• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.4
• /
• pp.188-196
• /
• 2001

This paper presents and efficient algorithm for the loss minimization by automatic sectionalizing switch operation in distribution systems. Ant colony algorithm is multi-agent system in which the behaviour of each single agent, called artificial ant, is inspired by the behaviour of real ants. Ant colony algorithm is suitable for combinatiorial optimization problem as network reconfiguration because it use the long term memory, called pheromone, and heuristic information with the property of the problem. The proposed methodology with some adoptions have been applied to improve the computation time and convergence property. Numerical examples demonstrate the validity and effectiveness of the proposed methodology using a KEPCO's distribution system.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.157-163
• /
• 2023

Recently, as businesses and data types become more complex and diverse, efficient data analysis using machine learning is required. However, since communication in the cloud environment is greatly affected by network latency, data analysis is not smooth if information delay occurs. In this paper, SPT (Safe Proper Time) was applied to the cluster-based machine learning data analysis agent proposed in previous studies to solve this delay problem. SPT is a method of remotely and directly accessing memory to a cluster that processes data between layers, effectively improving data transfer speed and ensuring timeliness and reliability of data transfer.

• The Journal of Korea Robotics Society
• /
• v.19 no.3
• /
• pp.281-286
• /
• 2024

This paper describes the solution method of Team AIRLAB used to participate in the League of Robot Runners Competition which tackles the problem of Lifelong Multi-agent Pathfinding (MAPF). In lifelong MAPF, multiple agents are tasked to navigate to their respective goal locations where new goals are consecutively revealed once they reach initial goals. The agents need to avoid collisions and deadlock situations while they navigate to perform tasks. Our method consists of (i) Puzzle Heuristics, (ii) MAPF-LNS2, and (iii) RHCR. The Puzzle Heuristics is our own algorithm that generates a compact heuristic table contributing to reduce memory consumption and computation time. MAPF-LNS2 and RHCR are state-of-the-art algorithms for MAPF. By combining these three algorithms, our method can improve the efficiency of paths for all agents significantly.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.171-176
• /
• 2020

Reinforcement learning is a well-known method for training an artificial software agent for a video game. Even though many reinforcement learning algorithms have been proposed, their performance was varies depending on an application area. This paper compares the performance of the algorithms when we train our reinforcement learning agent for a 2D racing game. We defined performance metrics to analyze the results and plotted them into various graphs. As a result, we found ACER (Actor Critic with Experience Replay) achieved the best rewards than other algorithms. There was 157% gap between ACER and the worst algorithm.

• Journal of the Korea Society for Simulation
• /
• v.17 no.2
• /
• pp.83-90
• /
• 2008

We introduce the coordination among the intrusion detection agents by BBA(BlackBoard Architecture) that belongs to the field of distributed artificial intelligence. The system which uses BBA for the coordination can be easily expanded by adding new agents and increasing the number of BB(BlackBoard) levels. Several simulation tests performed on the targer network will illustrate our techniques. And this paper applies PBN(Policy-Based Network) to reduce the false positives that is one of the main problems of IDS. The performance obtained from the coordination of intrusion detection agent with PBN is compared against the corresponding non PBN type intrusion detection agent. The application of the research results lies in the experimentation of the various security policies according to the network types in selecting the best security policy that is most suitable for a given network.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.4
• /
• pp.161-167
• /
• 2002

For the purpose of applying to micro-actuator, thermal properties and displacement of electrostrictive polyurethane(PU) elastomers have been measured. In order to understand an effect of PU component, crosslinking agent are controlled by 0.5 wt% and 1 wt%. DMPA and anther chain extenders were used. PU sample that chain extenders are DMPA is added NaOH for comprehension of effect of ionic groups. The deposited electrode sire on PU films is equal to acrylic holder size when the displacement was measured. Dynamic response according to frequency, displacement and recovery time according to PU thickness were measured. 1 wt% crosslinking agent contents PU samples have higher displacement and lower recovery time than 0.5 wt% crosslinking agent contents PU. If the PU thickness is increased, the actuating voltage for generating of same displacement is increased, too.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.2
• /
• pp.41-48
• /
• 2021

A smart tuned mass damper (TMD) is widely studied for seismic response reduction of various structures. Control algorithm is the most important factor for control performance of a smart TMD. This study used a Deep Deterministic Policy Gradient (DDPG) among reinforcement learning techniques to develop a control algorithm for a smart TMD. A magnetorheological (MR) damper was used to make the smart TMD. A single mass model with the smart TMD was employed to make a reinforcement learning environment. Time history analysis simulations of the example structure subject to artificial seismic load were performed in the reinforcement learning process. Critic of policy network and actor of value network for DDPG agent were constructed. The action of DDPG agent was selected as the command voltage sent to the MR damper. Reward for the DDPG action was calculated by using displacement and velocity responses of the main mass. Groundhook control algorithm was used as a comparative control algorithm. After 10,000 episode training of the DDPG agent model with proper hyper-parameters, the semi-active control algorithm for control of seismic responses of the example structure with the smart TMD was developed. The simulation results presented that the developed DDPG model can provide effective control algorithms for smart TMD for reduction of seismic responses.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.65-70
• /
• 2023

The "information roadway" will give us an impact of new PC based assignments and administrations, yet the unusualness of this new condition will ask for another style of human-PC association, where the PC transforms into a sharp, dynamic and customized partner. Interface administrators are PC programs that use Artificial Intelligence frameworks to give dynamic help to a customer with PC based errands. Operators drastically change the present client encounter, through the similitude that a specialist can go about as an individual collaborator. The operator procures its capability by gaining from the client and from specialists helping different clients. A couple of model administrators have been gathered using this methodology, including authorities that give customized help with meeting planning, electronic mail taking care of, Smart Personal Assistant and choice of diversion. Operators help clients in a scope of various ways: they perform assignments for the client's sake; they can prepare or educate the client, they enable diverse clients to work together and they screen occasions and methods.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.265-271
• /
• 2001

It is highly for the research in artificial intelligence area to be able to manage knowledge as human beings do. One of the fantastic natures that human knowledge management systems have is being active. Human beings actively manage their knowledge, solve conflicts and make inference. It makes a major difference from artificial intelligent systems. This paper focuses on the discussion of the features of that human knowledge systems, which underlies the active nature. With the features extracted, further research can be done to construct a suitable infrastructure to facilitate these features to build a man-made active knowledge management system. This paper proposed 10 features that human beings follow to maintain their knowledge. We believe it will advance the evolution of active knowledge management systems by realizing these features with suitable knowledge representation/decision models and software agent technology.

• The Journal of Information Systems
• /
• v.25 no.4
• /
• pp.23-36
• /
• 2016

Purpose Recently, many researchers have paid much attention to the Artificial Intelligence fields of GVGP, PCG. The paper suggests that the improved MCTS algorithm to apply for the framework can generate better AI agent. Design/methodology/approach As noted, the MCTS generate magnificent performance without an advanced training and in turn, fit applying to the field of GVGP which does not need prior knowledge. The improved and modified MCTS shows that the survival rate is increased interestingly and the search can be done in a significant way. The study was done with 2 different sets. Findings The results showed that the 10 training set which was not given any prior knowledge and the other training set which played a role as validation set generated better performance than the existed MCTS algorithm. Besed upon the results, the further study was suggested.