Page 244 - 《软件学报》2020年第11期

软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software,2020,31(11):3559−3570 [doi: 10.13328/j.cnki.jos.005827] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563

∗
基于二跳共同邻居的无人机群体网络演化算法

于 冲, 司帅宗, 赵 海, 朱 剑, 邵士亮, 刘佳良

(东北大学 计算机科学与工程学院,辽宁 沈阳 110819)
通讯作者: 司帅宗, E-mail: sishuaizong@neuera.com

摘 要: 无人机集群在执行任务过程中所面临的干扰,对集群通信网络的可靠性提出了新的挑战.针对这一问题,
提出了能够同时反映网络非均匀性与节点之间相似性的二跳共同邻居指标.基于该指标,使用链路预测研究方法,考
虑网络初始化阶段与网络维护阶段,提出了 LPTCN 无人机集群网络演化算法.从数学分析与仿真实验两个方面对
算法的有效性进行验证,结果显示,使用 LPTCN 网络演化算法所构建的无人机集群通信网络具有良好的生存性和
抗毁性,在随机攻击和蓄意攻击情况下均能保证通信网络的可靠.
关键词: 无人机群体;二跳共同邻居;链路预测;网络演化
中图法分类号: TP393

中文引用格式: 于冲,司帅宗,赵海,朱剑,邵士亮,刘佳良.基于二跳共同邻居的无人机群体网络演化算法.软件学报,2020,
31(11):3559−3570. http://www.jos.org.cn/1000-9825/5827.htm
英文引用格式: Yu C, Si SZ, Zhao H, Zhu J, Shao SL, Liu JL. Network evolution algorithm of unmanned aerial vehicle flocking
based on two-hop common neighbor. Ruan Jian Xue Bao/Journal of Software, 2020,31(11):3559−3570 (in Chinese). http://www.
jos.org.cn/1000-9825/5827.htm

Network Evolution Algorithm of Unmanned Aerial Vehicle Flocking Based on Two-hop
Common Neighbor

YU Chong, SI Shuai-Zong, ZHAO Hai, ZHU Jian, SHAO Shi-Liang, LIU Jia-Liang
(School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China)

Abstract: The disturbance facing by UAV (unmanned aerial vehicle) flocking in the process of carrying out tasks post a new challenge
to the reliability of the flocking communication network. To this end, a two-hop common neighbor metric is proposed to reflect the
heterogeneity of network and the similarity between nodes simultaneously. Considering network initialization stage and network
maintenance stage, a LPTCN (link prediction based on two-hop common neighbors) network evolution algorithm is proposed.
Mathematical analysis and simulation experiments are applied to verify the validity of the algorithm. The results show that UAV flocking
communication network constructed by the LPTCN network evolution algorithm has great survivability and invulnerability, and the
communication network reliability can be guaranteed in the case of random attack and deliberate attack.
Key words: unmanned aerial vehicle flocking; two-hop common neighbor; link prediction; network evolution

随着无人机领域研究的不断深入,无人机智能化与自主化程度得到持续提升,无人机的普及和应用越来越
广泛.相较于传统的单体无人机,无人机集群通过群体合作与协同,在多变的环境中执行复杂的任务,同时具有
[1]
良好的任务执行效率和经济效益 .其可以灵活地部署在人类无法到达的恶劣环境中,能够独立完成灾害探测、
搜寻救援、情报搜集以及军事作战等工作 [2,3] ,并且在执行任务过程中无需人工参与,很大程度地提高了安全性.
无人机集群可以看作是一种特殊的智能群体,集群中的个体通过通信和行为控制来完成协同配合.集群控

∗ 基金项目: 国家级重大科技创新项目(N161608001)
Foundation item: National Major Science and Technology Innovation Project (N161608001)
收稿时间: 2018-05-03; 修改时间: 2018-07-04, 2018-09-30, 2018-11-02; 采用时间: 2019-01-30