodology and tool for supporting DEVS M&S environment. The proposed SAF modeling tool is divided into two parts; the agent modeling part and SAF modeling part. In the agent modeling environment, the modeler can simply create the agent model by writing down the necessary rules. It also provides the agent testing environment so that the modeler maybe conveniently verify the prescribed agent model. The SAF model is finally created by combing the individual agents based on the pre-defined structure. DM&S engineers will be able to employ our tools and modeling methodology to design the DEVS-based DM&S system to be developed.

• Journal of Internet Computing and Services
• /
• v.12 no.3
• /
• pp.27-36
• /
• 2011

The sensor nodes of sensor network system are capable of wireless communication with sink nodes. They also acquire and transmit sensor data in broad region where people cannot access easily. However, the transmission of redundant data from sensor nodes reduces the lifetime of the entire system and substantial amount of resulted data needs to be resorted before implementing them to the specific applications. In this paper, the mobile agent middleware to eliminate the redundant sensor data is designed and implemented. In the proposed system, the mobile agent visits the destination sensor nodes according to the migration list offered by the meta table in the name space of the naming agent, eliminates the redundant sensor data corresponding to user condition, and acquires and transmits sensor data according to the purpose and needs. Thus, the excess transmission of the sensor data is avoided and the lifetime of the entire system can be extended. Moreover, the experiments using the mobile agent middleware with the conditions and limitations that are possible in real situation ore done to verify the successful elimination of the redundant sensor data and the efficiency of the data acquisition. Also, we show the potential applicability of the mobile agent middleware in various active sensor networks through the active rule based mobile agent middleware or the interaction with the active rule system.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.17-23
• /
• 2022

Network slicing is a promising paradigm and significant evolution for adjusting the heterogeneous services based on different requirements by placing dynamic virtual network functions (VNF) forwarding graph (VNFFG) and orchestrating service function chaining (SFC) based on criticalities of Quality of Service (QoS) classes. In system architecture, software-defined networks (SDN), network functions virtualization (NFV), and edge computing are used to provide resourceful data view, configurable virtual resources, and control interfaces for developing the modified deep reinforcement learning agent (MDRL-A). In this paper, task requests, tolerable delays, and required resources are differentiated for input state observations to identify the non-critical/critical classes, since each user equipment can execute different QoS application services. We design intelligent slicing for handing the cross-domain resource with MDRL-A in solving network problems and eliminating resource usage. The agent interacts with controllers and orchestrators to manage the flow rule installation and physical resource allocation in NFV infrastructure (NFVI) with the proposed formulation of completion time and criticality criteria. Simulation is conducted in SDN/NFV environment and capturing the QoS performances between conventional and MDRL-A approaches.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.06a
• /
• pp.91-100
• /
• 2003

In this paper we investigate the role that warfare played In the formation of the network of alliances between sites that are associated with the formation of the state in the Valley of Oaxaca, Mexico. A model of state formation proposed by Marcos and Flannery (1996) is used as the basis for an agent-based simulation model. Agents reside in sites and their actions are constrained by knowledge extracted from the Oaxaca Surface Archaeological Survey (Kowalewski 1989). The simulation is run with two different sets of constraint rules for the agents. The first set is based upon the raw data collected in the surface survey. This represents a total of 79 sites and constitutes a minimal level of warfare (raiding) in the Valley. The other site represents the generalization of these constraints to sites with similar locational characteristics. This set corresponds to 987 sites and represents a much more active role for warfare in the Valley. The rules were produced by a data mining technique, Decision Trees, guided by Genetic Algorithms. Simulations were run using the two different rule sets and compared with each other and the archaeological data for the Valley. The results strongly suggest that warfare was a necessary process in the aggregations of resources needed to support the emergence of the state in the Valley.

