计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (6): 358-366.doi: 10.11896/jsjkx.250400094

• 计算机网络 • 上一篇    下一篇

面向物联网的基于模糊聚类的DTN路由算法

常亚楠1, 孙祎1, 崔建群1,2, 严湘龙1, 宗诚路1   

  1. 1 华中师范大学计算机学院 武汉 430079
    2 华中师范大学人工智能与智慧学习湖北省重点实验室 武汉 430079
  • 收稿日期:2025-04-21 修回日期:2025-09-14 出版日期:2026-06-15 发布日期:2026-06-09
  • 通讯作者: 崔建群(jqcui@126.com)
  • 作者简介:(ynchang@mail.ccnu.edu.cn)
  • 基金资助:
    国家自然科学基金面上项目(62372206,62372206,62272189);人工智能与智慧学习湖北省重点实验室开放研究基金(2025AISL008);中央高校基本科研业务费资助项目(CCNU25JCPT038)

Fuzzy Clustering-based DTN Routing Algorithm for IoT

CHANG Yanan1, SUN Yi1, CUI Jianqun1,2, YAN Xianglong1, ZONG Chenglu1   

  1. 1 School of Computer Science,Central China Normal University,Wuhan 430079,China
    2 Hubei Key Laboratory of Artificial Intelligence and Intelligent Learning,Central China Normal University,Wuhan 430079,China
  • Received:2025-04-21 Revised:2025-09-14 Published:2026-06-15 Online:2026-06-09
  • About author:CHANG Yanan,born in 1984,Ph.D,associate professor,is a member of CCF(No.35671M).Her main research interests include wireless network,social network and Internet of Things.
    CUI Jianqun,born in 1974,Ph.D,professor,is a member of CCF(No.27790M).Her main research interests include opportunity network,Internet of Things,mobile network and application layer multicast.
  • Supported by:
    General Program of National Natural Science Foundation of China(62372206,62372206,62272189),Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning(2025AISL008) and Fundamental Research Funds for the Central Universities(CCNU25JCPT038).

PDF (PC)

61

摘要： 在物联网DTN网络中,节点分布的稀疏性和高动态性,导致源节点难以与目的节点直接建立连接并传输数据。因此,如何设计一种高效、稳定的路由算法是物联网DTN网络中的关键问题。近年来,机器学习技术的快速发展给解决路由优化问题提供了新的思路,使得算法能够从复杂网络数据中挖掘潜在的模式,提升决策过程的效率与准确性。基于此,提出了一种基于模糊聚类模型FCM的物联网DTN路由算法FCMROP(A loT DTN Routing Algorithm Based on the Fuzzy Clustering Model)。该算法采用基于多特征融合的动态簇划分方法,综合考虑节点缓存、活跃情况、投递预测值和结构稳定性等特征,以提高簇划分的合理性和路由决策的精准度。同时,引入基于模糊隶属度加权的距离度量方法,以优化簇的选择。仿真实验结果表明,与GMMR,DBSCAN-R,KROP和Prophet路由算法相比,FCMROP在投递率、平均时延和消息丢弃率等方面均表现出更优的性能。

关键词: DTN, 无监督学习, 物联网, 模糊聚类

Abstract: In IoT DTN networks,the sparse and highly dynamic distribution of nodes makes it difficult for source nodes to establish direct connections with destination nodes for data transmission.Therefore,how to design an efficient and stable routing algorithm is a critical challenge in IoT DTN networks.In recent years,the rapid development of machine learning has provided new insights into routing optimization,enabling algorithms to extract hidden patterns from complex network data and enhance decision-making efficiency and accuracy.This paper proposes FCMROP(An IoT DTN Routing Algorithm Based on the Fuzzy Clustering Model).The algorithm employs a multi-feature fusion-based dynamic clustering method,considering node buffer,activity le-vel,delivery probability,and structural stability to improve cluster partitioning and routing decision accuracy.Additionally,a fuzzy membership-weighted distance metric is introduced to optimize cluster selection.Simulation results demonstrate that compared to GMMR,DBSCAN-R,KROP,and Prophet routing algorithms,FCMROP achieves superior performance in delivery rate,average delay,and message drop rates.

