用户名: 密码: 验证码:
台风灾害下用户停电区域预测及评估
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Research on Prediction and Evaluation of User Power Outage Area Under Typhoon Disaster
  • 作者:侯慧 ; 耿浩 ; 肖祥 ; 黄勇 ; 吴昊 ; 李显强 ; 于士文
  • 英文作者:HOU Hui;GENG Hao;XIAO Xiang;HUANG Yong;WU Hao;LI Xianqiang;YU Shiwen;School of Automation, Wuhan University of Technology;Electric Power Research Institute, Guangdong Power Grid Co., Ltd.;
  • 关键词:台风灾害 ; 用户停电 ; 预测评估 ; 随机森林 ; 多因素
  • 英文关键词:typhoon disaster;;user power outage;;forecast and evaluate;;random forest;;multi-factor
  • 中文刊名:DWJS
  • 英文刊名:Power System Technology
  • 机构:武汉理工大学自动化学院;广东电网有限责任公司电力科学研究院;
  • 出版日期:2019-04-16 11:22
  • 出版单位:电网技术
  • 年:2019
  • 期:v.43;No.427
  • 基金:广东省电力科学研究院科技项目(GDKJXM20162449);; Supported by Science and Technology Project of Guangdong Electric Power Research Institute(GDKJXM20162449)
  • 语种:中文;
  • 页:DWJS201906012
  • 页数:7
  • CN:06
  • ISSN:11-2410/TM
  • 分类号:98-104
摘要
台风灾害会造成电网大面积停电,对停电区域进行预测及评估具有重要意义。综合考虑气象因素、电网因素及地理因素,提出一种台风灾害下基于随机森林算法的用户停电区域预测评估方法。该方法首先采用1km×1km网格进行历史样本数据的收集整理及特征选取;其次基于随机森林算法对样本数据进行训练及验证,建立停电区域预测模型;再次,为进一步提高预测精度,对预测停电网格进行重要性评估,进而得到用户停电区域的预测评估结果。最后通过算例分析验证了所提方法的科学性及有效性。
        Typhoon disaster causes large-scale power outages in power grid, and it is of great significance to forecast and evaluate power outage areas. Considering the factors of meteorology, geography and power grid, in this paper, a user power outage area prediction and evaluation method is proposed based on random forest algorithm under typhoon disaster. Firstly, 1 km×1 km grid is used to collect and sort historical sample data. Secondly, the sample data are trained and verified, and a power outage area prediction model is established based on the random forest algorithm. Thirdly, to further improve prediction accuracy, importance of the predicted power outage grid is evaluated. In turn, the predicted evaluation result of the user power outage area is obtained. Finally, scientificity and validity of the proposed method is verified with analytical examples.
引文
[1]苏盛,陈金富,段献忠.全球暖化与电力系统的相互影响综述[J].电网技术,2010,34(2):33-40.Su Sheng,Chen Jinfu,Duan Xianzhong.Interaction between global warming and electric power systems[J].Power System Technology,2010,34(2):33-40(in Chinese).
    [2]王永明,殷自力,李琳,等.台风灾害场景下考虑运行状态的配电网风险评估方法[J].电力系统及其自动化学报,2018,30(12):60-65.Wang Yongming,Yin Zili,Li Lin,et al.Risk assessment method for distribution network considering operation state in the scene of typhoon disaster[J/OL].Proceeding of the CSU-EPSA,2018,30(12):60-65(in Chinese).
    [3]黄勇,魏瑞增,周恩泽,等.台风灾害下输电线路损毁预警方法[J].电力系统自动化,2018,42(23):142-150.Huang Yong,Wei Ruizeng,Zhou Enze,et al.Early warning method of transmission line damage under typhoon disaster[J].Automation of Electric Power Systems,2018,42(23):142-150(in Chinese).
    [4]李锐,陈颖,梅生伟,等.基于停电风险评估的城市配电网应急预警方法[J].电力系统自动化,2010,34(16):19-23,63.Li Rui,Chen Ying,Mei Shengwei,et al.An early warning method for emergency response based on power failure risk analysis of distribution systems[J].Automation of Electric Power Systems,2010,34(16):19-23,63(in Chinese).
    [5]王成龙.基于区域重要性的电力应急物资调配策略研究[D].吉林:吉林大学,2016.
    [6]郑传材,管霖,梁英杰.基于影响因素识别的架空输电线路可靠性管理系统和评估模型[J].电网技术,2009,33(10):158-163.Zheng Chuancai,Guan Lin,Liang Yingjie.Impact factor recognition based reliability management system for overhead transmission lines and its evaluation model[J].Power System Technology,2009,33(10):158-163(in Chinese).
    [7]谢云云,薛禹胜,文福拴,等.冰灾对输电线故障率影响的时空评估[J].电力系统自动化,2013,37(18):32-41.Xie Yunyun,Xue Yusheng,Wen Fushuan,et al.Space-time evaluation for impact of ice disaster on transmission line fault probability[J],Automation of Electric Power Systems,2013,37(18):32-41(in Chinese).
    [8]吴勇军,薛禹胜,陆佳政,等.山火灾害对电网故障率的时空影响[J].电力系统自动化,2016,40(3):14-20.Wu Yongjun,Xue Yusheng,Lu Jiazheng,et al.Space-time impact of forest fire on power grid fault probability[J].Automation of Electric Power Systems,2016,40(3):14-20(in Chinese).
