Distribution Characteristics of Ice Thickness on Transmission Lines Based on BWO-SVR
DOI:
https://doi.org/10.52152/4166Keywords:
Beluga Whale Optimization, Line Ice Thickness, Support Vector Regression, Thickness Distribution Characteristics, Transmission LinesAbstract
Regarding the distribution characteristics of ice thickness on transmission lines (TLs), the traditional method has poor prediction effect in multi-dimensional and high-noise data, low computational efficiency, and is prone to local optimal solution problems. This paper proposes an enhanced and more accurate analysis method of ice thickness distribution characteristics of transmission lines combined with the BWO-SVR (Beluga Optimization-Support Vector Regression) model. The collected TLs ice thickness data were processed to remove noise data and extract features related to ice thickness. The BWO algorithm was used to optimize the hyperparameters of the SVR model, simulate the beluga whale's predation behavior, achieve global optimal search, and avoid the local optimal problem that may occur in traditional optimization methods. The optimized SVR model was used for multi-level regression analysis to integrate data from different regions and periods to improve the reliability of the prediction. The cross-validation method was used to train the model, and the SVR was adjusted based on the ice thickness distribution characteristics in different areas, so that it can maintain good adaptability in various scenarios. The experimental results show that BWO-SVR has an average MSE (Mean Square Error) of 0.13 mm in the 12-month forecast, with better prediction accuracy. The average inference time under 10 different folds is 14.97 seconds, and the computational efficiency is superior.
References
B.J. Weng, W. Gao, W.C. Zheng, G.J. Yang. Newly designed identifying method for ice thickness on high‐voltage transmission lines via machine vision. High Voltage, 2021, 6(5), 904-922. DOI: 10.1049/hve2.12086
G.Z. Huang, B. Yan, Y.J. Guo, B. Zhang, G.N. Wu. Experimental study on dynamic response characteristics of isolated‐span transmission lines after ice‐shedding. High Voltage, 2023, 8(1), 196-208. DOI: 10.1049/hve2.12219
J.X. Sun, Z.G. Zhang, Y.M. Li, Z.H. Yan, T. Zhai, et al. Distributed transmission line ice-coating recognition system based on BOTDR temperature monitoring. Journal of Lightwave Technology, 2021, 39(12), 3967-3973. DOI: 10.1109/JLT.2021.3063267
W. Huang, B. Hu, M. Shahidehpour, Y. Sun, Q.S. Sun, et al. Preventive scheduling for reducing the impact of glaze icing on transmission lines. IEEE Transactions on Power Systems, 2021, 37(2), 1297-1310. DOI: 10.1109/TPWRS.2021.3099978
Z.W. Ding, X.P. Zhang, N.M. Zou, F. Xiong, J.Y. Song, et al. Phi-OTDR based on-line monitoring of overhead power transmission line. Journal of Lightwave Technology, 2021, 39(15), 5163-5169. DOI: 10.1109/JLT.2021.3078747
H.L. Li, S.L. Ji, Y. Jiang, J.W. Chu. Parameter study and experimental analysis of a scraping de-icing concept for thin ice using end-of-life wire ropes. Journal of Mechanical Science and Technology, 2021, 35(8), 3395-3406. DOI: 10.1007/s12206-021-0713-y
L.C. Shu, Y.Q. Liu, X.L. Jiang, Q. Hu, G.H. He, et al. Three‐dimensional electric field simulation and flashover path analysis of ice‐covered suspension insulators. High Voltage, 2020, 5(3), 327-333. DOI: 10.1049/hve.2019.0095
