摘要
为了优化蜂群算法(BCA),平衡局部搜索与全局搜索,避免算法陷入局部最优,并提高蜂群算法的收敛速度,提出了一种多策略改进的方法优化蜂群算法(MSO—BCA)。算法在种群初始化阶段采用了反向学习(OBL)初始化的方法;在种群更新与邻域搜索中采用了具有Levy飞行特征的改进搜索策略。经过对经典Benchmark函数的反复实验并与其他算法的比较,表明了所提出的算法具有良好的加速和收敛效果,提高了全局搜索能力与效率。
In order to optimize bee colony algorithm (BCA), balance local and global search capability, avoid falling into local optimum and accelerate convergence speed of BCA, an improved algorithm multi-strategy optimized(MSO-BCA) is presented. The new algorithm constructs the initial population by using opposition-based learning(OBL) and levy flight inspired search strategy is designed to replace the original random step. The experiments on a set of benchmark functions show that the proposed algorithm has better performance than other BCA-based algorithms,especially on accelerating and convergence and the global search ability and efficiency.
出处
《传感器与微系统》
CSCD
2017年第1期111-114,共4页
Transducer and Microsystem Technologies
基金
国家"863"计划资助项目(2012AA041701)
关键词
蜂群算法
多策略改进
反向学习
Levy飞行
bee colony algorithm( BCA)
multi-strategy improved
opposition-based learning
Levy flight