新型排球超级联赛算法

Novel Volleyball Premier League Algorithm

针对排球超级联赛算法存在收敛速度慢、求解精度不高和易陷入局部最优等缺陷,提出一种新型排球超级联赛算法.首先,将超级明星球员引入排球联赛中,设计模仿算子,以增强算法的寻优精度;然后,改进替补策略,使算法自适应选择是否调用替补过程,进一步提高算法的收敛效率;最后,通过最劣球队学习最佳球队可加强算法的全局探索、任一球队学习最佳球队可加强算法的局部开发,提出一种随机交互训练策略,将两种策略随机交互动态生成新球队,使算法的全局探索和局部开发性能得到平衡.另外对11个经典测试函数的仿真实验,验证了新型排球超级联赛算法具有良好的优化性能.

To solve the problem of slow convergence speed,slow accuracy and easily falling into local optimum in the updating process of volleyball premier league algorithm(VPL),a kind of novel volleyball premier league algorithm(NVPL)w as proposed.Firstly,the super star player w as introduced into the volleyball league to enhance the searching ability and efficiency of the algorithm.Secondly,by improving the substitute operator,the algorithm can choose w hether to call the substitute or not adaptively.Finally,the new team vector is generated dynamically by means of random crossover for the global optimization problem,i.e.,the w orst team learning from the best team and the random selected other team learning from the best team w ith different strategies.The random crosser learning strategy is applied to balance the global search and local search performance of the algorithm.Simulation test experiments on eleven classical functions show the NVPL has better performance.