TY - GEN
T1 - Application of Distributed Brillouin Optical Fiber Sensor and MVO-DBSCAN for OPGW Outlier Identification
AU - Xia, Meng
AU - Tang, Xiaohui
AU - Wang, Ying
AU - Li, Can
AU - Wei, Yong
AU - Zhang, Jiaju
AU - Du, Xuexin
AU - Dong, Yongkang
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - The entire transmission line of the optical fiber composite overhead ground wire (OPGW) is formed by splicing multiple optical cable segments in the splice box. The Brillouin frequency shift change at the splice point and the density based spatial clustering of applications with noise (DBSCAN) algorithm can be used to realize the clustering of the Brillouin frequency shift, and then locate the splice point and outliers. However, the DBSCAN algorithm is very sensitive to the input parameters, which can easily cause poor clustering effect. In this paper, grid search is used to optimize the parameter selection of DBSCAN algorithm, and the effective parameter interval is obtained. The Multi-Verse Optimizer (MVO) algorithm is further used to obtain the optimal solution of DBSCAN parameters, and the actual line data is used to verify the effectiveness of DBSCAN after MVO optimization.
AB - The entire transmission line of the optical fiber composite overhead ground wire (OPGW) is formed by splicing multiple optical cable segments in the splice box. The Brillouin frequency shift change at the splice point and the density based spatial clustering of applications with noise (DBSCAN) algorithm can be used to realize the clustering of the Brillouin frequency shift, and then locate the splice point and outliers. However, the DBSCAN algorithm is very sensitive to the input parameters, which can easily cause poor clustering effect. In this paper, grid search is used to optimize the parameter selection of DBSCAN algorithm, and the effective parameter interval is obtained. The Multi-Verse Optimizer (MVO) algorithm is further used to obtain the optimal solution of DBSCAN parameters, and the actual line data is used to verify the effectiveness of DBSCAN after MVO optimization.
KW - Brillouin
KW - DBSCAN
KW - OPGW
KW - multi-verse optimizer
KW - outlier identification
KW - tower positioning
UR - https://www.scopus.com/pages/publications/85137850178
U2 - 10.1109/ICAIT56197.2022.9862632
DO - 10.1109/ICAIT56197.2022.9862632
M3 - 会议稿件
AN - SCOPUS:85137850178
T3 - 2022 IEEE 14th International Conference on Advanced Infocomm Technology, ICAIT 2022
SP - 236
EP - 242
BT - 2022 IEEE 14th International Conference on Advanced Infocomm Technology, ICAIT 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IEEE International Conference on Advanced Infocomm Technology, ICAIT 2022
Y2 - 8 July 2022 through 11 July 2022
ER -