复杂地形下的电网气象灾害识别及时空分布特征

王远谋; 唐家萍; 敖婷; 黄玉叶; 李勇

doi:10.16516/j.ceec.2025-177

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

复杂地形下的电网气象灾害识别及时空分布特征

极端气候事件下的能源与交通韧性 | 更新时间：2026-10-14

- 复杂地形下的电网气象灾害识别及时空分布特征
- Identification of Meteorological Hazards and Spatiotemporal Distribution Characteristics of Power Grids in Complex Terrain
- 南方能源建设 2026年13卷第3期页码：82-91
- 作者机构：
  
  1. 重庆市气象服务中心,重庆,401147
  2. 国网重庆市电力公司电力科学研究院,重庆,401123
- 作者简介：
  
  王远谋，ORCID: 0009-0002-6716-60321993-，女，高级工程师，硕士，主要从事气象服务应用研究工作（e-mail）njuwym9327@163.com
- 基金信息：
  
  重庆市气象局业务技术攻关项目 “电网安全气象监测预警技术研究”（YWJSGG-202410）
- DOI：10.16516/j.ceec.2025-177
  中图分类号： TM7;P429
- 纸质出版：2026
- 稿件说明：
移动端阅览
王远谋, 唐家萍, 敖婷, 等. 复杂地形下的电网气象灾害识别及时空分布特征[J]. 南方能源建设, 2026, 13(3): 82-91.

.
王远谋, 唐家萍, 敖婷, 等. 复杂地形下的电网气象灾害识别及时空分布特征[J]. 南方能源建设, 2026, 13(3): 82-91. DOI： 10.16516/j.ceec.2025-177.

. DOI： 10.16516/j.ceec.2025-177.

摘要

目的

气象灾害是影响电网安全稳定运行的重要因素，提高重庆复杂地形下的电网灾害气象防御能力至关重要。

方法

文章基于重庆市2014－2024年电网灾害事故个例及ERA5气象再分析资料，分析雷击、大风、覆冰3类灾害的时空分布规律，利用支持向量机（Support Vector Machine，SVM）与随机森林（Random Forest，RF）算法构建灾害识别模型，并检验其准确率。

结果

研究表明：雷击灾害的发生频次呈春夏季“双峰”特征，大风和覆冰则分别集中于春季和冬季；雷击及大风灾害集中于武陵山、大巴山区域，覆冰主要发生在东南部海拔800 m的区域，该区域也是多灾害叠加高发区。

结论

对比两种机器学习算法对电网灾害的识别准确率，发现RF算法对电网灾害的分类识别能力优于SVM，对大风、覆冰灾害的识别准确率超过99%；模型的输入特征中，风参数、动力参数和温湿参数对雷击和覆冰灾害识别效果的影响相当，对于大风灾害而言，温湿参数的重要性略高于另两类参数；对比不同区域和季节的识别准确率，发现东南部和东北部的识别效果整体优于其他地区，雷击、大风和覆冰灾害识别效果最好的季节分别为夏季、春季和冬季，均超过95%。

Abstract

Objective

Meteorological disaster is one of the most important factors that threaten the safe and stable operation of power grid. This paper aims to enhance the meteorological disaster prevention capability of the power grid in complex terrain of Chongqing.

Method

In this paper

the temporal and spatial distribution of lightning

wind and icing disasters was analyzed based on the weath

er-related power grid accidents and the ERA5 meteorological reanalysis data from 2014 to 2024 in Chongqing. Then the support vector machine (SVM) and random forests (RF) algorithms were used to build a recognition model

and the accuracies were calculated.

Result

The results show that the occurrence frequency of lightning disasters is characterized by double peaks in spring and summer

while wind and icing disasters are concentrated in spring and winter

respectively. Lightning and wind disasters are concentrated in Wuling and Daba Mountains

while icing mainly occurs in the southeast area with altitude over 800 m

which is also a multi-hazard superimposed high-incidence area.