Key words: DTN, Unsupervised learning, Internet of Things, Fuzzy clustering

中图分类号: 

  • TP393
[1]TAN L,WANG N.Future internet:The internet of things[C]//2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE).IEEE,2010:V5-376-V5-380.
[2]RAY P P.A survey on Internet of Things architectures[J].Journal of King Saud University-Computer and Information Sciences,2018,30(3):291-319.
[3]YAN Y,CHEN Z,WU J,et al.Effective data transmissionstrategy based on node socialization in opportunistic social networks[J].IEEE Access,2019,7:22144-22160.
[4]LE T.Multi-hop routing under short contact in delay tolerant networks[J].Computer Communications,2021,165:1-8.
[5]CHEN Y K.Challenges and opportunities of internet of things[C]//17th Asia and South Pacific Design Automation Confe-rence.IEEE,2012:383-388.
[6]BURLEIGH S,HOOKE A,TORGERSON L,et al.Delay-tole-rant networking:an approach to interplanetary internet[J].IEEE Communications Magazine,2003,41(6):128-136.
[7]FAWAZ W,ATALLAH R,ASSI C,et al.Unmanned aerial vehicles as store-carry-forward nodes for vehicular networks[J].IEEE Access,2017,5:23710-23718.
[8]MAO Y,ZHOU C,LING Y,et al.An optimized probabilistic delay tolerant network(DTN) routing protocol based on scheduling mechanism for internet of things(IoT)[J].Sensors,2019,19(2):243.
[9]GANDHI J,NARMAWALA Z.A comprehensive survey on machine learning techniques in opportunistic networks:Advances,challenges and future directions[J].Pervasive and Mobile Computing,2024,100:101917.
[10]CUI J Q,YAN H R,CHANG Y N,et al.Routing Algorithm Combining Collaborative Filtering and Encounter Probability Prediction in DTN[J].Journal of Chinese Computer Systems,2025,46(3):735-743.
[11]VASHISHTH V,CHHABRA A,SHARMA D K.A machinelearning approach using classifier cascades for optimal routing in opportunistic internet of things networks[C]//2019 16th AnnualIEEE International Conference on Sensing,Communication,and Networking(SECON).IEEE,2019:1-9.
[12]KANDHOUL N,DHURANDHER S K,WOUNGANG I.Random forest classifier－based safe and reliable routing foropportunistic IoT networks[J].International Journal of Communication Systems,2021,34(1):e4646.
[13]DUDUKOVICH R,HYLTON A,PAPACHRISTOU C.A machine learning concept for DTN routing[C]//2017 IEEE International Conference on Wireless for Space and Extreme Environments(WiSEE).IEEE,2017:110-115.
[14]SHARMA D K,RODRIGUES J J P C,VASHISHTH V,et al.RLProph:a dynamic programming based reinforcement learning approach for optimal routing in opportunistic IoT networks[J].Wireless Networks,2020,26:4319-4338.
[15]CHANG Y N,DUAN X Z,CUI J Q,et al.Opportunistic Network Routing Algorithm Based on Unsupervised Learning Model X-Means[J].Journal of Chinese Computer Systems,2025,46(7):1734-1744.
[16]SHARMA D K,DHURANDHER S K,AGARWAL D,et al.kROp:k-Means clustering based routing protocol for opportunistic networks[J].Journal of Ambient Intelligence and Humanized Computing,2019,10:1289-1306.
[17]VASHISHTH V,CHHABRA A,SHARMA D K.GMMR:AGaussian mixture model based unsupervised machine learning approach for optimal routing in opportunistic IoT networks[J].Computer Communications,2019,134:138-148.
[18]PILLAI R,RAO R,PRASAD C R,et al.DBSCAN-R:A Ma-chine Learning Approach for Routing in Opportunistic Networks[C]//2022 IEEE International Conference on Electronics,Computing and Communication Technologies(CONECCT).IEEE,2022:1-6.
[19]CONG L,DING H,XIE N,et al.Space delay-tolerant network routing algorithm based on node clustering and social attributes[J].Ad Hoc Networks,2024,155:103381.
[20]BEZDEK J C,EHRLICH R,FULL W.FCM:The fuzzy c-means clustering algorithm[J].Computers & Geosciences,1984,10(2/3):191-203.
[21]NAYAK J,NAIK B,BEHERA H S.Fuzzy C-means(FCM) clustering algorithm:a decade review from 2000 to 2014[C]//Computational Intelligence in Data Mining-Volume 2:Procee-dings of the International Conference on CIDM.Springer India,2015:133-149.
[22]LINDGREN A,DORIA A,SCHELÉN O.Probabilistic routingin intermittently connected networks[J].ACM SIGMOBILE Mobile Computing and Communications Review,2003,7(3):19-20.
[23]KERÄNEN A,OTT J,KÄRKKÄINEN T.The ONE simulator for DTN protocol evaluation[C]//Proceedings of the 2nd International Conference on Simulation Tools and Techniques.2009:1-10.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发