基于CGA算法的主动队列管理新策略  

New Active Queue Management Scheme Based on Composite Genetic Algorithm

作　　者：陆锦军[1,2] 李志权[2] 王执铨[1] 

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

出　　处：《南京理工大学学报》2010年第4期487-491,507,共6页Journal of Nanjing University of Science and Technology

基　　金：国家自然科学基金（60974016）; 江苏省自然科学基金（BK2008188）; 江苏省“六大人才高峰”资助项目（07-E-13）; 江苏省现代教育技术研究“十一.五”规划课题（2007-R-6145）; 南通市科技应用研究项目（K2007004）

摘　　要：基于流体流理论的网络简化模型,将NSGA-Ⅱ与PGA相结合的复合遗传优化算法应用于PID控制器参数优化,提出了一种多目标PID优化设计方法——在满足系统鲁棒性的前提下,以超调量、上升时间和调整时间最小作为多目标优化的子目标,并用复合遗传算法对其求解。该算法求得的Pareto最优解分布均匀,收敛性和鲁棒性好,根据网络主动队列管理控制系统的要求在解集中选择满意解。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GA、SPSO、QDPSO算法的优化结果。A simplified network model based on fluid flow theory is derived in this paper,and based on this model,an improved algorithm,that is,composite genetic optimization algorithm of combining NSGA-Ⅱ with PGA is applied to optimize PID controller parameters.A multi-objective PID optimization design method is proposed.When the system robustness is satisfied,the minimum of overshoot,rise time and adjusting time is taken as the sub-object of multi-objective optimization,and through this composite genetic algorithm,the objectives are gained.The Pareto optimal solutions obtained by this algorithm distributes evenly,and has good convergent and robust attributs.According to the requirement of the networked Active Queue Management control system,a satisfying solution from the solution set is chosen.The simulation experimental results show that under the two conditions of large time delay or sudden business flow,the dynamic state and steady state performances of the proposed algorithm are obviously superior to those of the existing GA,SPSO and QDPSO algorithms.

关 键 词：主动队列管理 网络拥塞 PID控制 复合遗传算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]