基于嵌套Logit模型的竞争性选址问题研究

A new competitive facility location model based on nested Logit model

为解决现有竞争性选址研究中,"不相关选项的独立性"引起的市场份额计算偏差问题.本文首先以嵌套Logit模型优化顾客效用函数,建立以收益最大化为目标的、连续多属性竞争性选址与设计模型;其次通过大量数值仿真实验,对比分析了GSA、PSO-GSA、CGSA1-10型算法性能.实验结果表明,PSO-GSA算法有着最强的解空间搜索能力,为本文模型一种高效、稳定的求解方法.

Independence of irrelevant alternatives(IIA)tends to cause deviations in the prediction of customers’choice behavior.To solve the problem,this study constructs a novel competitive facility location and design model.This model is also applicable to the continuous and multi-attribute design problem.This study ana-lyzes the performance of several algorithms through numerical experiment:The gravitational search algorithm(GSA),the particle swarm optimization-gravitational search algorithm(PSO-GSA),and chaotic gravitational search algorithm chaotic gravitational search algorithm 1 through 10.The experiment result shows the PSO-GSA has the best ability to search in solution space.Therefore,this study regards PSO-GSA as a highly efficient and stable algorithm for solving the new model.