F.J. Cui, X.J. Liu, S.X. Zhang, A.Q. Zhou, B. Huo. The impact of interphase spacers on galloping control of three-phase iced eight-bundled transmission lines: an experimental study. IEEE Transactions on Power Delivery, 2020, 36(1), 371-382. DOI: 10.1109/TPWRD.2020.2977044
A. Bahrami, M.Y. Yan, M. Shahidehpour, S. Pandey, A. Vukojevic, et al. Mobile and portable de-icing devices for enhancing the distribution system resilience against ice storms: Preventive strategies for damage control. IEEE Electrification Magazine, 2021, 9(3), 120-129. DOI: 10.1109/MELE.2021.3093639
Y.P. Hao, L. Huang, J. Wei, W. Liang, R.J. Pan, et al. The detecting system and method of quasi-distributed fiber Bragg grating for overhead transmission line conductor ice and composite insulator icing load. IEEE Transactions on Power Delivery, 2022, 38(3), 1799-1809. DOI: 10.1109/TPWRD.2022.3222774
O. Niksan, K. Colegrave, M.H. Zarifi. Battery-free, artificial neural network-assisted microwave resonator array for ice detection. IEEE Transactions on Microwave Theory and Techniques, 2022, 71(2), 698-709. DOI: 10.1109/TMTT.2022.3222194
A. Shah, O. Niksan, F. Niknahad, M.C. Jain, D. Fuleki, et al. Unlocking conformal microwave split ring resonant sensors for in-flight ice sensing. IEEE Transactions on Aerospace and Electronic Systems, 2023, 60(1), 525-536. DOI: 10.1109/TAES.2023.3328580
M. Wagih, J.J. Shi. Wireless ice detection and monitoring using flexible UHF RFID tags. IEEE Sensors Journal, 2021, 21(17), 18715-18724. DOI: 10.1109/JSEN.2021.3087326
M.Y. Yan, M. Shahidehpour, A. Paaso, L.X. Zhang, A.S. Alabdulwahab, et al. Distribution system resilience in ice storms by optimal routing of mobile devices on congested roads. IEEE Transactions on Smart Grid, 2020, 12(2), 1314-1328. DOI: 10.1109/TSG.2020.3036634
M.Q. Cai, X.H. Yang, H.J. Huang, L.S. Zhou. Investigation on galloping of D-shape iced 6-bundle conductors in transmission tower line. KSCE Journal of Civil Engineering, 2020, 24(6), 1799-1809. DOI: 10.1007/s12205-020-0595-z
H. Zhang, W.F. Wei, L.K. Pan, Z.F. Yang, G.Z. Huang, et al. Ice-covered Environmental Adaptability Assessment for Overhead Contact System in High-speed Railways. Chinese Journal of Electrical Engineering, 2024, 10(2), 70-79. DOI: 10.23919/CJEE.2024.000058
M.X. Wang, L. Li, D.M. Zhou, M. Jiang, J.Y. Chen. Overview of studies on application of distributed optical fiber sensing technology in online monitoring of transmission lines. Power System Technology, 2020, 45(9), 3591-3600. DOI: 10.13335/j.1000-3673.pst.2020.1795
M.G. Cooper, L.C. Smith, A.K. Rennermalm, M. Tedesco, R. Muthyala, et al. Spectral attenuation coefficients from measurements of light transmission in bare ice on the Greenland Ice Sheet, The Cryosphere, 2021, 15(4), 1931-1953. DOI: 10.5194/tc-15-1931-2021
Q.B. Wu, Y. Sheng, Q.H. Yu, J. Chen, W. Ma. Engineering in the rugged permafrost terrain on the roof of the world under a warming climate. Permafrost and Periglacial Processes, 2020, 31(3), 417-428. DOI: 10.1002/ppp.2059
M.A. Chandra, S.S. Bedi. Survey on SVM and their application in image classification. International Journal of Information Technology, 2021, 13(5), 1-11. DOI: 10.1007/s41870-017-0080-1
H. Hou, Y. Wang, X.L. Bai, J.S. Lv, R.J. Cui, et al. Modelling icing growth on overhead transmission lines: Current advances and future directions. Energy Conversion and Economics, 2024, 5(6), 343-357. DOI: 10.1049/enc2.12131
