Auxiliary Fault Location on Commercial Equipment Based on Supervised Machine Learning

doi:10.12142/ZTECOM.2022S1002

ZTE Communications ›› 2022, Vol. 20 ›› Issue (S1): 7-15.DOI: 10.12142/ZTECOM.2022S1002

• Research Paper • Previous Articles Next Articles

Auxiliary Fault Location on Commercial Equipment Based on Supervised Machine Learning

ZHAO Zipiao¹, ZHAO Yongli¹(), YAN Boyuan¹, WANG Dajiang²

^1.State Key Laboratory of Information Photonics and Optical Communictions, Beijing University of Posts and Telecomunications, Beijing 100876, China
^2.ZTE Corporation, Shenzhen 518057, China

Received:2020-04-01 Online:2022-01-25 Published:2022-03-01
About author:ZHAO Zipiao received the B.S. degree in communication engineering from Hebei Univiversity of Engineering, China in 2017. She is currently a Ph.D. candidate of Beijing Univiversity of Posts and Telecomunications (BUPT), China. Her research focuses on software defined optical networks and machine learning in optiacal networks.|ZHAO Yongli (yonglizhao@bupt.edu.cn) received the B.S. degree in communication engineering and Ph.D. degree in electromagnetic field and microwave technology from Beijing Univiversity of Posts and Telecomunications (BUPT), China in 2005 and 2010, respectively. He is currently a professor of the Institute of Information Photonics and Optical Communications, BUPT. From Jan. 2016 to Jan. 2017, he was a visiting associate professor with UC Davis, USA. He has published more than 300 papers in international journals and conference. Since 2015, he has become a senior member of IEEE. His research focuses on software defined optical networking, elastic optical networks, datacenter networking, and optical network security.|YAN Boyuan received the B.S. degree in communication engineering from Beijing Univiversity of Posts and Telecomunications (BUPT), China in 2015. He is currently pursuing his Ph.D. degree with BUPT. His research interests include software defined optical networking, service function chaining, and network resource allocation with machine learning.|WANG Dajiang received B.S. and M.S. degrees in mechanical and electronic engineering from East China University of Science and Technology , China, and Shanghai University, China in 1996 and 2001 respectively. By far, he has been working with ZTE Corporation for more than 17 years and persistently doing the job related to OTN intelligent management and control. Now he is the Director of Intelligent Optical Network Product Planning in ZTE and mainly responsible for researching autonomous network architecture and solution on OTN. In total, as the chief author, he has issued more than 60 patents in the fields of WASON, SDON, and AN, most of which had been authorized by CNIPA and USPTO and commercialized in ZTE OTN products. Meanwhile, cooperating with other experts in the field, he has also published more than 20 papers in international influential journals and conferences.
Supported by:
National Natural Science Foundation of China (NSFC)(61822105);ZTE Industry?Academia?Research Cooperation Funds(2018110016001047)

Abstract

Abstract:

As the fundamental infrastructure of the Internet, the optical network carries a great amount of Internet traffic. There would be great financial losses if some faults happen. Therefore, fault location is very important for the operation and maintenance in optical networks. Due to complex relationships among each network element in topology level, each board in network element level, and each component in board level, the concrete fault location is hard for traditional method. In recent years, machine learning, especially deep learning, has been applied to many complex problems, because machine learning can find potential non-linear mapping from some inputs to the output. In this paper, we introduce supervised machine learning to propose a complete process for fault location. Firstly, we use data preprocessing, data annotation, and data augmentation in order to process original collected data to build a high-quality dataset. Then, two machine learning algorithms (convolutional neural networks and deep neural networks) are applied on the dataset. The evaluation on commercial optical networks shows that this process helps improve the quality of dataset, and two algorithms perform well on fault location.

Key words: optical network, fault location, supervised machine learning

ZHAO Zipiao, ZHAO Yongli, YAN Boyuan, WANG Dajiang. Auxiliary Fault Location on Commercial Equipment Based on Supervised Machine Learning[J]. ZTE Communications, 2022, 20(S1): 7-15.

