基于约束多目标免疫算法的多载波卫星通信系统链路支持性优化  

Optimal link supportability of multi-carrier SATCOM systems with constrained nondominated neighbor immune algorithm

作　　者：姜兴龙[1,2] 肖寅[2,3] 梁广[2] 刘会杰[2] 余金培 

机构地区：[1]中国科学院上海微系统与信息技术研究所,上海200050 [2]上海微小卫星工程中心,上海201210 [3]中国科学院上海技术物理研究所,上海200083

出　　处：《红外与毫米波学报》2016年第3期368-376,共9页Journal of Infrared and Millimeter Waves

基　　金：国家自然科学基金(61401278)~~

摘　　要：毫米波通信系统因为带宽宽和易于小型化的特点被广泛应用于卫星通信中,基于提高多载波卫星毫米波通信系统容量的链路支持性优化面临诸多性能指标权衡的难题,如:降低上行EIRP需求,提高转发器功率利用率,增强链路稳健性等,将多目标优化思想引入到毫米波卫星通信系统的支持性优化模型,提出一种约束多目标免疫算法(Constrained Nondominated Neighbor Immune Algorithm,C-NNIA),并进行了相应的建模、仿真和优化.表明该算法可获得优于传统直接求解(Direct Search,DS)算法和基于单目标可变邻域搜索(Variable Neighbourhood Search,VNS)算法的Pareto最优解,且算法具有更好的约束处理能力、多样性保持能力以及快速收敛特性.最后,通过对最优解集的设计变量以及性能度量参数的统计和分析,获得了具有指导性的设计参考.Millimeter wave communication system is widely used in SATCOM due to the characteristics of wide bandwidth and miniaturization application. Optimal link supportability of multi-carrier millimeterwave SATCOM systems for improving the system capacity faces tradeoff issues among many performance metrics,such as reducing the uplink EIRP demand,improving the transponder power utility,and strengthening the robustness of the links. This paper introduced the concept of multi-objective optimization to the link supportability of millimeter-wave SATCOM modeling. A Constrained Nondominated Neighbor Immune Algorithm( C-NNIA) was presented. Results show that the Pareto-optimal solutions obtained with the algorithm are better than that derived with Direct Solution( DS) algorithm and single objective optimization based Variable Neighborhood Search( VNS) algorithm. It has better constraint handling,convergence and diversity performance as well. Several design guidelines were obtained through the statistics and analysis on design variables and performance metrics within the Paretooptimal solutions.

关 键 词：毫米波 卫星通信 链路支持性 多目标优化 免疫算法 

分 类 号：TN927[电子电信—通信与信息系统]