基于多种群进化与粒子群优化混合的频谱分配算法  

Spectrum Allocation Algorithm Based on Hybrid Multigroup Evolution and Particle Swarm Optimization

作　　者：王俊铭[1] 刘佳琦[1] 陈志刚[1] 郭霖[1] 

机构地区：[1]中南大学软件学院,长沙410075

出　　处：《计算机科学》2016年第4期28-32,共5页Computer Science

基　　金：国家自然科学基金(61379057;61309001;61379110;61103202);国家重点基础研究发展计划(973计划)(2014CB046305);教育部博士点基金新教师类(20110162120046);中南大学中央高校基本科研业务费专项资金(2015zzts232)资助

摘　　要：为了解决认知无线网络中的频谱分配问题,提出一种基于多种群进化与粒子群优化混合的频谱分配算法。它采用图论着色模型,首先使用遗传算法将多个种群进行独立进化,以提高种群的全局搜索能力;然后选出每个种群中的最优的个体作为粒子群优化的粒子,并通过控制每个粒子的初始速度方向来加快算法的收敛速度。最后以系统总收益最大化和用户间的公平性为优化目标与遗传算法和粒子群算法进行了对比实验,仿真结果表明,该算法在收敛速度、认知用户接入公平性和系统总收益3个方面的性能均优于遗传算法和粒子群算法。In order to solve the spectrum allocation problem in cognitive wireless network, a spectrum allocation algo- rithm based on multigroup evolution and particle swarm optimization hybrid was proposed in this paper. It uses graph coloring model,and makes multiple populations evolve independently by genetic algorithm in order to improve global search capability of populations first. Then it selects the optimal particle of each individual population as a particle parti- cle swarm optimization, and controls the direction of the initial velocity of each particle to speed up the convergence rate. Finally, the maximum benefit and the fairness among users were taken as the optimization goal to compare with ge- netic algorithm and particle swarm optimization by simulation experiment. The experimental results show that the algo- rithm is better than genetic algorithm and particle swarm optimization in convergence speed, cognitive user access fair- ness and total system efficiency.

关 键 词：认知无线网络 频谱分配 粒子群算法 遗传算法 系统总收益 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]