基于云模型和随机森林的韧性城市电网风险预警模型

doi:10.12204/j.issn.1000-7229.2024.05.003

电力建设 ›› 2024, Vol. 45 ›› Issue (5): 19-28.doi: 10.12204/j.issn.1000-7229.2024.05.003

• 新型电力系统韧性基础理论与关键技术·栏目主持许寅教授、时珊珊高工、魏韡副教授· • 上一篇下一篇

基于云模型和随机森林的韧性城市电网风险预警模型

魏新迟¹(), 董佳²(), 时珊珊¹(), 李存斌²(), 苏运¹()

1.国网上海市电力公司电力科学研究院,上海市 200437
2.华北电力大学经济与管理学院,北京市 102206

收稿日期:2023-10-09 出版日期:2024-05-01 发布日期:2024-04-29
通讯作者: 董佳(1997),女,博士研究生,主要研究方向为信息管理与决策支持,E-mail: 15611571133@163.com。
作者简介:魏新迟(1989),女,博士,高级工程师,主要研究方向为韧性电网优化运行、新能源与储能协调控制技术,E-mail:newlate@126.com;
时珊珊(1985),女,博士,高级工程师,主要研究方向为新型储能、车网互动和韧性电网技术,E-mail:sss3397@163.com;
李存斌(1959),男,教授,博士生导师,主要研究方向为信息管理、风险管理,E-mail:lcb999@263.net;
苏运(1987),男,硕士,高级工程师,主要研究方向为电力系统仿真及配用电大数据分析,E-mail:oppenvi@163.com。
基金资助:
国家重点研发计划青年科学家项目(2022YFB2405500);国网上海市电力公司科技项目(52094023000N)

Enhanced Risk Warning Model for Resilient Urban Power Grid Using Cloud Model and Random Forest

WEI Xinchi¹(), DONG Jia²(), SHI Shanshan¹(), LI Cunbin²(), SU Yun¹()

1. State Grid Shanghai Electric Power Research Institute, Shanghai 200437, China
2. School of Economics and Management, North China Electric Power University, Beijing 102206, China

Received:2023-10-09 Published:2024-05-01 Online:2024-04-29
Supported by:
National Key R&D Program of China(2022YFB2405500)

摘要/Abstract

摘要：

相比传统电网,韧性城市电网展现出了出色的适应多种扰动和灾害的能力,但其复杂性也使得韧性城市电网风险预警面临更大的挑战,亟需大数据和机器学习等先进技术的引入。首先,构建韧性城市电网风险评估指标体系,采用主客观结合的综合赋权法对指标赋权,通过大数据技术获取的实时数据流得到韧性城市电网风险评估指标的动态权重;然后,构建韧性城市电网风险评估标准云,计算韧性城市电网风险等级隶属度,确定风险等级;最后,基于随机森林构建韧性城市电网风险预警模型,并进行算例分析,通过与其他模型对比,发现所构建的模型表现出高精度的特征。所建模型具有较好的风险预警效果,从而能够及时采取有效风险管控措施,保障韧性城市电网稳定运行。

关键词: 韧性城市电网, 云模型, 随机森林, 风险评估, 风险预警

Abstract:

Resilient urban power grids, while showcasing remarkable adaptability to diverse disturbances and disasters, pose significant challenges in risk warning due to their complexity. This underscores the necessity of integrating advanced technologies such as big data and machine learning. This study proposes a novel approach to resolve these issues. First, a resilient urban power grid risk assessment index system was established, employing a comprehensive weighted approach that combined subjective and objective factors to weigh the indicators. Leveraging real-time data flow obtained through big data technology, dynamic weights for risk assessment indicators were determined. Subsequently, a resilient urban power grid risk assessment standard cloud was developed, and the membership degree of the resilient urban power grid risk level was computed to ascertain the risk level. Finally, a resilient urban power grid risk warning model was formulated using random forest, and a thorough numerical analysis was conducted. Compared with other models, the constructed model exhibited high precision characteristics. The findings demonstrated that the developed model exerted a substantial risk-warning effect, enabling timely implementation of effective risk control measures to ensure the stable operation of resilient urban power grids.

