改进人工鱼群算法在认知无线电决策引擎中的应用

针对遗传算法、粒子群算法等应用于认知无线电决策引擎时存在收敛速度慢，容易陷入局部最优解的缺陷，提出了一种基于改进人工鱼群算法的认知无线电决策引擎．利用改进人工鱼群算法全局收敛性强、鲁棒性能好、初值敏感度低等特点，更快速、高效地优化调整传输参数，从而寻找特定条件下的最优配置方案．仿真结果表明，在多载波通信系统下，该认知决策引擎具有收敛精度高、平均适应度值高、稳定性强等特点，性能优于二进制量子粒子群认知引擎．

The applications of improved artificial fish swarm algorithm in cognitive radio decision engine

In considering the defects of slow convergence speed and easy to fall into local optima in the traditional algorithms such as genetic algorithm and particle swarm optimization algorithm, this paper proposed a cognitive radio decision engine based on improved artificial fish swarm algorithm （AFSA）. The improved AFSA has the abilities of better global convergence and robust performance, low initial value sensitivity, and can adjust the transmission parameters more rapidly and efficiently, therefore finding the optimal allocation scheme under certain conditions. The simulation results show that in the multi-carrier communication system, with the characteristics of high accuracy of convergence, high average fitness value and strong stability, the performance of the cognitive radio decision engine with AFSA is significantly better than the advanced binary quantum particle swarm optimization （BQPSO） cognitive engine.