基于遗传算法的网络拥塞控制新策略  

A New Network Congestion Control Strategy Based on Generic Algorithm

作　　者：陆锦军[1] 王执铨[2] 戴跃伟[2] 孙金生[2] 

机构地区：[1]南通职业大学现代教育技术中心,江苏南通226007 [2]南京理工大学自动化学院,江苏南京210094

出　　处：《南通职业大学学报》2007年第2期70-75,共6页Journal of Nantong Vocational University

基　　金：国家自然科学基金(60374066);江苏省自然科学基金(BK2004132);江苏省现代教育技术研究"十一五"规划课题(2007-R-6145)

摘　　要：推导了基于流体流理论的网络简化模型,并基于该模型将遗传算法应用于PID控制器参数优化,定义了一个综合调节时间、上升时间、超调量、系统误差等动静态性能指标函数,在给定的参数空间进行组合优化搜索,迅速求得使性能指标优化函数极小化的一组PID控制器参数,而将PID控制器应用于网络主动队列管理系统中。仿真结果表明,在大时滞和突发业务流的冲击两种情况下,该方法设计的控制器的动静态性能优于RED、PI算法。In this paper, simplified network model based on fluid flow theory is derived, and based on this model, an improved algorithm, i.e. Generic Algorithm is applied to optimize PID controller parameters. Then a new performance function including the system adjusting time, rise time,overshoot, steady state error is defined. This model can fast calculate a group of PID controller parameters that minimize the evaluation function by searching in the given controller parameter area, and then the PID controller can be applied to AQM system. The simulation experimental results show that under the two conditions of large time delay and sudden business flow, the dynamic state and steady state performances of the proposed algorithm are obviously superior to those of the existing RED and PI algorithms.

关 键 词：主动队列管理 网络拥塞 PID控制 遗传算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]