Key words: resilient urban power grid, cloud model, random forest, risk assessment, risk warning

中图分类号:

TM712

魏新迟, 董佳, 时珊珊, 李存斌, 苏运. 基于云模型和随机森林的韧性城市电网风险预警模型[J]. 电力建设, 2024, 45(5): 19-28.

WEI Xinchi, DONG Jia, SHI Shanshan, LI Cunbin, SU Yun. Enhanced Risk Warning Model for Resilient Urban Power Grid Using Cloud Model and Random Forest[J]. ELECTRIC POWER CONSTRUCTION, 2024, 45(5): 19-28.

图/表 15

图1 韧性城市电网风险预警模型流程图

Fig.1 Flow chart of risk warning model for resilient urban power grid

表1 韧性城市电网风险评估指标体系

Table 1 Risk assessment index system of resilient urban power grid

图2 随机森林算法流程图

Fig.2 Flow chart of random forest algorithm

表2 精准率和召回率计算中的变量含义

Table 2 The meaning of variables in precision and recall calculation

表3 韧性城市电网风险评估指标权重结果

Table 3 Weight results of risk assessment indicators for resilient urban power grid

表4 风险严重程度的等级和指数

Table 4 Risk severity level and index

表5 韧性城市电网风险评估指标等级

Table 5 Risk assessment index levels for resilient urban power grid

表6 韧性城市电网风险评估指标云模型构建

Table 6 Construction of cloud model for risk assessment index of resilient urban power grid

图3 自主防御响应时间指标标准云图

Fig.3 Cloud chart of autonomous defense response time indicator standards

表7 自主防御响应时间指标隶属度结果

Table 7 Autonomous defense response time indicator membership results

图4 韧性城市电网风险等级隶属度结果

Fig.4 Risk grade subordination results of resilient urban power grid

表8 韧性城市电网风险等级

Table 8 Risk level of resilient urban power grid

图5 风险预警召回率和精准率对比

Fig.5 Comparison of recall rate and accuracy rate of risk early warning

图6 混淆矩阵对比

Fig.6 Comparison of confusion matrix

图7 韧性城市电网A风险预警结果(2022年12月—2023年1月)

Fig.7 Risk early warning results of resilient urban grid A (from December 2022 to January 2023)