Figures/Tables 7

Figure 1 Data preprocessing for collected alarm data

Figure 2 CNN and DNN architecture

Figure 3 Commercial optical network for evaluation

Table 1 Frequent item using FP-growth

Transaction ID	Included Alarm Data	Filtered Alarm Data
001	B, A, H, J, P	A(5), B(3)
002	A, D, C, W, U, V, F, E	A(5), C(4), D(3), F(3), E(3)
003	A	A(5)
004	B, C, N, O, E	C(4), B(3)
005	D, B, C, A, Q, F, P	A(5), C(4), B(3), D(3), F(3)
006	D, A, C, G, Q, E, F, M	A(5), C(4), D(3), E(3), F(3)

Figure 4 Results of building an available dataset

Figure 5 Evaluation results for CNN and DNN model

Figure 6 Comparison of fault location accuracy and fault location delay between different algorithms

References 27

1	RAFIQUE D, VELASCO L. Machine learning for network automation: overview, architecture, and applications [J]. Journal of optical communications and networking, 2018, 10(10): D126. DOI: 10.1364/jocn.10.00d126 DOI URL
2	BISHOP C M. Pattern Recognition and Machine Learning [M]. New York, USA: Springer, 2006
3	TALEBI H A, KHORASANI K, TAFAZOLI S. A recurrent neural-network-based sensor and actuator fault detection and isolation for nonlinear systems with application to the satellite’s attitude control subsystem [J]. IEEE transactions on neural networks, 2009, 20(1): 45–60. DOI: 10.1109/TNN.2008.2004373 DOI URL
4	CARDOSO G, ROLIM J G, ZURN H H. Identifying the primary fault section after contingencies in bulk power systems [J]. IEEE transactions on power delivery, 2008, 23(3): 1335–1342. DOI: 10.1109/TPWRD.2008.916743 DOI URL
5	FANG H Z, SHI H, DONG Y F, et al. Spacecraft power system fault diagnosis based on DNN [C]//Prognostics and System Health Management Conference. IEEE, 2017: 1–5. DOI: 10.1109/PHM.2017.8079271 DOI URL
6	MUSUMECI F, ROTTONDI C, NAG A, et al. An overview on application of machine learning techniques in optical networks [J]. IEEE communications surveys & tutorials, 2019, 21(2): 1383–1408. DOI: 10.1109/COMST.2018.2880039 DOI URL
7	RUIZ M, FRESI F, VELA A P, et al. Service-triggered failure identification/localization through monitoring of multiple parameters [C]//The 42nd European Conference on Optical Communication. ECOC, 2016: 1–3
8	TEMBO S R, VATON S, COURANT J L, et al. A tutorial on the EM algorithm for Bayesian networks: Application to self-diagnosis of GPON-FTTH networks[C]//2016 International Wireless Communications and Mobile Computing Conference. IEEE, 2016: 369–376. DOI: 10.1109/IWCMC.2016.7577086 DOI URL
9	GOSSELIN S, COURANT J L, TEMBO S R, et al. Application of probabilistic modeling and machine learning to the diagnosis of FTTH GPON networks [C]//2017 International Conference on Optical Network Design and Modeling. IEEE, 2017: 1–3. DOI: 10.23919/ONDM.2017.7958529 DOI URL
10	CHRISTODOULOPOULOS K, SAMBO N, VARVARIGOS E. Exploiting network kriging for fault localization [C]//Optical Fiber Communication Conference. OSA, 2016: 1–3. DOI: 10.1364/ofc.2016.w1b.5 DOI URL
11	VELA A P, RUIZ M, FRESI F, et al. BER degradation detection and failure identification in elastic optical networks [J]. Journal of lightwave technology, 2017, 35(21): 4595–4604. DOI: 10.1109/JLT.2017.2747223 DOI URL
12	VELA A P, SHARIATI B, RUIZ M, et al. Soft failure localization during commissioning testing and lightpath operation [J]. IEEE/OSA journal of optical communications and networking, 2018, 10(1): A27–A36. DOI: 10.1364/JOCN.10.000A27 DOI URL
13	SHAHKARAMI S, MUSUMECI F, CUGINI F, et al. Machine-learning-based soft-failure detection and identification in optical networks [C]//Optical Fiber Communication Conference. OSA, 2018: 1–3. DOI: 10.1364/ofc.2018.m3a.5 DOI URL
14	RAFIQUE D, SZYRKOWIEC T, AUTENRIETH A, et al. Analytics-driven fault discovery and diagnosis for cognitive root cause analysis [C]//Optical Fiber Communication Conference. OSA, 2018: 1–3. DOI: 10.1364/ofc.2018.w4f.6 DOI URL
15	ABADI M, BARHAM P, CHEN J, et al. TensorFlow: a system for large-scale machine learning [C]//The 12th USENIX Conference on Operating Systems Design and Implementation. USENIX, 2016: 256–283
16	ZHAO Y L, YAN B Y, LIU D M, et al. SOON: self-optimizing optical networks with machine learning [J]. Optics express, 2018, 26(22): 28713. DOI: 10.1364/oe.26.028713 DOI URL
17	ZHAO Y L, YAN B Y, LI Z T, et al. Coordination between control layer AI and on-board AI in optical transport networks [J]. Journal of optical communications and networking, 2019, 12(1): A49. DOI:10.1364/jocn.12.000a49 DOI URL
18	YAN B Y, ZHAO Y L, RAHMAN S, et al. Dirty-data-based alarm prediction in self-optimizing large-scale optical networks [J]. Optics express, 2019, 27(8): 10631. DOI: 10.1364/oe.27.010631 DOI URL
19	KIM W, CHOI B, HONG E, et al. A taxonomy of dirty data [J]. Data mining & knowledge discovery, 2003, 7(1):81-99. DOI: 10.1023/A:1021564703268 DOI URL
20	WANG B J, ZHAN Y. A survey and performance evaluation on sliding window for data stream [C]//The 3rd International Conference on Communication Software and Networks. IEEE, 2011: 654–657. DOI:10.1109/ICCSN.2011.6014977 DOI URL
21	HAN J W, PEI J, YIN Y W. Mining frequent patterns without candidate generation [C]//The 2000 ACM SIGMOD International Conference on Management of Data. ACM, 2000. DOI:10.1145/342009.335372. DOI URL
22	BORGELT C. An implementation of the FP-growth algorithm [C]//The 1st International Workshop on Open Source Data Mining Frequent Pattern Mining Implementations. ACM, 2005: DOI: 10.1145/1133905.1133907 DOI URL
23	HAN J, MORAGA C. The Influence of the Sigmoid Function Parameters on the Speed of Backpropagation Learning [C]//From Natural to Artificial Neural Computation, International Workshop on Artificial Neural Networks. IEEE: 1995.
24	NAIR V, HINTON G E. Rectified linear units improve restricted boltzmann machines vinod nair [C]//International Conference on International Conference on Machine Learning. IEEE, 2010
25	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84–90. DOI: 10.1145/3065386 DOI URL
26	HUANG Y, SUN S Y, DUAN X S, et al. A study on deep neural networks framework [C]//The IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference. IEEE, 2016: 1519–1522. DOI: 10.1109/IMCEC.2016.7867471 DOI URL
27	LAUZON F Q. An introduction to deep learning [C]//The 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA). IEEE, 2012: 1438–1439. DOI: 10.1109/ISSPA.2012.6310529 DOI URL

