基于支持向量机的发/输电系统快速蒙特卡洛可靠性评估方法

doi:10.11959/j.issn.1000-0801.2019155

Abstract

Abstract:

A fast Monte Carlo reliability evaluation method for composite power system based on support vector machine (SVM) was proposesd.Firstly,sample data for training the SVM model was obtained by enumerating component failures and calculating the corresponding minimum load shedding.Then,the SVM algorithm was used to mine the nonlinear mapping relationship between component failures and minimum load shedding,and the minimum load shedding estimation model was trained.Finally,the model was combined with the Monte Carlo simulation.By randomly sampling component states,for each state,the estimation model obtained by the training directly gave the minimum load shedding,thereby achieving a rapid assessment of the reliability of the composite power system.The proposed method is applied to the IEEE RTS 79 system,which verifies its effectiveness.

Key words: support vector machine, fast Monte Carlo simulation, reliability evaluation, composite power system

CLC Number:

TM712

LEI Yuxiao,LI Gengfeng,HUANG Yuxiong,BIE Zhaohong. Support vector machine based fast Monte Carlo reliability evaluation method for composite power system[J]. Telecommunications Science, 2019, 35(6): 15-24.

Figures/Tables 11

References 17

[1]	王勇 . 电力系统运行可靠性分析与评价理论研究[D]. 济南：山东大学, 2012.
	WANG Y . Theoretical research on reliability analysis and eval-uation of power system operation[D]. Jinan:Shandong Univer-sity, 2012.
[2]	汪隆君 . 电网可靠性评估方法及可靠性基础理论研究[D]. 广州:华南理工大学, 2010.
	WANG L J . Research on reliability evaluation method and basic reliability theory of power grid[D]. Guangzhou:South China University of Technology, 2010.
[3]	别朝红, 王建华, 王锡凡 . 一种减小蒙特卡洛模拟方差的新方法[J]. 中国电力, 1999(12): 43-46.
	BIE Z H , WANG J H , WANG X F . A new method for reducing monte carlo analog variance[J]. China Electric Power, 1999(12): 43-46.
[4]	昝贵龙, 王主丁, 李秋燕 ,等. 基于状态空间截断和隔离范围推导的高压配电网可靠性评估[J]. 电力系统自动化, 2017,41(13): 79-85.
	ZAN G L , WANG Z D , LI Q Y ,et al. High voltage distribution network reliability evaluation based on state space truncation and isolation scope derivation[J]. Automation of Electric Power Systems, 2017,41(13): 79-85.
[5]	贾燕冰, 严正 . 基于改进快速排序法的发电系统可靠性评估[J]. 电网技术, 2010,34(6): 144-148.
	JIA Y B , YAN Z . Reliability evaluation of generation system based on improved quick sorting method[J]. Power Grid Tech-nology, 2010,34(6): 144-148.
[6]	卫志农, 朱梓荣, 赵静波 ,等. 电力系统半线性与全线性最优潮流模型[J]. 电力系统自动化, 2018,42(14): 107-114.
	WEI Z N , ZHU Z R , ZHAO J B ,et al. Semilinear and full linear optimal power flow models for power systems[J]. Power sys-tem automation, 2018,42(14): 107-114.
[7]	梁静, 葛士磊, 瞿博阳 ,等. 求解电力系统经济调度问题的改进粒子群优化算法[J]. 控制与决策, 2019.doi:10.13195/j.kzyjc.2018.1490.
	LIANG J , GE S L , ZHAI B Y ,et al. An improved particle swarm optimization algorithm[J]. Control and decision-making, 2019.doi:10.13195/j.kzyjc.2018.1490.
[8]	宋长伟 . 基于改进Monte Carlo法的发输电系统可靠性评估[D]. 济南:山东大学, 2017.
	SONG C W . Reliability evaluation of power generation and transmission system based on improved Monte Carlo method[D]. Jinan:Shandong University, 2017.
[9]	鞠平, 周孝信, 陈维江 ,等. “智能电网+”研究综述[J]. 电力自动化设备, 2018,38(5): 2-11.
	JU P , ZHOU X X , CHEN W J ,et al. “Smart Grid+” review[J]. Power Automation Equipment, 2018,38(5): 2-11.
[10]	何秋泠 . 配电网网架结构的坚强性评估[D]. 成都:西南交通大学, 2014.
	HE Q L . Strong evaluation of distribution network structure[D]. Chengdu:Southwest Jiaotong University, 2014.
[11]	乐全明 . 电网高级智能故障诊断系统中关键技术的研究[D]. 上海:上海交通大学, 2006.
	YUE Q M . Research on key technologies of advanced intelli-gent fault diagnosis system for power grid[D]. Shanghai:Shanghai Jiaotong University, 2006.
[12]	王上行 . 电网功角稳定安全分析及控制策略研究[D]. 北京:华北电力大学, 2017.
	WANG S X . Power angle stability security analysis and control strategy research[D]. Beijing:North China Electric Power University, 2017.
[13]	MROCCO C . Fast Monte Carlo reliability evaluation using support vector machine[J]. Reliability Engineering, 2002(76): 237-243.
[14]	王景辰, 李孝全, 杨洋 ,等. 基于蒙特卡洛法和最小二乘支持向量机的复杂电力系统可靠性评估[J]. 华东电力, 2013,41(5): 1001-1004.
	WANG J C , LI X Q , YANG Y ,et al. Reliability evaluation of complex power system based on Monte Carlo method and least squares support vector machine[J]. East China Power, 2013,41(5): 1001-1004.
[15]	ZIMMERMAN R D , MURILLO-SANCHEZ C E , THOMAS R J . MATPOWER:steady-state operations,planning and analysis tools for power systems research and education[J]. IEEE Transactions on Power Systems, 2011,26(1): 12-19.
[16]	CHANG C C , LIN C J . LIBSVM:a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011,2(3): 1-27.
[17]	BILLINTON R , LI W Y . Reliability assessment of electric power systems using Monte Carlo methods[M]. New York: Plenum PressPress, 1994: 88-91.

