论文部分内容阅读
人工鱼群算法是一种基于动物行为的群体智能优化算法。传统人工鱼群算法优化精度低、运行时间长,不能有效地应用于实时计算和大规模数据处理。针对以上问题,提出一种采用多子群并行计算、动态调整视野和步长、引入全局鱼群优化信息(群体最优人工鱼位置和最优子群中心位置)的改进算法(MSSP_AFSA算法)。试验结果表明,改进算法的寻优效率和准确度更高,在大规模数据计算寻优的情况下,执行时间更短,具有很高的推广应用价值。
Artificial fish swarm algorithm is a group intelligent optimization algorithm based on animal behavior. The traditional artificial fish swarm algorithm has low optimization accuracy and long running time, and can not be effectively applied to real-time calculation and large-scale data processing. Aiming at the above problems, this paper proposes an improved algorithm (MSSP_AFSA) which adopts multi-subgroup parallel computation, dynamically adjusts field of view and step size, and introduces global fish optimization information (optimal artificial fish population position and optimal subgroup center position). The experimental results show that the improved algorithm has higher efficiency and accuracy in searching. With the optimization of large-scale data, the execution time is shorter and has a high value for popularization and application.