改进的人工鱼群算法及其在无线定位中的应用*

摘 要：人工鱼群算法是一种基于动物行为的群体智能优化算法。针对基本鱼群算法收敛速度慢和在算法运行后期搜索盲目性较大等问题，给出了一种改进的鱼群算法。该算法采用可变视野，在搜索的后期使用随机步长，并给出了局部最优人工鱼移动策略，较好地平衡了全局搜索能力和局部搜索能力；在假设目标函数分布未知的情况下，规范了人工鱼的各种行为，给出了明确的收敛条件。在文章最后，结合蜂窝网中以功率值作为测量参数的无线定位问题，给出一种基于人工鱼群算法的分布式定位方法。仿真实验表明，该方法实现简单，全局搜索能力强，满足了定位的有效性和实时性。

Improved artificial fish swarm algorithm and its application for wireless location

Abstract: The artificial fish swarm algorithm (AFSA) is a swarm intelligence optimization algorithm based on the animal behavior. The improved artificial fish swarm algorithm was proposed to overcome the demerit of slow computational speed and the blindness of searching at the later stage of the basic artificial fish swarm algorithm. Firstly, this algorithm used alterable visual and stochastic step, and a move strategy of the local better artificial fish was presented, to well balance the abilities of searching the global and local extremum. Secondly, in the case of unknown target function, a behavior order of artificial fish and a specific convergence term were presented. Finally, to the question of the location in Cellular Network, a distributed location method which used the signal strength as the measurement parameter, and based on the improved artificial fish swarm algorithm was presented .The analysis of simulation result shows that this method has a strong ability in global search, and could complete the assignment of location in availability and timeliness.