Distribution Transformer Outage Prediction Based on Logistic Fast Minimum Error Entropy Algorithm

doi:10.12096/j.2096-4528.pgt.21006

Abstract

Abstract:

In order to improve the speed and accuracy of distribution transformer outage prediction, a distribution transformer outage prediction method based on Logistic fast minimum error entropy algorithm was proposed. Aiming at the problem that the basic minimum entropy regression algorithm runs too slowly, a fast minimum error entropy algorithm was proposed, which can keep the same regression effect as the minimum entropy regression, and greatly reduce the running time of the algorithm. In view of the application of Logistic regression in outage prediction, a fast minimum error entropy regression algorithm based on logistic was proposed, and the weight of distribution transformer was selected. The overload duration, maximum active load rate, average active load rate, average three-phase unbalance degree and heavy three-phase unbalance degree were used as the characteristic variable data of distribution transformer outage prediction. A distribution transformer outage prediction model was established, and the effect was found to be better than Logistic regression in the comparative experiment.

Key words: Logistic fast minimum error entropy, distribution transformer, outage prediction

CLC Number:

TK 01

Zhong XU, Le LUAN, Wenxiong MO, Simin LUO, Zonglin YE, Chao CHEN, Xuanda LAI, Minghui XIE. Distribution Transformer Outage Prediction Based on Logistic Fast Minimum Error Entropy Algorithm[J]. Power Generation Technology, 2022, 43(2): 313-319.

