• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.5
• /
• pp.49-57
• /
• 2008

In this paper, we suggested a methodology that can be used by an agent to learn models of other agents in a multi-agent system. To construct these model, we used influence diagram as a modeling tool. We present a method for learning models of the other agents at the decision nodes, value nodes, and chance nodes in influence diagram. We concentrated on learning of the other agents at the value node by using neural network learning technique. Furthermore, we treated anti-air units in anti-air defense domain as agents in multi. agent system.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.27-28
• /
• 2007

본 논문은 배전계통을 운영함에 있어서 배전자동화 시스템의 가장 중요한 기능인 정전복구 기능에 대해서 현재의 중앙집중 방식에서 분산형으로 보다 효율적인 처리를 위한 알고리즘을 제안하였다. 분산형으로 처리하기 위하여 단말장치들을 Intelligent 기능에 능동 자율학습 기능을 보완할 수 있는 Multi-Agent 기법을 알고리즘에 도입하였다. 기존의 agent 기법을 응용한 연구는 적용 대상이 불분명한데 반해 본 논문에서는 적용 대상도 분명하고 현재 계통에도 바로 적용이 가능한 알고리즘을 제안하였다. 또한 Multi-Agent 기반 분산형 정전복구 시스템의 약점이라 할 수 있는 통신망 보안에 대해서 위협사례들을 분석하고, 이 위협들에 대한 보안알고리즘 적용방안을 제시하였다. 본 논문에서 제시한 알고리즘들을 PC 기반으로 예제계통을 꾸며 그 성능을 입증하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1735-1740
• /
• 2005

In this paper, ways of improving the performances of roundabouts under the assumption that the Advanced Vehicle System is proposed. The situation on a road contains uncertainty and complexity caused by different vehicles having different directions and time-varying traffic flow. This sort of system with high uncertainty is called Multi Agent System (MAS). The MAS is a collective system, including numbers of agents and performs high diversity of the configuration as well as it has nonlinear property and complexity. Hence it is difficult to analyze and control the multi-agent system. A roundabout can be considered as an MAS with numbers of moving vehicles. So it must be difficult to use a centralized control technique to all vehicles in an intersection. Therefore, to improve the performances of roundabouts, multi-agents flow control algorithm for vehicles in Roundabouts using 'self-organization' technique is proposed.

• KIEE International Transactions on Power Engineering
• /
• v.2A no.3
• /
• pp.89-94
• /
• 2002

In this paper, a protection system using a Multi-Agent concept for power distribution networks is proposed. Every digital over current relay(OCR) is developed as an agent by adding its own intelligence, self-tuning and communication ability. The main advantage of the Multi-Agent concept is that a group of agents work together to achieve a global goal which is beyond the ability of each individual agent. In order to cope with frequent changes in the network operation condition and faults, an OCR agent, suggested in this paper, is able to detect a fault or a change in the network and find its optimal parameters for protection in an autonomous manner considering information of the whole network obtained by communication between other agents. Through this kind of coordination and information exchanges, not only a local but also a global protective scheme is completed. Simulations in a simple distribution network show the effectiveness of the suggested protection system.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.9-17
• /
• 2021

In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.703-704
• /
• 2008

Multi-agent technologies are essential in realizing the upcoming ubiquitous environment. In the multi-agent environment, each agent has its own set of services and stores these services in the service repository of the multi-agent system. By using this repository, the user can retrieve the most appropriate service. In this paper, we propose an efficient service repository architecture that can improve the existing agent-based service discovery.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.511-514
• /
• 1998

This paper proposes efficient methods that integrate and execute local plan rules of task agents in a multi-agent environment. In these methods, each agent's plan rules are represented in a network structure, and these networks are then collected by a single task agent to build a integrated domain network, which is exploited to achieve the goal. Agent problem solving by using the domain network enables a concurrent execution of plan rules that are sequential in nature.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.2
• /
• pp.29-36
• /
• 2023

Reinforcement learning (RL) is widely applied to various engineering fields. Especially, RL has shown successful performance for control problems, such as vehicles, robotics, and active structural control system. However, little research on application of RL to optimal structural design has conducted to date. In this study, the possibility of application of RL to structural design of reinforced concrete (RC) beam was investigated. The example of RC beam structural design problem introduced in previous study was used for comparative study. Deep q-network (DQN) is a famous RL algorithm presenting good performance in the discrete action space and thus it was used in this study. The action of DQN agent is required to represent design variables of RC beam. However, the number of design variables of RC beam is too many to represent by the action of conventional DQN. To solve this problem, multi-agent DQN was used in this study. For more effective reinforcement learning process, DDQN (Double Q-Learning) that is an advanced version of a conventional DQN was employed. The multi-agent of DDQN was trained for optimal structural design of RC beam to satisfy American Concrete Institute (318) without any hand-labeled dataset. Five agents of DDQN provides actions for beam with, beam depth, main rebar size, number of main rebar, and shear stirrup size, respectively. Five agents of DDQN were trained for 10,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases. This study shows that the multi-agent DDQN algorithm can provide successfully structural design results of RC beam.

• Proceedings of the KIEE Conference
• /
• 2002.07a
• /
• pp.193-195
• /
• 2002

In this paper, a communication module is proposed to be applied to communication between over current relay (OCR) agents in multi agent protection system. A multi agent system can achieve a global goal beyond the ability of each individual agent by working together, in which it is the prerequisite for each agent to be able to exchange or share information or processing status with other agent. The proposed communication module is purposed to enable not only each agent to bring about its own goal, but also the whole protective system to provide much improved coordinated protection. It is applied to a self adaptive protection system for a distribution network using multi agent concept to show its effectiveness.

• Journal of information and communication convergence engineering
• /
• v.20 no.3
• /
• pp.181-188
• /
• 2022

An intelligent distributed multi-agent system (IDMS) using reinforcement learning (RL) is a challenging and intricate problem in which single or multiple agent(s) aim to achieve their specific goals (sub-goal and final goal), where they move their states in a complex and cluttered environment. The environment provided by the IDMS provides a cumulative optimal reward for each action based on the policy of the learning process. Most actions involve interacting with a given IDMS environment; therefore, it can provide the following elements: a starting agent state, multiple obstacles, agent goals, and a cluttered index. The reward in the environment is also reflected by RL-based agents, in which agents can move randomly or intelligently to reach their respective goals, to improve the agent learning performance. We extend different cases of intelligent multi-agent systems from our previous works: (a) a proposed environment-clutter-based-index for agent sub-goal selection and analysis of its effect, and (b) a newly proposed RL reward scheme based on the environmental clutter-index to identify and analyze the prerequisites and conditions for improving the overall system.