A distributed services based conference planner application using software agents, grid services and web services

This demonstration highlights the applications of our research work i.e. second generation (Scalable Fault Tolerant Agent Grooming Environment - SAGE) Multi Agent System, Integration of Software Agents and Grid Computing and Autonomous Agent Architecture in the Agent Platform. It is a conference planner application that uses collaborative effort of services deployed geographically wide in different technologies i.e. Software Agents, Grid computing and Web services to perform useful tasks as required. Copyright 2005 ACM.

一个面向异构多UUV协作任务的分层式控制系统

针对异构多UUV协作任务,提出了基于多智能体系统的分层式体系结构(MAHA).在个体层面,将UUV智能体的思维状态分为社会心智和个体心智两个层次分别实现,更加符合人类社会协作模式;在群体层面,提出了复杂海洋环境下UUV群体结构的评价准则,并据此将MAHA与现有结构进行了对比分析.此外,利用面向对象的Petri网理论建立了系统的协作模型,有效降低了系统建模的复杂性.最后,水下多目标搜索使命的实例研究表明,MAHA能够保证异构UUV之间进行有效的协作.

基于KQML语言的合同网协议模型及实现

本文首先分析了基于 KQML会话的 Multi- Agent系统 ( MAS)构成及其特点 ,然后提出了基于 CORBA、KQML的合同网协议 ( CNP)系统模型及 Agent通信模型 ,并针对此合同网模型 ,结合调度系统实例分析了其中 KQML语言的形式化表达方式

一个多智能体机器人协作装配系统

介绍了一个基于多智能体概念实现的多机器人协作装配系统——ＭＲＣＡＳ（Ｍｕｌｔｉ－ＲｏｂｏｔＣｏｏｐｅｒａｔｉｖｅＡｓｓｍｂｌｙＳｙｓｔｅｍ）。该系统由组织级计算机、三台工业机器人和一台全方位移动小车（ＯＤＶ）组成，采用分层递阶体系结构。利用ＭＲＣＡＳ系统进行了多机器人协作装配的实验：在ＯＤＶ装配平台上，四台机器人合作装配一个大型桁架式工件。该工件具有多种装配构型，但任何一台机器人不能独立完成装配。

协作机器人学的研究现状与发展

随着机器人向系统应用的方向发展，提出了由多机器人构成的群体或社会的组织与控制问题．多机器人协作问题已成为机器人学研究领域的热点之一．其中基于分布式人工智能中多智能体系统理论，研究多机器人协作问题正受到普遍关注．本文对协作机器人学的研究现状进行了综述，并展望了其未来的发展。

分布自主协作式的多机器人系统研究

本文作者在研究多机器人协调的基础上，将多机器人作为一个整体，从系统的角度研究多机器人系统的整体行为和组织结构．以人工智能的多自主体系统为理论基础，以网络通讯和分布数据库为技术基础，设计了多机器人分布自主协作系统的体系结构，提出了实现该系统需要研究的内容和解决的关键技术，介绍了我们在这方面的工作

基于多智能体的制造系统生产控制建模研究

为提高制造系统生产控制的性能,建立了基于多智能体系统的混合控制模型。该模型把生产控制系统分为管理智能体层、单元智能体层和执行智能体层。管理智能体层负责调度和协调各单元智能体,并对所有智能体进行管理;单元智能体层中的各单元智能体间通过公用数据库相互协作;执行智能体对制造系统内的硬件负责,它们根据局部的本地资源信息及当前状态,接收发布的任务,并对其求解。同一层次的智能体之间是分布式结构。采用基于多智能体的混合控制模式,提高了制造系统生产控制的实时性和灵活性。通过激光拼焊生产系统中的试验,验证了该模型的有效性。

Decentralised formation control and stability analysis for cooperative multi-vehicle manoeuvre

Multi-vehicle cooperative formation control problem is an important and typical topic of research on multi-agent system. This paper presents a formation stability conjecture to conceive a new methodology for solving the decentralised multi-vehicle formation control problem. It employs the “extension-decomposition-aggregation” scheme to transform the complex multi-agent control problem into a group of sub-problems which is able to be solved conveniently. Based on this methodology, it is proved that if all the individual augmented subsystems can be stabilised by using any approach, the overall formation system is not only asymptotically but also exponentially stable in the sense of Lyapunov within a neighbourhood of the desired formation. Simulation study on 6-DOF aerial vehicles (Aerosonde UAVs) has been performed to verify the achieved formation stability result. The proposed multi-vehicle formation control strategy can be conveniently extended to other cooperative control problems of multi-agent systems.