Figures/Tables 5

References 24

1	尤田柱，鄢志平．配电网安全防护技术[M]．北京：中国电力出版社，2015：125-128．
	YOU T Z， YAN Z P ．Distribution network security protection technology[M]．Beijing：China Electric Power Press，2015：125-128．
2	刘建伟，李学斌，刘晓鸥．有源配电网中分布式电源接入与储能配置[J/OL]．发电技术：1-9[2022-02-14]．．
	LIU J W， LI X B， LIU X O ．Distributed generation access and energy storage configuration in active distribution network[J/OL]．Power Generaton Technology：1-9[2022-02-14]．．
3	张志华，刘健，程林，等．基于串联电抗器的城市配电线路全线速断保护[J]．智慧电力，2020，48(1)：111-117． doi:10.1109/spies48661.2020.9243102
	ZHANG Z H， LIU J， CHENG L，et al ．The whole line quick-trip protection of city distribution line based on series reactor allocation[J]．Smart Power，2020，48(1)：111-117． doi:10.1109/spies48661.2020.9243102
4	宋云亭，张东霞，吴俊玲，等．国内外城市配电网供电可靠性对比分析[J]．电网技术，2008，32(23)：13-18．
	SONG Y T， ZHANG D X， WU J L，et al ．Analysis of big data technology in power distribution system and typical applications[J]．Power System Technology，2008，32(23)：13-18．
5	张坤，党东升，马艳霞，等．主动式配电网电源分区布点规划关键技术研究[J]．电网与清洁能源，2020，36(3)：42-48． doi:10.3969/j.issn.1674-3814.2020.03.007
	ZHANG K， DANG D S， MA Y X，et al ．Research on key technologies of power supply distribution zones planning for active distribution network[J]．Power System and Clean Energy，2020，36(3)：42-48． doi:10.3969/j.issn.1674-3814.2020.03.007
6	肖勇，陆文升，李云涛，等．城市配电网发展形态指标体系及其评估方法研究[J]．电力系统保护与控制，2021，49(1)：62-71．
	XIAO Y， LU W S， LI Y T，et al ．Research on index system and its evaluation methods of urban distribution network development form[J]．Power System Protection and Control，2021，49(1)：62-71．
7	胡丽娟，刁赢龙，刘科研，等．基于大数据技术的配电网运行可靠性分析[J]．电网技术，2017，41(1)：265-271． doi:10.1109/cyberc.2018.00042
	HU L J， DIAO Y L， LIU K Y，et al ．Operational reliability analysis of distribution network based on big data technology[J]．Power System Technology，2017，41(1)：265-271． doi:10.1109/cyberc.2018.00042
8	费思源．大数据技术在配电网中的应用综述[J]．中国电机工程学报，2018，38(1)：85-96．
	FEI S Y ．Overview of application of big data technology in power distribution system[J]．Proceedings of the CSEE，2018，38(1)：85-96．
9	冷华，童莹，李欣然，等．配电网运行状态综合评估方法研究[J]．电力系统保护与控制，2017，45(1)：53-59．
	LENG H， TONG Y， LI X R，et al ．Comprehensive evaluation method research of the operation state in distributed network[J]．Power System Protection and Control，2017，45(1)：53-59．
10	段穰达．有源配网后评价指标体系及其综合评价方法[J]．发电技术，2021，42(1)：86-93． doi:10.12096/j.2096-4528.pgt.20102
	DUAN R D ．A post-evaluation index system of active distribution network project and its comprehensive evaluation method[J]．Power Generation Technology，2021，42(1)：86-93． doi:10.12096/j.2096-4528.pgt.20102
11	李延真，郭英雷，彭博，等．基于多时间尺度状态估计的配电网实时态势预测[J]．电力工程技术，2020，39(2)：127-134． doi:10.12158/j.2096-3203.2020.02.018
	LI Y Z， GUO Y L， PENG B，et al ．Real-time situation prediction of distribution network based on multi-time scale state estimation[J]．Electric Power Engineering Technology，2020，39(2)：127-134． doi:10.12158/j.2096-3203.2020.02.018
12	邢晓敏，徐海瑞，廖孟柯，等．基于云模型和D-S证据理论的配电终端健康状态综合评估方法[J]．电力系统保护与控制，2021，49(13)：72-81．
	XING X M， XU H R， LIAO M K，et al ．Comprehensive evaluation method of distribution terminal units health status based on cloud model and D-S evidence theory[J]．Power System Protection and Control，2021，49(13)：72-81．
13	蒋碧莺，荣建，张军．Logistic分类算法下的配电网故障识别技术研究[J]．电工技术，2018(24）：70-71． doi:10.3969/j.issn.1002-1388.2018.24.032
	JIANG B Y， RONG J， ZHANG J ．Research on fault identification technology of distribution network based on logistic classification algorithm[J]．Electric Engineering，2018(24)：70-71． doi:10.3969/j.issn.1002-1388.2018.24.032
14	陈颖，刘冰倩，朱淑娟，等．极端气象条件下配电网大范围停电贝叶斯网络建模和停电概率预测方法[J]．供用电，2019，36(7)：30-34．
	CHEN Y， LIU B Q， ZHU S J，et al ．Bayesian network modeling and power outage probability prediction method for largescale power outages in distribution networks under extreme weather conditions[J]．Distribution & Utilization，2019，36(7)：30-34．
15	侯慧，耿浩，肖祥，等．台风灾害下用户停电区域预测及评估[J]．电网技术，2019，43(6）：1948-1954．
	HOU H， GENG H， XIAO X，et al. Research on prediction and evaluation of user power outage area under typhoon disaster[J]．Power System Technology，2019，43(6)：1948-1954．
16	严道波，杨勇，邱丹，等．基于天气因素和XGBoost算法的配电线路故障停电预测[J]．电力与能源，2019，40(2)：168-171．
	YAN D B， YANG Y， QIU D，et al ．Failure prediction of distribution line based on weather factors and XGBoost algorithm[J]．Power and Energy，2019，40(2)：168-171．
17	MENSAH A F， DUENAS-OSORIO L ．Outage predictions of electric power systems under Hurricane winds by Bayesian networks[C]//International Conference on Probabilistic Methods Applied to Power Systems．Durham，UK：IEEE，2014：1-6． doi:10.1109/pmaps.2014.6960677
18	WANIK D W， PARENT J R， ANAGNOSTOU E N，et al ．Using vegetation management and LiDAR-derived tree height data to improve outage predictions for electric utilities[J]．Electric Power Systems Research，2017，146：236-245． doi:10.1016/j.epsr.2017.01.039
19	PRINCIPE JOSÉ C ．Information theoretic learning：renyi's entropy and kernel perspectives[M]．Berlin：Springer Publishing Company，2010． doi:10.1007/978-1-4419-1570-2
20	RENYI A ．On measures of entropy and information[C]//Proceedings of the 4th Berkeley Symposium on Mathematics，Statistics and Probability．Berkeley，USA：University of California 1，1960：158-174．
21	WEIDEMANN H， STEAR E ．Entropy analysis of estimating systems[J]．IEEE Transactions on Information Theory．1970，16(3)：264-270． doi:10.1109/tit.1970.1054444
22	Thomas M C， Thomas J A ．信息论基础[M]．阮吉寿，张华，译．北京：机械工业出版社，2005．
	THOMAS M C， THOMAS J A ．Elements of information theory[M]．Beijing：China Machine Press，2005．
23	WALLACE D L ．Asymptotic approximations to distributions[J]．Annals of Mathematical Statistics．1958，29(3)：635-654． doi:10.1214/aoms/1177706528
24	HU T， WU Q， ZHOU D X ．Convergence of gradient descent for minimum error entropy principle in linear regression[J]．IEEE Transactions on Signal Processing，2016，64(12)：6571-6579． doi:10.1109/tsp.2016.2612169