Metrics

Recommended 0

No Suggested Reading articles found!

故障线路编号Ⅰ	故障线路编号Ⅱ	切负荷量/MW	故障线路编号Ⅰ	故障线路编号Ⅱ	切负荷量/MW	故障线路编号Ⅰ	故障线路编号Ⅱ	切负荷量/MW
1	5	0.00	5	35	0.00	5	22	4.01
1	27	0.00	5	36	0.00	25	27	0.00
2	5	0.00	5	37	0.00	5	23	3.73
2	7	19.51	5	38	0.00	5	24	2.32
2	27	50.05	7	9	0.00	5	25	3.08
3	5	0.00	7	13	0.00	5	26	1.04
3	27	0.00	7	14	0.00	5	27	11.83
4	5	0.00	7	15	0.00	5	28	0.81
4	7	0.00	7	20	0.00	5	29	0.54
4	14	0.00	8	27	0.00	5	30	0.00
4	27	0.00	9	27	0.00	5	31	0.00
5	6	0.00	12	27	0.00	5	32	0.00
5	7	0.87	13	27	0.00	5	33	0.00
5	8	0.00	14	15	0.00	5	34	0.00
5	9	1.41	14	27	0.00	26	27	0.00
5	12	0.42	15	27	0.00	27	28	0.00
5	13	1.73	16	27	0.00	27	29	0.00
5	14	3.00	17	27	0.00	27	30	0.00
5	15	3.38	18	27	0.00	27	31	0.00
5	16	4.05	19	27	0.00	27	32	0.00
5	17	4.01	20	27	0.00	27	33	0.00
5	18	2.69	21	27	0.00	27	34	0.00
5	19	3.87	22	27	0.00	27	35	0.00
5	20	4.38	23	27	0.00	27	36	0.00
5	21	4.38	24	27	0.00	27	37	0.00
						27	38	0.00

序号	故障线路编号	故障发电机编号	切负荷量/MW	序号故障线路编号	故障发电机编号	切负荷量/MW
1	5	1	0.00	367	8	0.00
2	5	2	0.00	377	9	0.00
3	5	3	0.00	3827	1	0.00
4	5	4	0.00	3927	2	0.00
5	5	6	0.00	4027	3	0.00
6	5	7	0.00	4127	4	0.00
7	5	8	0.00	4227	6	0.00
8	5	9	0.00	4327	7	0.00
9	5	15	0.00	4427	8	0.00
10	5	16	0.00	4527	9	0.00
11	5	17	0.00	4627	15	0.00
12	5	22	0.00	4727	16	0.00
13	5	23	0.37	4827	17	0.00
14	5	24	0.11	4927	22	0.00
15	5	27	0.20	5027	23	0.00
16	5	28	0.00	5127	24	0.00
17	5	29	0.00	5227	27	0.00
18	5	30	0.59	5327	28	0.00
19	5	31	0.71	5427	29	0.00
20	5	32	1.44	5527	30	0.00
21	5	33	1.06	5627	31	0.00
22	5	35	1.28	5727	32	0.00
23	5	37	0.84	5827	33	0.00
24	5	41	0.36	5927	35	0.00
25	5	42	0.90	6027	37	0.00
26	5	43	0.68	6127	41	0.00
27	5	44	0.52	6227	42	0.00
28	5	45	0.00	6327	43	0.00
29	5	46	0.39	6427	44	0.00
30	5	47	0.82	6527	45	0.00
31	5	48	1.20	6627	46	0.00
32	5	49	3.67	6727	47	0.00
33	5	50	4.52	6827	48	0.00
34	7	3	0.00	6927	49	0.00
35	7	4	0.00	7027	50	0.00

