基于局部搜索的反向学习竞争粒子群优化算法

为提升粒子群优化算法在复杂优化问题,特别是高维优化问题上的优化性能,提出一种基于Solis&Wets局部搜索的反向学习竞争粒子群优化算法(solis and wets-opposition based learning competitive particle swarm optimizer with local search, SW-OBLCSO). SW-OBLCSO算法采用竞争学习和反向学习两种学习机制,并设计了基于个体的局部搜索算子.利用10个常用基准测试函数和12个带有偏移旋转的复杂测试函数,在不同维度情况下将SW-OBLCSO算法与多种优化算法进行对比.实验结果表明,所提出算法在收敛速度和全局搜索能力上表现出突出的性能.对模糊认知图(fuzzy cognitive maps)学习问题的测试表明, SW-OBLCSO算法在处理实际问题时同样具有出色的性能.

Opposition-based learning competitive particle swarm optimizer with local search

In order to improve the optimization ability of particle swarm optimization(PSO) algorithms in complex optimization problems, especially in high dimensional problems, an opposition-based learning competitive particle swarm optimization algorithm based on Solis & Wets(SW-OBLCSO) local search is proposed. The SW-OBLCSO algorithm adopts two learning mechanisms, namely competitive learning and opposition-based learning. An individual-based local search operator is also introduced. The SW-OBLCSO algorithm is compared with various optimization algorithms on the 10 benchmark functions and 12 complex test functions in different dimensions. The experimental results show that the proposed algorithm exhibits outstanding performance in convergence speed and global search ability. Performance comparison on the fuzzy cognitive map(FCM) learning problems shows that the SW-OBLCSO algorithm also has excellent performance when dealing with practical problems.