样本数量	平均运行时间/s		最快运行时间/s
样本数量	最小误差熵	快速最小误差熵	最小误差熵	快速最小误差熵
100	103.89	0.040 1	77.77	0.015 6
200	384.31	0.058 0	310.05	0.031 2
300	801.52	0.076 9	654.21	0.046 8
400	1 430.61	0.100 0	1 254.12	0.046 8
500	2 306.24	0.110 4	2 072.50	0.062 4

样本数量	平均运行时间/s		最快运行时间/s
样本数量	最小误差熵	快速最小误差熵	最小误差熵	快速最小误差熵
100	103.89	0.040 1	77.77	0.015 6
200	384.31	0.058 0	310.05	0.031 2
300	801.52	0.076 9	654.21	0.046 8
400	1 430.61	0.100 0	1 254.12	0.046 8
500	2 306.24	0.110 4	2 072.50	0.062 4

序号	标准化后的重过载时长	最大有功负载率/%	平均有功负载率/%	平均三相不平衡度/%	标准化后的重三相不平衡度	模型输出结果
1	0	74.98	78.06	52.60	0	1
2	0.010 53	87.14	46.89	20.17	17.570 000	1
3	0.125 70	131.58	32.45	38.16	0.012 300	0
4	0.025 96	97.10	29.74	23.15	0.001 366	0
5	0.083 33	123.86	35.80	35.15	0.002 732	0

序号	标准化后的重过载时长	最大有功负载率/%	平均有功负载率/%	平均三相不平衡度/%	标准化后的重三相不平衡度	模型输出结果
1	0	74.98	78.06	52.60	0	1
2	0.010 53	87.14	46.89	20.17	17.570 000	1
3	0.125 70	131.58	32.45	38.16	0.012 300	0
4	0.025 96	97.10	29.74	23.15	0.001 366	0
5	0.083 33	123.86	35.80	35.15	0.002 732	0

序号	标准化后的重过载时长	最大有功负载率/%	平均有功负载率/%	平均三相不平衡度/%	标准化后的重三相不平衡度	实际停电情况	模型预测输出	输出停电概率
1	0.095 62	115.92	31.37	34.44	0	0	0	0.000 0
2	0.019 13	97.14	25.38	26.40	0	0	0	0.000 0
3	0.062 84	125.54	35.19	32.72	0.120 2	0	0	0.000 0
4	0.124 50	136.80	31.84	31.84	0.019 91	1	0	0.000 0
5	0.278 70	95.22	100.90	34.27	0	1	1	1.000 0