检索结果-南通市图书馆

Computers, Materials & Continua 2020年第10期65卷 865-878页

作者： Fuquan Huang Zijun Liu Tinghuang Wang Haitai Zhang Tony Yip Shenzhen Power Utility Co. Ltd.Shenzhen518000China Shandong Kehui Electric Power Automation Co. Ltd.Zibo255000China Kehui International Ltd. Studio 206Mill Studio Business CentreCrane MeadWareHertsSG129PYUK

In order to quickly and accurately locate the fault location of the distribution network and increase the stability of the distribution network,a fault recovery method based on multi-objective optimization algorithm is *** optimization of the power distribution network fault system based on multiagent technology realizes fast recovery of multi-objective fault,solve the problem of network learning and parameter adjustment in the later stage of particle swarm optimization algorithm falling into the local extreme value dilemma,and realize the multi-dimensional nonlinear optimization of the main grid and the auxiliary *** system proposed in this study takes power distribution network as the goal,applies fuzzy probability algorithm,simplifies the calculation process,avoids local extreme value,and finally realizes the energy balance between each power *** results show that the multi-agent Technology enjoys priority in restoring important load,shortening the recovery time of power grid balance,and reducing the overall line loss rate of power ***,the power grid fault self-healing system can improve the safety and stability of the important power grid,and reduce the economic loss rate of the whole power grid.

关键词： multi agent technology power distribution network fault self-healing

Containment control of multi-agent systems with nonvanishing disturbance via topology reconfiguration

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第7期64卷 250-252页

作者： Qihe SHAN Fei TENG Tieshan LI C.L.Philip CHEN Navigation College Dalian Maritime University College of Information Science and Engineering Northeastern University

Dear editor,multi-agent systems (MASs) are ubiquitous in natural as well as artificial systems. Over the past several decades, an increasing number of researchers have devoted attention to distributed cooperative cont... 详细信息

关键词： multi agent nonvanishing disturbance topology reconfiguration containment control convex parameters

基于multi agent的航路容量评估研究

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

基于Multi Agent的航路容量评估研究

作者：龚粮中国民用航空飞行学院

学位级别：硕士

我国民航发展过程中一直受到基础设施、空域航路资源、人员素质和管理水平等限制,使得空中交通流量的需求与空域航路容量之间的矛盾日益突出,航路拥堵已经成为一种普遍现象。因此,随着我国民用航空不断发展和航班数量的增加,研究如何快... 详细信息

我国民航发展过程中一直受到基础设施、空域航路资源、人员素质和管理水平等限制,使得空中交通流量的需求与空域航路容量之间的矛盾日益突出,航路拥堵已经成为一种普遍现象。因此,随着我国民用航空不断发展和航班数量的增加,研究如何快速、有效地评估航路容量,提高航路使用效率。在我国现有的空域结构与既定航路条件下,经济有效地解决航路拥堵的办法是对未来的空域航路容量进行科学合理的客观评估,以便合理地制订航班时刻、航班计划,减少航班延误。本文基于我国空域航路的实际运行现状,研究和分析了国内外相关航路容量评估模型方法,结合国内外相关multi agent技术研究现状,采用multi agent相关理论技术结合航路容量模型方法进行了航路容量评估研究。首先,研究航路容量评估方法,得到论文中的航路容量评估模型;然后,研究国内外multi agent理论,以解决传统航路容量评估仿真中智能性差和灵活性不足的缺点;再将航路容量评估模型与方法特点和multi agent理论结合,构建基于multi agent的航路容量评估模型方法;最后,对航路容量评估模型,采用C#语言在Visual Studio平台上进行计算机程序设计。从而,提升空域航路使用效率,为我国航路容量评估提供理论参考,促进航班时刻有效管理、制定,减少航班延误,增加航空公司收益。

关键词：航路 multi agent 容量评估

AdvCommNet: Enhancing multi-agent Interaction in Deep Reinforcement Learning Systems

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

AdvCommNet: Enhancing Multi-Agent Interaction in Deep Reinfo...

