融合多种策略的改进粒子群算法及其在电子商务多级物流中的应用研究

为了提高粒子群优化算法(PSO)求解复杂优化问题的能力,本文对基于细菌趋化的粒子群优化算法(PSOBC)进行改进。PSOBC算法是PSO算法的一种新思路,可以有效地克服其易陷入局部最优、后期粒子多样性差的缺点,故将一般反向学习策略和自适应惯性权重与PSOBC算法相结合,得到一种改进的粒子群优化算法。改进的粒子群优化算法的开发能力和勘探能力都得到了很大的提高;在求解复杂性优化问题时种群能够在搜索范围内快速收敛到局部最优处,并且当种群密度足够小时,及时增大种群密度即进行去全局寻优。最后将改进后算法应用到电子商务多级物流中心选址及路径规划问题上。

IMPROVED PARTICLE SWARM OPTIMIZATION ALGORITHM WITH MULTIPLE STRATEGIES AND ITS APPLICATION IN MULTI-LEVEL LOGISTICS OF E-COMMERCE

In order to improve the ability of particle swarm optimization (PSO) to solve complex optimization problems, this paper improves the PSO algorithm based on bacterial chemotaxis (PSOBC). Aiming at the problem of slow convergence and low convergence of PSO in solving complexity problems, a general inverse learning strategy and adaptive inertia weight are combined with PSOBC algorithm to obtain an improved particle swarm optimization algorithm. The improved particle swarm optimization algorithm has greatly improved the development and exploration capabilities; it can quickly converge to the local optimum within the search capability when solving the complexity optimization problem, and increase the population density when it is small enough. The large population density is to perform global optimization. Finally, the improved algorithm is applied to the e-commerce multi-level logistics center location and path planning.