基于多时间段优化贝叶斯网络的车载容迟网络路由算法  

Vehicular delay tolerant network routing algorithm based on optimized multi-period Bayesian network

作　　者：吴家皋[1,2] 郭亚航 蔡沈磊 刘林峰 WU Jiagao;GUO Yahang;CAI Shenlei;LIU Linfeng(School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Jiangsu Key Laboratory of Big Data Security&Intelligent Processing,Nanjing 210023,China)

机构地区：[1]南京邮电大学计算机学院,江苏南京210023 [2]江苏省大数据安全与智能处理重点实验室,江苏南京210023

出　　处：《通信学报》2021年第12期109-120,共12页Journal on Communications

基　　金：国家自然科学基金资助项目(No.61872191,No.41571389)。

摘　　要：针对车载容迟网络(VDTN)中车辆节点高速移动造成的通信链路不稳定性问题,利用车辆节点移动的规律性和时段性特点,提出了基于多时间段优化贝叶斯网络(BN)的VDTN路由算法。首先,提出了新的多时间段BN模型及其节点分类动态奖励机制,以更准确地描述车辆的移动模式。接着,提出了2种新的BN的时间段优化划分算法:二分搜索K2GA(BS-K2GA)算法和模拟退火K2GA(SA-K2GA)算法,其中,BS-K2GA算法具有简单高效的优势,而SA-K2GA算法则能有效避免陷入局部最优解,进一步优化算法性能。仿真实验表明,所提出的基于多时间段优化BN的VDTN路由算法能显著提高消息的投递率,降低消息的投递时延,从而验证了研究方案的有效性。Aiming at the instability of communication link caused by the high-speed movement of vehicle nodes in vehicular delay tolerant network(VDTN),considering the characteristics of regularity and periodicity of vehicle nodes movement,a VDTN routing algorithm based on optimized multi-period Bayesian network(BN)was proposed.Firstly,a new multi-period BN model and its dynamic reward mechanism for node classification were proposed to describe the movement pattern of vehicle nodes with higher accuracy.Then,two novel time-optimal-partition algorithms of multi-period BN were proposed including binary search K2GA(BS-K2GA)algorithm and simulated annealing K2GA(SA-K2GA)algorithm,where BS-K2GA algorithm had the advantages of simplicity and efficiency,while SA-K2GA could effectively avoid falling into the local optimal solution and further optimize the performance.The simulation results show that the proposed VDTN routing algorithm based on optimized multi-period BN model can significantly improve the message delivery ratio and reduce the delivery delay.Thus,the effectiveness of the approach is validated.

关 键 词：车载容迟网络 贝叶斯网络 路由算法 二分搜索 模拟退火 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]