参考文献 32

[1]	ZAKARIYA M Z, TEH J. A systematic review on cascading failures models in renewable power systems with dynamics perspective and protections modeling[J]. Electric Power Systems Research, 2023, 214:108928. doi: 10.1016/j.epsr.2022.108928 URL
[2]	陈韵含, 许寅, 王颖, 等. 考虑潜在恢复需求的城市配电网移动应急资源灾前布点[J]. 电力系统自动化, 2023, 47(14): 105-113.
	CHEN Yunhan, XU Yin, WANG Ying, et al. Pre-disaster positioning of mobile emergency resources for urban distribution network considering potential restoration demand[J]. Automation of Electric Power Systems, 2023, 47(14): 105-113.
[3]	许寅, 王颖, 和敬涵, 等. 多源协同的配电网多时段负荷恢复优化决策方法[J]. 电力系统自动化, 2020, 44(2): 123-131.
	XU Yin, WANG Ying, HE Jinghan, et al. Optimal decision-making method for multi-period load restoration in distribution network with coordination of multiple sources[J]. Automation of Electric Power Systems, 2020, 44(2): 123-131.
[4]	骆晨, 冯玉, 吴凯, 等. 多源大规模电网的多阶攻击风险感知量化和防御技术[J]. 科学技术与工程, 2023, 23(30): 12976-12984.
	LUO Chen, FENG Yu, WU Kai, et al. Multi-stage attack risk quantification and defense techniques for multi-source large-scale power grids[J]. Science Technology and Engineering, 2023, 23(30): 12976-12984.
[5]	王曦悦, 张浩, 彭超逸. 基于风险抑制理论的电网弹性运行方法[J]. 中国电力, 2023, 56(12): 127-137.
	WANG Xiyue, ZHANG Hao, PENG Chaoyi. Risk limiting based resilient operation method for power grid[J]. Electric Power, 2023, 56(12): 127-137.
[6]	陈颖, 高仕林, 宋炎侃, 等. 面向新型电力系统的高性能电磁暂态云仿真技术[J]. 中国电机工程学报, 2022, 42(8): 2854-2864.
	CHEN Ying, GAO Shilin, SONG Yankan, et al. High-performance electromagnetic transient simulation for new-type power system based on cloud computing[J]. Proceedings of the CSEE, 2022, 42(8): 2854-2864.
[7]	郭创新, 刘祝平, 刘永刚, 等. 基于图神经网络和强化学习的电网风险态势感知[J]. 电网与清洁能源, 2023, 39(12): 41-49.
	GUO Chuangxin, LIU Zhuping, LIU Yonggang, et al. GNN and RL based power system risk situation perception[J]. Power System and Clean Energy, 2023, 39(12): 41-49.
[8]	魏韡, 范越, 谢睿, 等. 平抑高比例新能源发电功率波动的风-光-储容量最优配比[J]. 电力建设, 2023, 44(3): 138-147. doi: 10.12204/j.issn.1000-7229.2023.03.014
	WEI Wei, FAN Yue, XIE Rui, et al. Optimal ratio of wind-solar-storage capacity for mitigating the power fluctuations in power system with high penetration of renewable energy power generation[J]. Electric Power Construction, 2023, 44(3): 138-147. doi: 10.12204/j.issn.1000-7229.2023.03.014
[9]	GAO F, LI Q, JI Y Z, et al. EWNet: an early warning classification framework for smart grid based on local-to-global perception[J]. Neurocomputing, 2021, 443: 199-212. doi: 10.1016/j.neucom.2021.03.007 URL
[10]	杨淳岚, 宁鑫, 徐会凯, 等. 电网山火监测及风险预警技术研究综述[J]. 电网技术, 2023, 47(11): 4765-4777.
	YANG Chunlan, NING Xin, XU Huikai, et al. Overview of mountain fire monitoring and early warning for power grid demand[J]. Power System Technology, 2023, 47(11): 4765-4777.
[11]	胡珊珊, 王保帅, 尹家悦, 等. 基于FMECA的智能电能表关键元器件风险评估[J]. 电测与仪表, 2023, 60(1): 174-179.
	HU Shanshan, WANG Baoshuai, YIN Jiayue, et al. Risk assessment of key components for smart meters based on FMECA[J]. Electrical Measurement & Instrumentation, 2023, 60(1): 174-179.
[12]	何馥彤, 李存斌. 考虑信息物理融合系统的韧性电网风险研究现状及发展趋势可视化分析[J]. 中国安全生产科学技术, 2024, 20(2): 35-43.
	HE Futong, LI Cunbin. Visual analysis on research status and development trend of resilient power grid risk considering cyber-physical systems[J]. Journal of Safety Science and Technology, 2024, 20(2): 35-43.
[13]	郭傲, 陈颖, 肖谭南, 等. 基于消息传递网络的多变拓扑微电网群故障检测方法[J]. 高电压技术, 2023, 49(6):2339-2347.
	GUO Ao, CHEN Ying, XIAO Tannan, et al. A fault detection method for multi-microgrid considering topological variationsbased on message passing neural network[J]. High Voltage Engineering, 2023, 49(6):2339-2347.
[14]	王振浩, 王正韬, 梁志峰, 等. 含高比例分布式光伏的主配网紧急切负荷策略研究[J]. 电网与清洁能源, 2024, 40(1): 40-51.
