Yuze SU, Xiangru MENG, Xiaoyang HAN, Qiaoyan KANG

Symptom-aware hybrid fault diagnosis algorithm in the network virtualization environment

As an important technology in next-generation networks, network virtualization has received more and moreattention. Fault diagnosis is the crucial element for fault management and it is the process of inferring the exact failurein the network virtualization environment (NVE) from the set of observed symptoms. Although various traditional faultdiagnosis algorithms have been proposed, the virtual network has some new characteristics, which include inaccessiblefault information of the substrate network, inaccurate network observations, and a dynamic embedding relationship.To solve these challenges, a symptom-aware hybrid fault diagnosis (SAHFD) algorithm in the NVE is proposed in thispaper. First, a multifactor Bayesian hierarchical model is proposed to denote the relationships between multiple factorsin different layers. Second, the contribution degree is improved to locate the faults in the virtual layer and the activedetection algorithm is introduced to filter some spurious faults in virtual layer fault diagnosis. Then, in substrate layerfault diagnosis, the active detection algorithm is introduced to solve the problem of incomplete network observations.Finally, a heuristic greedy algorithm is proposed to select appropriate actions based on minimum weight set coveringmethod with minimum cost. Simulation results show that, compared with other algorithms, the SAHFD algorithm hasa higher accuracy rate, lower false positive rate, and better environmental adaptability in the NVE.

PDF

___

[1] Morales F, Ruiz M, Velasco L. Virtual network topology reconfiguration based on big data analytics for traffic prediction. J Opt Commun Netw 2017; 9: 35-45.
[2] Blenk A, Basta A, Reisslein M, Kellerer W. Survey on network virtualization hypervisors for software defined networking. IEEE Commun Surv Tut 2017; 18: 655-685.
[3] Kou TW, Liou BH, Lin KC, Tsai MJ. Deploying chains of virtual network functions: on the relation between link and server usage. IEEE ACM T Network 2018; 26: 1-15.
[4] Su Y, Meng X, Kang Q, Han X. Survivable virtual network link protection method based on network coding and protection circuit. IEEE Access 2018; 6: 67477-67493.
[5] Dusia A, Sethi A. Recent advances in fault localization in computer networks. IEEE Commun Surv Tut 2016; 18: 3030-3051.
[6] Li RTH, Chung SH. Digital boundary controller for single-phase grid-connected CSI. In: IEEE 2008 Power Electronics Specialists Conference; Rhodes, Greece. New York, NY, USA: IEEE; 2018. pp. 4562-4568.
[7] Boem F, Ferrari RMG, Keliris C, Parisini T, Polycarpou MM. A distributed networked approach for fault detection of large-scale systems. IEEE T Automat Contr 2016; 62: 18-33.
[8] Huang XH, Zou SH, Wang WD, Cheng SD. Fault management for Internet service: Modeling and algorithms. In: IEEE International Conference on Communications; İstanbul, Turkey. New York, NY, USA: IEEE; 2006. pp. 854-859.
[9] Zhang S, Qiu X, Meng L. Service fault diagnosis algorithm in network virtualization environment. J Software 2018; 23: 2772-2781.
[10] Yan CX, Wang Y, Qiu XS, Li WJ, Guan L. Multi-layer fault diagnosis method in the network virtualization environment. In: Sixteenth Asia-Pacific Network Operations and Management Symposium; Taipei, China. New York, NY, USA: IEEE; 2014. pp. 1-6.
[11] Liu N, Zhang S, Wang X. Virtual network fault diagnosis using trust evaluation. Video Eng 2016; 40: 80-84.
[12] Gillani S, Demirci M, Al-Shaer E, Ammar M. Problem localization and quantification using formal evidential reasoning for virtual networks. IEEE T Netw Serv Man 2014; 11: 307-320.
[13] Wang H, Wang Y, Qiu XS, Li WJ, Xiao AL. Fault diagnosis based on evidences screening in virtual network. In: 2015 IFIP/IEEE International Symposium on Integrated Network Management; Ottawa, Canada. New York, NY, USA: IEEE; 2015. pp. 802-805.
[14] Bennacer L, Amirat Y, Chibani A, Mellouk A, Ciavaglia L. Self-diagnosis technique for virtual private networks combining Bayesian networks and case-based reasoning. IEEE T Autom Sci Eng 2015; 12: 354-366.
[15] Zhang L, Zhu XR, Zhao S, Xu D. A novel virtual network fault diagnosis method based on long short-term memory neural networks. In: 2017 IEEE 86th Vehicular Technology Conference; Toronto, Canada. New York, NY, USA: IEEE; 2017. pp. 1-5.
[16] Mehmood A, Alrajeh N, Mukherjee M, Abdullah S, Song H. A survey on proactive, active and passive fault diagnosis protocols for WSNs: network operation perspective. Sensors 2018; 18: 1787.
[17] Liu S, Wang Y. A dynamic probe station selection algorithm in the network virtualization environment. J Beijing U Posts Telecommun 2016; 39: 1-5.
[18] Pan YL, Qiu XS, Zhang SL. Fault diagnosis in network virtualization environment. In: Eighteenth International Conference on Telecommunication; Ayia Napa, Cyprus. New York, NY, USA: IEEE; 2011. pp. 517-522.
[19] Tang Y, Shaer E, Boutaba R. Efficient fault diagnosis using incremental alarm correlation and active investigation for Internet and overlay networks. IEEE T Netw Serv Man 2008; 5: 36-49.