Pass-ball trainning based on genetic reinforcement learning

第43届中国控制会议

作者： Libin Chen Luyao Wang Qian Li Yuqun Wang Hongfu Liu College of Intelligence Science and Technology National University of Defense Technology College of Systems Engineering National University of Defense Technology

This paper addresses the challenge of efficient information processing in multi-agent systems by introducing an innovative approach, AdvCommNet. Building on the foundation of deep reinforcement learning, AdvCommNet incorporates advanced kernel functions such as softmax and sigmoid to optimize information interaction and highlight the significance of crucial data. The effectiveness of AdvCommNet is demonstrated through extensive experiments in various simulated multi-agent environments. Our results show a significant improvement over the traditional CommNet algorithm in terms of information processing efficiency and collaborative decision-making capabilities. This research not only addresses limitations in complex interactive scenarios found in existing methodologies but also opens new avenues for future advancements in multi-agent systems.

关键词： multi agent markov decision process communication mechanism deep reinforcement learning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2001年第3期8卷 279-282页

作者：褚海涛洪炳熔 Dept. of Comp. Sci. and Eng. Harbin Inst. of Technol. Harbin 150001 China

Introduces a mixture genetic algorithm and reinforcement learning computation model used for independent agent learning in continuous, distributive, open environment, which takes full advantage of the reactive and robust of reinforcement learning algorithm and the property that genetic algorithm is suitable to the problem with high dimension,large collectivity, complex environment, and concludes that through proper training, the result verifies that this method is available in the complex multi agent environment.

关键词： reinforcement genetic multi agent genetic reinforcement learning

维普期刊数据库

Heterogeneous Robots Allocation and Selection in Robocup Environment

在线全文

学校读者我要写书评

暂无评论

International Journal of Systems and Control

International Journal of Systems and Control 2006年第1期 40-46页

作者： MIAO Kehua ,LI Maoqing Department of Automation Xiamen University Xiamen City, P.R.China

Role assignment according to robot features is a crucial step in the coordination of multiple heterogeneous robots. This paper presents a strategy to pick heterogeneous players and form a soccer team in the RoboCup simulation environment, which is a multi-robot coordination research platform. Using fuzzy evaluation and fuzzy inference, we identify the most suitable role in a soccer team for a given heterogeneous robot. In games, the team based on this strategy showed significantly better performance compared to a team based on the previous hand-tuning solution.

关键词： RoboCup multi agent fuzzy comprehensive simulation

Study on optimization of agent initial positions in land combat simulation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Progress in Natural Science:Materials International 2004年第3期 65-69页

作者： WU Chunguo 1,2 , LIANG Yanchun* 1, 2 , LEE Heow Pueh 2, LU Chun 2 and YANG Xiaowei 3,4 (1. College of Computer Science and Technology, Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun 130012, China 2. Institute of High Performance Computing, Singapore 117528, Singapore 3. Department of Applied Mathematics, South China University of Technology, Guangzhou 510640, China 4. Centre for ACES, Department of Mechanical Engineering, National University of Singapore, 119260, Singapore)

The use of computational intelligence based techniques in the optimization of agent initial positions in land combat simulations is studied. A novel method for the reduction of support vectors in the support vector machine (SVM) is presented. The optimization on the width of the Gaussian kernel function and the combination of the SVM with the radial basis function neural network are performed in the proposed method. Simulation results show that the proposed method can improve the running efficiency drastically compared with that using the traditional SVM with the same precision. We also summarize and present some experiences and trends in the study on the optimization problem in land combat simulation.

关键词： multi agent support vector machine radial basis function genetic algorithm regression.

Recognition of robot-soccer in point of information fusion

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2001年第3期8卷 287-289页

作者：张彦铎姚峰 Dept. of Computer Sci. Engineering Wuhan Institute of Chemical Technology

Summary of typical information fusion systems, synthesis analysis of Robot Soccer’s architecture, recognition of its characteristic and key technique are given. The result is prompted that Robot Soccer can be treated... 详细信息

关键词： information fusion robot soccer multi agent

维普期刊数据库