基于位置吸引力的加权复杂供应链网络局域世界演化模型研究  

Study on Local World Evolution Model of Weighted Complex Supply Chain Network Based on Location Attraction

作　　者：赵志刚 周根贵[3] 潘瑞芳[2] ZHAO Zhi-gang;ZHOU Gen-gui;PAN Rui-fang(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310014,China;College of Economics and Management,Zhejiang University of Technology,Hangzhou 310014,China;Zhejiang University of Media and Communications,Hangzhou 310018,China)

机构地区：[1]浙江工业大学计算机科学与技术学院,杭州310014 [2]浙江传媒学院,杭州310018 [3]浙江工业大学经贸管理学院,杭州310014

出　　处：《计算机科学》2018年第12期71-76,共6页Computer Science

基　　金：国家自然科学基金面上项目(71371169);浙江传媒学院一流学科"计算机科学与技术"(网络空间安全方向)资助

摘　　要：在一般局域世界演化模型的基础上,文章使得企业节点的初始位置值呈现幂率分布,以体现节点企业的不同角色。受万有引力定律的启发,用位置值的大小和远近值来定义节点企业间位置吸引力的概念,并应用吸引力规则确定每一个新加入节点的局域世界。新节点与局域世界中的老节点之间采用节点度与节点强度的复合优先连接方式,弥补了优先连接仅仅依赖节点度值的缺陷,从而构建基于位置吸引力的加权复杂供应链网络局域世界演化模型。实验模拟了该复杂网络的生长、边的退出和节点的退出等动态演化过程,通过计算与统计整体度分布、平均路径长度和聚集系数等复杂供应链网络的重要参数发现:该复杂供应链网络的度分布呈现出一定的幂率分布形式,能够保证大多数节点的度较低和少数节点的度较高的重尾特征,同时具有较大的集聚系数和较小的平均路径长度的小世界特征。该研究工作为供应链企业在实践中构建供应链网络提供了理论依据,有助于更好地分析现实供应链网络的相关特性并识别重要节点以便对供应链网络进行保护。The initial position values of enterprise nodes are presented as power-law distribution to reflect different roles of node enterprises on the basis of common local-world evolving network models.Inspired by the law of universal gravitation,this paper utilized the size of position and distance values to define the concept of position attraction of node enterprises,and determined the local world of every newly added node by using attraction rules.The compound priority connection mode of node degree and node strength is adopted among new nodes and the old nodes in the local world,making up for the defect that priority connection only relies on node degrees.In this sense,the weighted complex supply chain network-world evolving model was established based on position attraction.The experiments were conducted to simulate the dynamic evolution process such as complex network growth,edge exit and node exit etc.Through the calculation and statistic analysis of important parameters in complex supply chain networks such as network integrity degree distribution,average path length and average gather coefficient,it is found that the degree distribution of the complex supply chain network shows power-law distribution.It can guarantee the heavy tailed characteristics with the majority of the nodes possessing low degree and few nodes possessing high degree.At the same time,the complex supply chain network possesses small world characteristics with larger clustering coefficient and smaller average path length.This research provides theoretical foundation for supply chain enterprises to establish supply chain networks in practice,and it is conducive to analyze characteristics related to real supply chain networks better and identify important nodes for further protection.

关 键 词：复杂网络 供应链 交易量 局域世界 位置吸引力 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]