通过分析认知无线网络引擎决策,给出了其数学模型,并将其转化为一个多目标优化问题,进而提出一种基于混沌量子克隆的优化求解算法,并证明了该算法以概率1收敛.算法采用量子编码,利用Logistic映射初始化抗体种群,设计了一种基于混沌扰动的量子变异方案.最后,在多载波环境下对算法进行了仿真实验.结果表明,与QGA-CE(基于量子遗传算法的认知引擎)算法相比,本文算法收敛速度较快,具有较高的目标函数值,可以对无线参数优化调整,满足认知引擎的实时性要求.
By analyzing engine decision of cognitive wireless network,the mathematical model of engine decision is given,and then it is converted into a multi-objective optimization problem.A Chaos quantum clonal algorithm is proposed to solve the problem,and the algorithm convergent with probability 1 is proved,in which the quantum coding and logistic mapping are used to initialize the population.A quantum mutation scheme is designed with chaotic disturbances.Finally,the simulation experiments are done to test the algorithm under a multi-carrier system.The results show that compared with QGA-CE(quantum genetic algorithm based cognitive engine),this algorithm has a good convergence and an objective function value.It can adapt the parameter configuration and meet the real-time requirement for cognitive engine.