指标	N=1 000			N=10 000
指标	LOLE （ / h·年^-1）	LOEE （ / MW·h·年^-1）	计算所需时间/s	LOLE （ / h·年^-1）	LOEE （ / MW·h·年^-1）	计算所需时间/s
常规蒙特卡洛法	7.87	1 443.5	12.3	9.06	1 503.8	89.5
基于SVM技术的蒙特卡洛法	7.67	1 273.9	1.8	7.97	1 300.5	7.7

Support vector machine based fast Monte Carlo reliability evaluation method for composite power system

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 17

Related Articles 15

Metrics

Recommended 0

序号	故障发电机Ⅰ	故障发电机Ⅱ	切负荷量/MW	序号	故障发电机Ⅰ	故障发电机Ⅱ	切负荷量/MW
1	22	37	74.67	11	33	41	33.03
2	22	41	73.05	12	35	37	34.14
3	22	50	29.95	13	35	41	32.46
4	23	37	74.67	14	37	41	276.89
5	23	41	73.05	15	37	48	30.36
6	23	50	29.95	16	37	49	30.36
7	24	37	74.67	17	37	50	221.13
8	24	41	73.05	18	41	48	28.71
9	24	50	29.95	19	41	49	28.71
10	33	37	34.41	20	41	50	219.48

[1]	Shitong LI, Daying QUAN, Zeyu TANG, Yun CHEN, Xiaofeng WANG, Xiaoping JIN. Time-frequency image and high-order spectrum characteristics based radar signal recognition [J]. Telecommunications Science, 2022, 38(2): 84-91.
[2]	Yajie LI,Yongli ZHAO,Shoudong LIU,Jie ZHANG. Overview of research on fiber nonlinear equalization algorithm based on artificial intelligence [J]. Telecommunications Science, 2020, 36(3): 61-70.
[3]	Rongfang ZHANG,Dandan XU,Yuanguang WANG,Siyu PAN,Zhengmao LI. Application of machine learning in the fake user identification of IoT [J]. Telecommunications Science, 2019, 35(7): 136-144.
[4]	Yaguan QIAN,Xiaohui GUAN,Shuhui WU,NBensheng YU,Dongxiao REN. A novel perturbation attack on SVM by greedy algorithm [J]. Telecommunications Science, 2019, 35(1): 81-89.
[5]	Chuangchuang LI,Guangyue LU,Hanglong WANG. SVM classifier for telecom user arrears based on boundary samples-based under-sampling approaches [J]. Telecommunications Science, 2017, 33(9): 85-91.
[6]	Xiao WANG,Rong ZHANG,Lijun GUO. Robust tampering detection and localization of composite image [J]. Telecommunications Science, 2017, 33(8): 120-129.
[7]	Zhenhong HE. Iris recognition based on generalized Gaussian distribution FDCT_Wrap and FSVM [J]. Telecommunications Science, 2016, 32(7): 126-131.
[8]	Yaguan QIAN,Xiaohui GUAN,Bensheng YUN,Qiong LOU,Pengfei MA. Internet traffic classification using SVM with flexible feature space [J]. Telecommunications Science, 2016, 32(5): 105-113.
[9]	Zhenhong HE. Iris recognition algorithm based on feature weighting fast discrete Curvelet transform and fuzzy LS-SVM [J]. Telecommunications Science, 2016, 32(3): 92-98.
[10]	Hui Cheng,Jinglong Fang,Daquan Wang,Xingqi Wang. Performance Analysis of Simplification of Hyperplane Support Vector Machine [J]. Telecommunications Science, 2015, 31(8): 78-83.
[11]	Hao Dong,Hua Qu,Jihong Zhao,Liangjun Chen,Huijun Dai. Service-Aware Algorithm Based on DT-KSVM [J]. Telecommunications Science, 2015, 31(11): 67-71.
[12]	Ruitong Cao,Xu Cao. A Scheme of QoS Evaluation Based on Support Vector Machine [J]. Telecommunications Science, 2014, 30(2): 123-126.
[13]	Jiyuan Lu,Chenghui Huang,Fang Hou,Bin Li. Image Classification and Annotation Based on Hadoop Cloud Computing Platform [J]. Telecommunications Science, 2014, 30(2): 65-69.
[14]	Yuan Xu,Huaxiang Lu,Xu Chen. A SVM Based Spectrum Prediction Scheme for Cognitive Radio [J]. Telecommunications Science, 2014, 30(11): 87-92.
[15]	Xiaoyun Teng,Hongyi Yu,Jia Yuan. Spectrum Sensing Algorithm Based on SVM [J]. Telecommunications Science, 2009, 25(6): 65-67.