[1]	HU Jin, LIU Xu, ZHU Songlin, ZHUANG Yudi, WU Yuejun, XIA Xiang, HE Zuyuan. Waveguide Bragg Grating for Fault Localization in PON [J]. ZTE Communications, 2024, 22(2): 94-98.
[2]	LI Zhongya, CHEN Rui, HUANG Xingang, ZHANG Junwen, NIU Wenqing, LU Qiuyi, CHI Nan. SVM for Constellation Shaped 8QAM PON System [J]. ZTE Communications, 2022, 20(S1): 64-71.
[3]	ZHANG Weiliang, YUAN Liquan. Higher Speed Passive Optical Networks for Low Latency Services [J]. ZTE Communications, 2021, 19(2): 61-66.
[4]	WANG Hua, ZHAO Yongli, WANG Dajiang, WANG Jiayu, WANG Zhenyu. A Quantum Key Re-Transmission Mechanism for QKD-Based Optical Networks [J]. ZTE Communications, 2018, 16(3): 52-58.
[5]	LI Yajie, ZHAO Yongli, ZHANG Jie, WANG Dajiang, WANG Jiayu. Software Defined Optical Networks and Its Innovation Environment [J]. ZTE Communications, 2016, 14(4): 50-57.
[6]	Xiangjun Xin. The Key Technology in Optical OFDM-PON [J]. ZTE Communications, 2012, 10(1): 40-44.
[7]	Li Mo, Fei Yuan, and Jian Yang. Mobile Backhaul Solutions [J]. ZTE Communications, 2011, 9(4): 63-67.

Auxiliary Fault Location on Commercial Equipment Based on Supervised Machine Learning

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 27

Related Articles 7

Recommended Articles

Metrics