J. Chen, N.L. Zhang, G. Qiu, S. Gao. Icing prediction grey model for transmission line conductors based on small sample database and its application. Journal of Electric Power Science and Technology, 2024, 38(6), 267-272. DOI: 10.19781/j.issn.1673-9140.2023.06.028
Y. Yang, X.Q. Zhu, X. Song, H.H. Zhang, X. Zhang. Early warning and decision-making model of geological disaster damage of transmission lines based on intelligent online monitoring technology. International Journal of Information and Communication Technology, 2024, 24(7), 65-89. DOI: 10.1504/IJICT.2024.139109
M.H. Jia, X.H. Huang, F.J. Han, D.Q. Yan, W. Wang, et al. Multi‐view synergistic enhanced fault recording data for transmission line fault classification. IET Communications, 2024, 18(12), 713-725. DOI: 10.1049/cmu2.12784
L. Huang, S. Song, C. Liu, J.J. Wang, D. Hu, et al. Icing prediction model of transmission line based on IHHO‑HKELM. Journal of Electric Power Science and Technology, 2024, 39(4), 33-41. DOI: 10.19781/j.issn.1673-9140.2024.04.004
A.E. Sumachev, L.S. Banshchikova, S.A. Griga. Using the Methods of Neural Network Learning for Peak Water Level Prediction: A Case Study for the Rivers in the Dvina-Pechora Basin. Russian Meteorology and Hydrology, 2024, 49(4), 354-362. DOI: 10.3103/S1068373924040095
V.D. Bloshchinskiy, A.I. Andreev, L.S. Kramareva, A.N. Davidenko. Satellite Data Processing for Hydrometeorologal Research with the Use of Neural Network Technologies: The Approaches Used at Planeta State Research Center on Space Hydrometeorology. Russian Meteorology and Hydrology, 2024, 49(4), 304-312. DOI: 10.3103/S1068373924040034
A. Ahajjam, J. Putkonen, E. Chukwuemeka, R. Chance, T.J. Pasch. Predictive Analytics of Air Temperature in Alaskan Permafrost Terrain Leveraging Two-Level Signal Decomposition and Deep Learning. Forecasting, 2024, 6(1), 55-80. DOI: 10.3390/forecast6010004
V. Steidl, J.L. Bamber, X.X. Zhu. Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard. The Cryosphere, 2025, 19(2), 645-661. DOI: 10.5194/tc-19-645-2025
H.M. Jia, Q.X. Wen, D. Wu, Z. Wang, Y.H. Wang, et al. Modified beluga whale optimization with multi-strategies for solving engineering problems. Journal of Computational Design and Engineering, 2023, 10(6), 2065-2093. DOI: 10.1093/jcde/qwad089
X.Y. Chen, M.J. Zhang, M. Yang, D.G. Wang. A multi-strategy improved beluga whale optimization algorithm for constrained engineering problems. Cluster Computing, 2024, 27(10), 14685-14727. DOI: 10.1007/s10586-024-04680-4
Z.H. Wang, T. Wang, Q.F. Niu, J.F. Wu, M.W. Li, et al. Research on multiobjective capacity configuration optimization of grid‐connected wind–solar–storage microgrid system based on improved BWO algorithm. Energy Science & Engineering, 2024, 12(6), 2365-2384. DOI: 10.1002/ese3.1727
C.H. Wu, X.L. Fu, H.H. Li, X. Li, L.Q. Zhang. A method based on improved ant colony algorithm feature selection combined with GWO-SVR model for predicting chlorophyll-a concentration in Wuliangsu Lake. Water Science & Technology, 2024, 89(1), 20-37. DOI: 10.2166/wst.2023.410
Y. Chen, P. Li, W.P. Ren, X. Shen, M. Cao. Field data–driven online prediction model for icing load on power transmission lines. Measurement and Control, 2020, 53(1-2), 126-140. DOI: 10.1177/0020294019878872
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Yang Yang, Hongxia Wang, Mingguan Zhao, Xinsheng Dong (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