    [9]程正刚,房鑫炎,俞国勤,等.基于脆弱性的电力应急体系灾害损失预评估[J].电力系统保护与控制,2010,38(16):68-72.Cheng Zhenggang,Fang Xinyan,Yu Guoqin,et al.Vulnerability based disaster loss pre-evaluation of power emergency system[J].Power System Protection and Control,2010,38(16):68-72(in Chinese).
    [10]吴勇军,薛禹胜,谢云云,等.台风及暴雨对电网故障率的时空影响[J].电力系统自动化,2016,40(2):20-29.Wu Yongjun,Xue Yusheng,Xie Yunyun,et al.Space-time impact of typhoon and rain storm on power grid fault probability[J].Automation of Electric Power Systems,2016,40(2):20-29(in Chinese).
    [11]薛禹胜,吴勇军,谢云云,等.停电防御框架向自然灾害预警的拓展[J].电力系统自动化,2013,37(16):1-9.Xue Yusheng,Wu Yongjun,Xie Yunyun,et al.Extension of blackout defense scheme to natural disasters early-warning[J].Automation of Electric Power Systems,2013,37(16):1-9(in Chinese).
    [12]Hou Hui,Yu Shiwen,Wang Hongbin,et al.Risk assessment and its visualization of power tower under typhoon disaster based on machine learning algorithms[J].Energies,2019,12(2):1-23.
    [13]Liu H,Davidson R A,Apanasovich T V.Statistical forecasting of electric power restoration times in hurricanes and ice storms[J].IEEETransactions on Power Systems,2007,22(4):2270-2279.
    [14]Gutwin T B.Application of BCTC standardized risk estimation model to assess risk due to ice storms[C]//8th International Conference on Probabilistic Methods Applied to Power Systems,Ames,USA,2004:970-974.
    [15]程淼海,楼俏,王琼,等.基于随机森林算法的配网抢修故障量预测方法[J].计算机系统应用,2016,25(9):137-143.Cheng Miaohai,Lou Qiao,Wang Qiong,et al.Method for fault forecasting in repair of distribution network based on the Random Forest algorithm[J].Computer Systems&Applications,2016,25(9):137-143(in Chinese).
    [16]Guikema S D,Nateghi R,Quiring S M,et al.Predicting hurricane power outages to support storm response planning[J].IEEE Access,2014(2):1364-1373.
    [17]Guikema S D,Quiring S M.Hybrid data mining regression for infrastructure risk assessment based on zero-inflated data[J].Reliability Engineering and System Safety,2012(99):178-182.
    [18]Liu Haibin,Davidsona R A,Apanasovich T V.Spatial generalized linear mixed models of electric power outages due to hurricanes and ice storms[J].Reliability Engineering&System Safety,2008,93(6):897-912.
    [19]Guikema S D,Quiring S M,Han S R.Prestorm estimation of hurricane damage to electric power distribution systems[J].Risk Anal,2010,30(12):1744-1752.
    [20]李彦斌,韩颖,张嵘,等.气象因素对电力安全事故影响的模型[J].电网技术,2013,37(6):1683-1687.Li Yanbin,Han Ying,Zhang Rong,et al.Research on impact model of meteorological factors on the power accidents[J].Power System Technology,2013,37(6):1683-1687(in Chinese).
    [21]Liu Haibin,Davidsona R A,Rosowsky D V,et al.Negative binomial regression of electric power outages in hurricanes[J].Journal of Infrastructure Systems,2005,11(4):258-267.
    [22]陆佳政,刘毓,徐勋建,等.架空输电线路山火预测预警技术[J].高电压技术,2017,43(1):314-320.Lu Jiazheng,Liu Yu,Xu Xunjian,et al.Prediction and early warning technology of wildfire nearby overhead transmission lines[J].High Voltage Engineering,2017,43(1):314-320(in Chinese).
    [23]Wanik D W,Anagnostou E N,Hartman B M,et al.Storm outage modeling for an electric distribution network in Northeastern USA[J].Natural Hazards,2015,79(2):1359-1384.
    [24]Shashaanis S,Guikema S D,Zhai Chengwei,et al.Multi-stage prediction for zero-inflated hurricane induced power outages[J].IEEEAccess,2018(6):62432-62449.
    [25]Chawla N V,Bowyer K W,Hall L O.SMOTE:synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,2002,16(1):321-357.
    [26]梁杰,陈嘉豪,张雪芹,等.基于独热编码和卷积神经网络的异常检测[J/OL].[2019-01-23].清华大学学报(自然科学版),2019:1-7.https://doi.org/10.16511/j.cnki.qhdxxb.2018.25.061.Liang Jie,Chen Jiahao,Zhang Xueqin,et al.One-hot encoding and convolutional neural network based anomaly detection[J/OL].[2019-01-23].Journal of Tsinghua University(Science and Technology),2019:1-7.https://doi.org/10.16511/j.cnki.qhdxxb.2018.25.061(in Chinese).
    [27]Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.
    [28]李建更,高志坤.随机森林针对小样本数据类权重设置[J].计算机工程与应用,2009,45(26):131-134.Li Jiangeng,Gao Zhikun.Setting of class weights in random forest for small-sample data[J].Computer Engineering and Applications,2009,45(26):131-134(in Chinese).

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700