• Proceedings of the KIEE Conference
• /
• 2006.07a
• /
• pp.52-53
• /
• 2006

현재 국내 배전자동화 시스템의 고장구간을 최소한으로 하는 불필요 정전구간 복구시스템은 고장발생 시 중앙에서 고장구간을 판단하고 Fuzzy Rule을 이용한 복구해를 통하여 계통의 Device들을 운영자가 직접 제어하는 방식이다. 이러한 방식은 원격으로 제어가 가능하며 운영자가 직접 상황에 따라 적절한 판단을 하여 신뢰성이 크다는 장점이 있지만, 운영자의 실수에 의해서 계통에 문제가 발생할 가능성도 있고, 정전복구시간 면에서 볼 때 오퍼레이터의 실수에 의해 생기는 복구지연시간은 소비자들에게는 경제적 손실 및 불편을 초래할 수 있다. 따라서 이러한 운영자의 실수를 미연에 방지하고 정전복구 시간 또한 가급적 줄일 수 있는 방안을 마련하는 것이 필요하다. 본 연구에서 제안하는 Multi-Agent 기반의 분산형 정전복구 시스템은 중앙의 제어를 통하지 않고 계통 내의 Device들이 Agent 개념의 지능을 가지고 상호 정보교환을 통하여 고장구간을 판단하고 정전을 복구하는 시스템으로 현재 배전자동화 시스템의 복구시간을 1분 이내로 단축시킬 수 있는 시스템을 제안하였다. 간단한 배전계통을 구성하고 전력계통의 현재 통신망중 유/무선의 대표적인 LAN 및 CDMA 통신을 이용한 사례연구를 통해 제안한 시스템에서의 정전구간 1분 이내의 복구시간을 입증하였다.

• Journal of Internet Computing and Services
• /
• v.7 no.6
• /
• pp.21-40
• /
• 2006

As the knowledge-based society hot been constructed, the size of work process that has to be done grows big and the amount of the information that has to be analyzed increases. In the paper business process can be accurately executed by the rule agent to manage precise rules and definitions to be needed by execution of process for management of business process. And individuals con accurately measure and manage personal schedules to execute process through supporting the agent of schedule management. The model is designed and implemented for organization to improve process of control, flexibleness, agility, reliability, and reuse through business process automation and removing process overlapping and for personal to improve measuring personal process capacity and distinguishing process weak points.

• Journal of the Korea Society for Simulation
• /
• v.27 no.4
• /
• pp.47-60
• /
• 2018

Today's unmanned technology, which is being used in various industries, is expected to be able to make autonomous judgements as autonomous technology matures, in the long run aspects. In order to improve the usability of unmanned system in the military field, it is necessary to develop a technique for systematically and quantitatively analyzing the efficiency and effectiveness of the unmanned system by means of a substitute for the tasks performed by humans. In this paper, we propose the method of representing rule-based tactical behavior and modeling manned and unmanned reconnaissance agents that can effectively analyze the path alternatives which is required for the future armored cavalry to establish a reconnaissance mission plan. First, we model the unmanned ground vehicle, small tactical vehicle, and combatant as an agent concept. Next, we implement the proposed agent behavior rules, e.g., maneuver, detection, route determination, and combatant's dismount point selection, by NetLogo. Considering the conditions of maneuver, enemy threat elements, reconnaissance assets, appropriate routes are automatically selected on the operation area. It is expected that it will be useful in analyzing unmanned ground system effects by calculating reconnaissance conducted area, time, and combat contribution ratio on the route.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2592-2594
• /
• 2004

본 연구에서는 갈수록 늘어나는 이메일 문서의 관리를 효율적으로 하기 위한 방법으로 새로운 메일이 도착했을 때 해당 카테고리를 추천받아 사용자가 직접 최적의 분류를 할 수 있는 이메일 추천 에이전트 시스템을 제안한다. 이메일 문서들의 카테고리별 분류 및 해당 폴더 저장에서 핵심이 될 수 있는 정확한 분류를 위해 동적 임계치를 이용한 베이지안 학습 알고리즘을 적용하였으며, 또한 주요 모듈 부분을 확장성과 재 사용성을 위해 컴포넌트화 하였다.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.543-545
• /
• 1998

Robotic soccer is multi-agent system playing soccer game under given rule. This system consists of three mobile robots, vision sensor, action decision module, action execution module and communication module. This paper presents new action decision method using multi-layer neural networks.