求解动态优化问题的多种群竞争差分进化算法

摘要

针对动态优化问题(DOP)的求解,提出结合多种群方法和竞争策略的差分进化算法(DECS).首先,将一个种群作为侦测种群,通过监测种群中所有个体的评价值和种群维度来判断环境是否发生变化.其次,将余下多个种群作为搜索种群,独立搜索环境中的最优值.在搜索过程中,引入排除规则,避免多个搜索种群聚集在同一个局部最优的邻域.在迭代若干代后对各搜索种群执行竞争操作,保留评估值最优个体所在的种群并对该种群的下一代个体生成采用量子个体生成机制,而对其他搜索种群重新初始化.最后,利用7个测试函数的49个动态变化问题对DECS进行验证,并将实验结果与人工免疫算法(Dopt-aiNet)、复位粒子群优化(rPSO)算法、改进差分进化(MDE)算法进行比较.实验结果表明,在49个问题上,DECS有34个问题的平均离线误差期望小于Dopt-aiNet算法,所有问题的平均离线误差期望都小于rPSO算法和MDE算法,因此DECS对DOP求解动态优化问题是可行的.%To solve Dynamic Optimization Problems (DOP),a Differential Evolution algorithm with Competitive Strategy based on multi-population (DECS) was proposed.Firstly,one of the populations was chosen as a detection population.Whether the environment had changed was determined by monitoring the fitness values of all individuals in the population and dimension of the population.Secondly,the remaining populations were used as the search populations to search the optimal value independently.During the search,a exclusion rule was introduced to avoid the aggregation of multiple search populations in the same local optimal neighborhood.After the iteration of several generations,competitive operation was performed on all search populations.The population to which the optimal individual belong was retained and the next generation's individuals of the population were generated by using the quantum individual generation mechanism.Then other search populations were reinitialized.Finally,49 dynamic change problems about 7 test functions were used to verify DECS,and the experimental results were compared with Artificial Immune Network for Dynamic optimization (Dopt-aiNet) algorithm,restart Particle Swarm Optimization (rPSO) algorithm,and Modified Differential Evolution (MDE) algorithm.The experimental results show that the average error mean of 34 problems for DECS is less than Dopt-aiNet and the average error mean of all problems for DECS was less than that for rPSO and MDE.Therefore,DECS is feasible to solve DOP.