Dynamic artificial neural network for electricity market prices forecast

This paper presents an artificial neural network applied to the forecasting of electricity market prices, with the special feature of being dynamic. The dynamism is verified at two different levels. The first level is characterized as a re-training of the network in every iteration, so that the artificial neural network can able to consider the most recent data at all times, and constantly adapt itself to the most recent happenings. The second level considers the adaptation of the neural network’s execution time depending on the circumstances of its use. The execution time adaptation is performed through the automatic adjustment of the amount of data considered for training the network. This is an advantageous and indispensable feature for this neural network’s integration in ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to the market negotiating players of MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).

Self-optimization module for scheduling using case-based reasoning

Metaheuristics performance is highly dependent of the respective parameters which need to be tuned. Parameter tuning may allow a larger flexibility and robustness but requires a careful initialization. The process of defining which parameters setting should be used is not obvious. The values for parameters depend mainly on the problem, the instance to be solved, the search time available to spend in solving the problem, and the required quality of solution. This paper presents a learning module proposal for an autonomous parameterization of Metaheuristics, integrated on a Multi-Agent System for the resolution of Dynamic Scheduling problems. The proposed learning module is inspired on Autonomic Computing Self-Optimization concept, defining that systems must continuously and proactively improve their performance. For the learning implementation it is used Case-based Reasoning, which uses previous similar data to solve new cases. In the use of Case-based Reasoning it is assumed that similar cases have similar solutions. After a literature review on topics used, both AutoDynAgents system and Self-Optimization module are described. Finally, a computational study is presented where the proposed module is evaluated, obtained results are compared with previous ones, some conclusions are reached, and some future work is referred. It is expected that this proposal can be a great contribution for the self-parameterization of Metaheuristics and for the resolution of scheduling problems on dynamic environments.

Complex market integration in MASCEM electricity market simulator

The restructuring that the energy sector has suffered in industrialized countries originated a greater complexity in market players’ interactions, and thus new problems and issues to be addressed. Decision support tools that facilitate the study and understanding of these markets become extremely useful to provide players with competitive advantage. In this context arises MASCEM, a multi-agent system for simulating competitive electricity markets. To provide MASCEM with the capacity to recreate the electricity markets reality in the fullest possible extent, it is essential to make it able to simulate as many market models and player types as possible. This paper presents the development of the Complex Market in MASCEM. This module is fundamental to study competitive electricity markets, as it exhibits different characteristics from the already implemented market types.

Energy and ancillary services joint market simulation

In order to develop a flexible simulator, a variety of models for Ancillary Services (AS) negotiation has been implemented in MASCEM – a multi-agent system competitive electricity markets simulator. In some of these models, the energy and the AS are addressed simultaneously while in other models they are addressed separately. This paper presents an energy and ancillary services joint market simulation. This paper proposes a deterministic approach for solving the energy and ancillary services joint market. A case study based on the dispatch of Regulation Down, Regulation Up, Spinning Reserve, and Non-Spinning Reserve services is used to demonstrate that the use of the developed methodology is suitable for solving this kind of optimization problem. The presented case study is based on CAISO real AS market data considers fifteen bids.

Self-organization for scheduling in agile manufacturing

Agility refers to the manufacturing system ability to rapidly adapt to market and environmental changes in efficient and cost-effective ways. This paper addresses the development of self-organization methods to enhance the operations of a scheduling system, by integrating scheduling system, configuration and optimization into a single autonomic process requiring minimal manual intervention to increase productivity and effectiveness while minimizing complexity for users. We intend to conceptualize real manufacturing systems as interacting autonomous entities in order to build future Decision Support Systems (DSS) for Scheduling in agile manufacturing environments.

Meta-heuristics tunning using CBR for dynamic scheduling

This paper addresses the problem of Biological Inspired Optimization Techniques (BIT) parameterization, considering the importance of this issue in the design of BIT especially when considering real world situations, subject to external perturbations. A learning module with the objective to permit a Multi-Agent Scheduling System to automatically select a Meta-heuristic and its parameterization to use in the optimization process is proposed. For the learning process, Casebased Reasoning was used, allowing the system to learn from experience, in the resolution of similar problems. Analyzing the obtained results we conclude about the advantages of its use.