基于改进雷达图法的群智能算法综合性能评估

Comprehensive performance evaluation of swarm intelligence algorithms based on improved radar graph method

为解决传统性能评估方法无法准确评估群智能算法性能的问题,提出一种基于改进雷达图法的群智能算法综合性能评估方法。建立适应度评价次数、寻优时间、寻优稳定性、寻优精度、覆盖度、覆盖速率6种群体智能算法性能评估指标模型。在典型测试函数上,基于上述6种指标,通过改进雷达图法分析3种常用群智能算法的综合性能。仿真结果表明:所提方法能够全面客观的反映群智能算法的综合性能,为群智能算法的性能分析、优化和决策提供理论依据。

In order to solve the problem that traditional performance evaluation methods cannot accurately evaluate the performance of swarm intelligence algorithms,a comprehensive performance evaluation method for swarm intelligence algorithms based on the improved radar graph method was proposed.Six performance evaluation index models for swarm intelligence algorithm were established,including fitness evaluation time,optimization time,optimization stability,optimization accuracy,coverage,and coverage rate.The improved radar graph method was utilized to examine the complete performance of three widely-known swarm intelligence algorithms based on the aforementioned six indicators using common test functions.The simulation results show that the comprehensive proposed method of swarm intelligence algorithm based on the improved radar graph can reflect the comprehensive performance of swarm intelligence algorithm comprehensively and objectively,and provide theoretical basis for the performance analysis,optimization,and decision-making of swarm intelligence algorithm.