基于粒子群优化算法和博弈论的网络学习控制系统带宽调度  

Bandwidth scheduling of a networked learning control system using particle swarm optimization and the game theory

作　　者：严翔[1] 李洪波[2] 王立德[1] 申萍[1] 

机构地区：[1]北京交通大学电气工程学院,北京100044 [2]清华大学计算机科学与技术系,北京100084

出　　处：《北京科技大学学报》2014年第7期979-985,共7页Journal of University of Science and Technology Beijing

基　　金：中央高校基本科研业务费资助项目(E11JB00310;E12JB00140);国家重点基础研究发展计划资助项目(2012CB821206);国家自然科学基金资助项目(61004021;61174069;61004023);北京市自然科学基金资助项目(4122037)

摘　　要：研究了双层网络学习控制系统的带宽调度优化问题.为了合理分配子系统的带宽,引入了网络定价体系和动态带宽调度方法,建立了非合作博弈模型,从而将网络控制系统的网络资源分配问题转换为非合作博弈竞争模型下的Nash均衡点求解问题.在此基础上,采用粒子群优化算法得到此框架下的纳什均衡解,并进一步给出了网络控制系统的时间片调度方法.仿真结果表明了所提方法的有效性.The optimal bandwidth scheduling problem was studied for a two-layer networked learning control system （ NLCS） . A dynamic bandwidth scheduling methodology based on the network pricing mechanism was proposed to allocate the bandwidth for each subsystem, so the network resource allocation problem was transformed into the solution of the Nash equilibrium with a non-cooperation game model. Under this framework, particle swarm optimization （ PSO） was used to obtain the Nash equilibrium for NLCS, and the time slice scheduling method was also provided. Simulation results were given to demonstrate the effectiveness of the proposed approach.

关 键 词：网络控制系统 定价 博弈论 粒子群优化算法 

分 类 号：TP302.7[自动化与计算机技术—计算机系统结构]