期刊名称：International Journal of Future Generation Communication and Networking
印刷版ISSN：2233-7857
出版年度：2014
卷号：7
期号：6
页码：217-230
DOI：10.14257/ijfgcn.2014.7.6.20
出版社：SERSC
摘要：Differing from the physical connectivity of the topology structure, the logical connectivity of VANET considers both the interior network configuration and the external communication environment. Hence, the traditional mathematical analysis and modeling methods which are usually used in physical connectivity research are no longer suitable for the logical connectivity prediction. Taking the AODV protocol as an example, this paper simulates the effects of different road traffic parameters on logical connectivity probability and selects three main effect factors, roadway length, vehicle number and vehicle speed. Furthermore, the inner relation between the logical connectivity and the three road traffic parameters is studied based on data mining technique and then two logical connectivity prediction models are presented, the nonlinear regression-based model and the extreme learning machine- based model. Simulation results show that the two models are both with high accuracy in predicting the network logical connectivity under different road traffic environments.