Conclusion

The identification accuracies of two machine learning algorithms for power grid disasters are compared in this paper

shows that the recognition abilities of RF algorithm for power grid disasters are better than that of SVM

for the accuracies of wind and icing disasters are more than 99%. Among the input characteristics of the model

the effect of wind

dynamic and temperature-humidity parameters for the recognition accuracies of lightning and icing disasters are equivalent

and which of the temperature-humidity parameters is slightly higher than that of the other two types of parameters. Comparing the recognition accuracy in different regions and seasons

it is found that the identification accuracies of the southeast and northeast are better than that of other regions

and the best seasons for the identification of lightning

wind and icing disasters are summer

spring and winter

respectively

which are all more than 95%.

关键词

Keywords

references

ZUO J, ZHONG Y S, BAO B, et al. A multi-objective optimization model of power grid operation and dispatching considering uncertainty of new energy [J]. Power system and clean energy, 2025, 41(3): 152-158. DOI: 10.3969/j.issn.1674-3814.2025.03.018.

LU M, GUO Z M, MENG G J, et al. Refined meteorological risk modeling of transmission lines and online warning and defense strategies of meteorological disasters [J]. Journal of electric power science and technology, 2024, 39(1): 208-217. DOI: 10.19781/j.issn.1673-9140.2024.01.021.

ZHANG X L, SUN A C, HAO S P, et al. Multi-machine cooperative control strategy of wind farm participating in power grid frequency modulation [J]. Power generation technology, 2024, 45(3): 448-457. DOI: 10.12096/j.2096-4528.pgt.23068.

WANG Y T, MO W B, BAI M Y, et al. Lightning interference identification method based on voltage traveling wave waveform characteristics for flexible DC transmission lines [J]. Power system protection and control, 2024, 52(8): 31-44. DOI: 10.19783/j.cnki.pspc.230947.

BAI Y Q, YIN H, WU G L, et al. Parameters selection for lightning protection calculation for transmission line in Chongqing grid [J]. High voltage engineering, 2007, 33(12): 162-163, 172. DOI: 10.13336/j.1003-6520.hve.2007.12.011.

JIANG X L, DU Z, WANG H Y, et al. Icing features of wire in Chongqing region [J]. High voltage engineering, 2011, 37(12): 3065-3069. DOI: 10.13336/j.1003-6520.hve.2011.12.034.

LI G F, ZHANG P, LUH P B, et al. Risk analysis for distribution systems in the Northeast U. S. under wind storms [J]. IEEE transactions on power systems, 2014, 29(2): 889-898. DOI: 10.1109/TPWRS.2013.2286171.

RIOS M A, KIRSCHEN D S, JAYAWEERA D, et al. Value of security: modeling time-dependent phenomena and weather conditions [J]. IEEE transactions on power systems, 2002, 17(3): 543-548. DOI: 10.1109/tpwrs.2002.800872.

WU W Q. Construction of power grid disaster risk warning model based on WebGIS technology [J]. Techniques of automation and applications, 2025, 44(9): 79-83. DOI: 10.20033/j.1003-7241.(2025)09-0079-05.

FANG Y Q, YIN F, GE N C, et al. Optimization of extreme natural disaster warning mechanism for power grid based on cluster analysis and time series prediction [J]. Electrical automation, 2024, 46(6): 79-81, 85. DOI: 10.3969/j.issn.1000-3886.2024.06.022.

SUN X B, ZHANG W Y, ZHANG J Q, et al. The relationship between climate characteristics of wire icing days in Liaoning Province and atmospheric general circulation anomalies [J]. Journal of meteorology and environment, 2021, 37(3): 125-131. DOI: 10.3969/j.issn.1673-503X.2021.03.017.

KOU X S, WANG D L, KE J Y, et al. Risk early warning method of severe convective disasters for transmission lines based on radar echo and LSTM [J]. Electric power engineering technology, 2024, 43(5): 189-198. DOI: 10.12158/j.2096-3203.2024.05.019.

