建筑工业化发展的多群体演化博弈与仿真研究

新型建筑工业化具有高质量、低消耗、可循环发展等特征，其推广已上升到国家战略层面。利用演化博弈方法，建立“政府-开发商-银行” 的三方动态演化博弈模型，进行各博弈主体策略的演化稳定性分析，并针对初始状态、奖惩力度、借贷风险和开发成本等对演化结果的影响进行动态仿真。在此基础上， 考虑开发商群体的网络拓扑特征对演化真实性的影响，引入复杂网络理论， 以无标度网络为载体描述开发商个体的连接偏好和决策机制，构建政府监管下的建筑工业化扩散模型，并通过仿真深入研究相关因素对扩散深度的影响作用，最后结合仿真结果给出相应对策建议。     

Leader-following consensus of fractional-order multi-agent systems via adaptive control

This article focuses on the consensus problem of leader-following fractional-order multi-agent systems (MASs) with general linear and Lipschitz nonlinear dynamics. First, the distributed adaptive protocols for linear and nonlinear fractional-order MASs are constructed, respectively. We allow the control coupling gains to be time varying for each agent. Moreover, the adaptive modification schemes for the control gain are designed, which renders smaller control gains and thus requires smaller amplitude on the control input without sacrificing consensus convergence. Second, based on fractional-order Lyapunov stability theorem and Barbalat's lemma, two novel sufficient conditions in terms of linear matrix inequalities are provided to ensure that the leader-following consensus can be obtained in the case for any undirected connected communication graph. Furthermore, we show that the proposed algorithm also works for consensus of agents with intrinsic Lipschitz nonlinear dynamics. As a result, the proposed framework requires no global information and thus can be implemented in a fully distributed manner. Finally, the numerical simulations are given to demonstrate the effectiveness of obtained the theoretical results.     

Controllability and observability of multi-agent systems with heterogeneous and switching topologies

ABSTRACT

This paper focuses on controllability and observability of multi-agent systems with heterogeneous and switching topologies, where the first- and the second-order information interaction topologies are different and switching. First, based on the controllable state set, a controllability criterion is obtained in terms of the controllability matrix corresponding to the switching sequence. Next, by virtue of the subspace sequence, two necessary and sufficient algebraic conditions are established for controllability in terms of the system matrices corresponding to all the possible topologies. Furthermore, controllability is considered from the graphic perspective. It is proved that the system is controllable if the union graph of all the possible topologies is controllable. With respect to observability, two sufficient and necessary conditions are derived by taking advantage of the system matrices and the corresponding invariant subspace, respectively. Finally, some simulation examples are worked out to illustrate the theoretical results.     

When Does Communication Learning Need Hierarchical Multi-Agent Deep Reinforcement Learning

Abstract

Multi-agent systems need to communicate to coordinate a shared task. We show that a recurrent neural network (RNN) can learn a communication protocol for coordination, even if the actions to coordinate are performed steps after the communication phase. We show that a separation of tasks with different temporal scale is necessary for successful learning. We contribute a hierarchical deep reinforcement learning model for multi-agent systems that separates the communication and coordination task from the action picking through a hierarchical policy. We further on show, that a separation of concerns in communication is beneficial but not necessary. As a testbed, we propose the Dungeon Lever Game and we extend the Differentiable Inter-Agent Learning (DIAL) framework. We present and compare results from different model variations on the Dungeon Lever Game.     

DCOP FOR SMART HOMES: A CASE STUDY

The aim of this article is to bring forth the issue of integrating the services provided by intelligent artifacts in Ambient Intelligence applications. Specifically, we propose a Distributed Constraint Optimization procedure for achieving a functional integration of intelligent artifacts in a smart home. To this end, we employ Adopt-N , a state-of-the-art algorithm for solving Distributed Constraint Optimization Problems (DCOP). This article attempts to state the smart home coordination problem in general terms, and provides the details of a DCOP-based approach by describing a case study taken from the RoboCare project. More specifically, we show how (1) DCOP is a convenient metaphor for casting smart home coordination problems, and (2) the specific features which distinguish Adopt-N from other algorithms for DCOP represent a strong asset in the smart home domain.     

基于能力拍卖和多Agent的综合生产计划分布式建模及求解

把拍卖和市场理念引入到生产计划的求解过程中,结合多Agent理论,对大规模生产系统按生产单元建立分布式模型.各个生产单元看作相对独立核算的经济实体,其目标是实现自身利益最大化.当生产能力足够时,按照需求进行生产;当生产能力不足以完全满足需求时,紧缺生产资源的持有者按照单位能力获得最大收益的原则进行生产竞价与拍卖,实现了各个生产单元的分布式自主协商决策,并设计了求解算法.算例研究证明该方法的可操作性和求解的有效性.     

基于多智能体的数控机床资源共享技术研究

以数控铣床为对象，应用多智能体技术，以解决传统的资源共享所面lI缶的透明度低和效率低下的问题。首先，在分析功能模型的基础上，提出并实现了资源共享的四层网络拓扑结构；其次，构造了面向设备资源共享功能的智能体信息流模型，以实现四层结构之间的交互；其三，定义了智能体状态函数，并以此为依据，建立了智能体协商机制。所开发的原型系统表明，以上成果有效地提高了数控机床资源共享的透明度和效率。     

在线安全预警和决策支持系统的软件构架与实现

安全预警和决策支持（EWSC）系统作为未来控制中心自动化系统的重要功能，一方面需要对能量管理系统（EMS）成熟功能进行封装，另一方面需要适应自动化系统功能演变的需要。提出了一种基于多代理系统（MAS）的软件开发范式，用于开发EWSC系统的软件构架。该系统具有一个松散、开放的可插入式结构。其中核心框架是负责系统通信和任务调度的协调层，是相对固定的;其余部分为独立模块，由一系列相对独立的决策分析和人机表达智能体组成，可以独立开发，方便地嵌入系统。在该框架下系统各个模块层次分明，具有很强的解耦性，并且可以实现把历史遗留系统集成到新的环境中。基于文中所提出的软件构架的在线EWSC系统已在某省级电网投运。     

具有时变时滞耦合的二阶多主体系统的编队控制

多主体系统的编队控制是一类重要的网络协同控制问题.研究了在有向连接拓扑结构下,具有时变时滞耦合的二阶多主体系统的编队控制问题.通过一种多层领导机制的框架建模,得到了时不变编队、时变编队和时变轨迹追踪3种编队问题的充分性条件,并证明了各种预期队列是以指数的收敛速度形成的.数值仿真进一步验证了理论结果的正确性,为该理论在实际中应用起到指导作用.     

面向动态任务合作求解的联盟模型

多Agent系统中,Agent间通过形成联盟达到提高任务求解能力,获取更多收益的目的。主要关注联盟模型的改进和联盟形成阶段的改进,基于ARG(agent,role,group)元模型和学习机制提出了一种采用角色和学习机制的新联盟模型CLAR(coalition model based on learnin gagent and role);在采用合同网协议的CLAR联盟模型中提出了两阶段联盟形成机制;通过捕食者问题实验验证了角色和学习机制的作用,以及两阶段联盟形成机制在减少通讯代价上的作用。