基于模体的目标区域网络拓扑划分方法  

A motif-based topology partitioning method for target area networks

作　　者：杨迪 刘琰 陈静 张伟丽 YANG Di;LIU Yan;CHEN Jing;ZHANG Wei-li(State Key Laboratory of Mathematical Engineering and Advanced Computing,The PLA Information Engineering University,Zhengzhou 450000,China)

机构地区：[1]数学工程与先进计算国家重点实验室,河南郑州450000

出　　处：《计算机工程与科学》2019年第3期466-478,共13页Computer Engineering & Science

基　　金：国家自然科学基金(61309007;U1636219;61602508;61772549;U1736214;61572052);国家重点研发计划课题(2016YFB0801303;2016QY01W0105)

摘　　要：随着信息社会的发展,网络安全的重要性日益凸显,准确获取网络实体的地理位置有助于更好地实施网络管理。现有经典的基于拓扑启发式聚类的网络实体定位方法,采用基于网络结构的集群划分对网络实体进行聚类,由于没有考虑网络拓扑的具体特性,导致最后的结果误差较大。为解决这一问题,提出一种基于模体的目标区域网络拓扑划分方法。该方法根据目标网络拓扑呈现局部节点高聚类性的特点,创新性地引入"模体"的概念,在目标网络拓扑中挖掘模体结构并进行分析;然后借鉴复杂网络研究领域内局部社团发现方法中初始种子扩展的思路,以模体结构为初始种子进行相应扩展,将拓扑中与模体紧密相连的节点划分为多个集合;最后分别根据地标和公开的IP地理位置数据库对划分的节点集合进行定位,将集合的位置作为集合内节点的地理位置,从而实现网络实体的批量定位。基于香港和台湾两个地区网络拓扑的实验结果表明,该方法与经典的HC-Based方法、NNC方法相比,在网络实体定位准确率上分别能提高25%和16%左右,并且可批量定位的网络实体更多。With the development of the information society, the importance of network security has become increasingly prominent, and the accurate geographical location of network entities can help better implement network management. The existing classical network entity location method based on topology heuristic clustering adopts the clustering based on network structure to cluster network entities, does not consider the specific characteristics of the network topology, and leads to final results with big error. In order to solve this problem, we propose a target area network topology partitioning method based on the motifs. According to the high clustering characteristics of local nodes in the target network topology, we innovatively introduce the concept of "motif" and analyze the motif structure in the target network topology. Learning from the idea of the initial seed expansion in local community discovery methods for the complex network, we take the motif structure as the initial seed to expand, and divide the nodes closely connected with the motif in the topology into different sets. Finally we locate the node sets according to the landmark and the public IP geo-location database, and take the location of the set as the geographic location of the nodes within it so as to achieve the bulk positioning of network entities. Experiments based on the network topologies in Hong Kong and Taiwan show that compared with the classical HC-Based method and network node clustering method (NNC), the positioning accuracy of network entities of our method can be enhanced by about 25% and 16% respectively, and there are more network entities can be located in a batch way.

关 键 词：复杂网络 目标网络拓扑 模体 拓扑划分 网络实体定位 

分 类 号：TP393.022[自动化与计算机技术—计算机应用技术]