WANG B L, SONG L L, YUAN C H, et al. Study of meteorological indices for transmission line galloping in Henan power grid [J]. Meteorological monthly, 2017, 43(1): 108-114. DOI: 10.7519/j.issn.1000-0526.2017.01.012.

LI W, MA J, WANG S R, et al. Research on prediction and warning of overhead line icing under refined meteorological elements [J]. Power systems and big data, 2018, 21(2): 1-7. DOI: 10.19317/j.cnki.1008-083x.2018.02.001.

FU X B, HOU J Q, LI B J, et al. A two-modal weather classification method and its application in photovoltaic power probability prediction [J]. Power generation technology, 2024, 45(2): 299-311. DOI: 10.12096/j.2096-4528.pgt.23017.

MA X H. Analysis of meteorological conditions for an ice accretion event on high-voltage transmission lines in Zhaotong [J]. Journal of agricultural catastrophology, 2024, 14(3): 203-206. DOI: 10.3969/j.issn.2095-3305.2024.03.067.

FU G Q, CAO X. The characteristic analysis of thunderstorm gale and electrical network disaster in Hebei [J]. Meteorological monthly, 2012, 38(3): 353-357. DOI: 10.7519/j.issn.1000-0526.2012.03.014.

WANG C H, YAO Y Q, XIA L Z, et al. Cause of the galloping in Anhui province along the Yangtze River in early 2018 [J]. Plateau meteorology, 2019, 38(5): 1091-1098. DOI: 10.7522/j.issn.1000-0534.2018.00141.

WEI R Z. The characteristic of gale in Guangdong Province and gale precaution for power grid [D]. Nanjing: Nanjing University, 2016. DOI: 10.27235/d.cnki.gnjiu.2016.000258.

GAO S, XU P H, CHEN Z H. Wind speed multi-mode ensemble forecasting for wind farms based on machine learning [J]. Southern energy construction, 2024, 11(1): 85-95. DOI: 10.16516/j.ceec.2024.1.09.

LI D Q. Research on transmission line ice cover prediction method based on multi-dimensional impact coefficient optimized support vector machine [D]. Changchun: Changchun University of Technology, 2025. DOI: 10.27805/d.cnki.gccgy.2025.000389.

ZHANG X G. Introduction to statistical learning theory and support vector machines [J]. Acta automatica sinica, 2000, 26(1): 32-42. DOI: 10.16383/j.aas.2000.01.005.

DING S F, QI B J, TAN H Y. An overview on theory and algorithm of support vector machines [J]. Journal of University of Electronic Science and Technology of China, 2011, 40(1): 1-10. DOI: 10.3969/j.issn.1001-0548.2011.01.001.

DONG S S, HUANG Z X. A brief theoretical overview of random forests [J]. Journal of integration technology, 2013, 2(1): 1-7.

LIU X Y, GONG Y F, REN Q, et al. Synergistic effect of Tibetan plateau severe convection and Tibetan plateau vortex eastward-propagating on the downstream heavy precipitation process [J]. Plateau and mountain meteorology research, 2024, 44(1): 10-20. DOI: 10.3969/j.issn.1674-2184.2024.01.002.

AI Z Z, DONG Y S, XU X, et al. Effect of topography of eastern Qinghai-Xizang Plateau on a rainstorm occurred in northeastern Sichuan Basin [J]. Journal of Nanjing University (natural science edition), 2024, 60(2): 209-217. DOI: 10.13232/j.cnki.jnju.2024.02.003.

LI R P, WANG X M, LI S W, et al. Effect of sub-synoptic scale system on environment field of strong convection under the background of a cold vortex [J]. Journal of marine meteorology, 2024, 44(1): 76-87. DOI: 10.19513/j.cnki.hyqxxb.20221030001.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

复杂地形风电场微观选址实践探讨

高比例风光集群并网多时间尺度惯量协同与暂态稳定优化控制

基于双工质气体压缩储能的供气系统

基于工程实践的分布式构网型储能系统控制策略与应用

Cu/Al共掺杂P2-Na0.72Fe0.3Mn0.7O2正极材料的制备及其电化学性能