用改进的遗传算法设计交换式工业以太网拓扑  

Using Improved Genetic Algorithms to Design Switched Industrial Ethernet Topology

作　　者：胡晓娅[1] 朱德森[1] 汪秉文[1] 

机构地区：[1]华中科技大学控制科学与工程系,湖北武汉430074

出　　处：《计算机工程与科学》2007年第9期9-11,33,共4页Computer Engineering & Science

基　　金：高等学校博士点专项基金资助项目(20020487023)

摘　　要：本文提出了使用改进的遗传算法来优化和设计工业控制网络的具体方法。针对交换式工业以太网的冗余拓扑结构和数据通信特点,将网络拓扑设计问题等价为一个多目标优化问题,即一方面要减少子网间通信量,同时需要平衡各个子网的通信负荷;此外,交换机物理条件的限制也为该优化问题设置了约束条件。在设计具体的遗传算法时,从编码方案、交叉概率和变异概率等三个方面进行改进,克服了基本遗传算法全局搜索能力较差、容易导致局部最优,以及收敛速度和全局收敛性存在矛盾等缺点。最后,仿真结果验证了该改进算法的有效性。This paper proposes an approach which uses improved genetic algorithms to optimize and design industrial control networks. With the redundant topology structure and the communication characteristics of switched industrial Ethernet, the problem of network partitioning ~s analyzed to be equivalent to a multi-objective optimization problem： topology optimization should reduce the inter-network communications, and simultaneously allow the network traffic to be evenly distributed over all sub-networks. Moreover, the switch＇s capability must be respected, which sets constraints for the optimization problem. In the improved genetic algorithms, the coding strategy, the probability of crossover and the probability of mutation are improved, which conquers the shortcomings of premature convergence in simple genetic algorithms. The simulation result shows that the algorithm is effective

关 键 词：交换式工业以太网 遗传算法 拓扑设计 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]