	WANG Zhenhao, WANG Zhengtao, LIANG Zhifeng, et al. Research on the emergency load shedding strategy for transmission and distribution networks with high penetration of distributed photovoltaic[J]. Power System and Clean Energy, 2024, 40(1): 40-51.
[15]	莫石, 徐秋实, 卢子敬, 等. 模糊分割多目标风险框架下电网连锁故障运行风险评估[J]. 中国电力, 2024, 57(2): 41-48.
	MO Shi, XU Qiushi, LU Zijing, et al. Fuzzy partitioned multi-objective risk framework based operational risk assessment of cascading failure for power grid[J]. Electric Power, 2024, 57(2): 41-48.
[16]	唐海国, 张帝, 刘成英, 等. 计及拓扑变换的主动配电网故障风险智能预警[J]. 电力工程技术, 2022, 41(5): 193-201.
	TANG Haiguo, ZHANG Di, LIU Chengying, et al. Intelligent forecast of fault risk in active distribution networks considering network reconfiguration[J]. Electric Power Engineering Technology, 2022, 41(5): 193-201.
[17]	李格格. 含大规模新能源的电力系统风险动态评估模型研究[D]. 北京: 华北电力大学, 2020.
	LI Gege. Research on dynamic risk assessment model of power system with large-scale new energy[D]. Beijing: North China Electric Power University, 2020.
[18]	李存斌, 董佳, 丁佳. 基于大数据的燃煤发电运行风险实时评估[J]. 电力系统保护与控制, 2022, 50(16): 47-57.
	LI Cunbin, DONG Jia, DING Jia. Real-time assessment of operational risk of coal-fired power generation based on big data[J]. Power System Protection and Control, 2022, 50(16): 47-57.
[19]	郭创新, 刘祝平, 冯斌, 等. 新型电力系统风险评估研究现状及展望[J]. 高电压技术, 2022, 48(9): 3394-3404.
	GUO Chuangxin, LIU Zhuping, FENG Bin, et al. Research status and prospect of new-type power system risk assessment[J]. High Voltage Engineering, 2022, 48(9): 3394-3404.
[20]	黎静华, 左俊军, 汪赛. 大规模风电并网电力系统运行风险评估与分析[J]. 电网技术, 2016, 40(11): 3503-3513.
	LI Jinghua, ZUO Junjun, WANG Sai. Analysis and assessment of operation risk for power system with large-scale wind power integration[J]. Power System Technology, 2016, 40(11): 3503-3513.
[21]	马光, 张伊宁, 陈哲, 等. 含大规模风电的交直流混联系统风险评估方法[J]. 电网技术, 2019, 43(9): 3241-3252.
	MA Guang, ZHANG Yining, CHEN Zhe, et al. Risk assessment method for hybrid AC/DC system with large-scale wind power integration[J]. Power System Technology, 2019, 43(9): 3241-3252.
[22]	苗子清. 基于大数据方法的中国系统性金融风险监测和预警研究[D]. 北京: 中国社会科学院大学, 2022.
	MIAO Ziqing. Research on China’s systematic financial risk monitoring and early warning based on big data method[D]. Beijing: University of Chinese Academy of Social Sciences, 2022.
[23]	陈卓, 丁利, 曹天红, 等. 基于层次分析法和随机森林回归算法的谷物资源风险评估模型[J]. 食品与机械, 2021, 37(12): 58-66.
	CHEN Zhuo, DING Li, CAO Tianhong, et al. Risk assessment model of grain resources based on AHP and random forest regression algorithm[J]. Food & Machinery, 2021, 37(12): 58-66.
[24]	齐先军, 王朋, 张付华. 考虑需求响应不确定性的配电网模糊可信约束规划[J]. 南方电网技术, 2022, 16(12): 76-87.
	QI Xianjun, WANG Peng, ZHANG Fuhua. Distribution network fuzzy credibility constraint planning considering the uncertainty of demand response[J]. Southern Power System Technology, 2022, 16(12): 76-87.
[25]	钱胜, 王琦, 颜云松, 等. 计及网络攻击影响的安全稳定控制系统风险评估方法[J]. 电力工程技术, 2022, 41(3): 14-21.
	QIAN Sheng, WANG Qi, YAN Yunsong, et al. Risk assessment method of security and stability control system considering the impact of cyber attacks[J]. Electric Power Engineering Technology, 2022, 41(3): 14-21.
[26]	王宁, 田家英, 董宁, 等. 基于改进SVM的智能电网调控系统实时风险评估与预警技术[J]. 沈阳工业大学学报, 2022, 44(1): 7-13. doi: 10.7688/j.issn.1000-1646.2022.01.02
	WANG Ning, TIAN Jiaying, DONG Ning, et al. Real-time risk-assessment and early-warning technology of smart grid regulation system based on improved SVM[J]. Journal of Shenyang University of Technology, 2022, 44(1): 7-13. doi: 10.7688/j.issn.1000-1646.2022.01.02
[27]	王瑾, 裴亮. 基于深度学习的电网调控系统异常检测与多阶段风险预警[J]. 沈阳工业大学学报, 2021, 43(6): 601-607. doi: 10.7688/j.issn.1000-1646.2021.06.01
	WANG Jin, PEI Liang. Anomaly detection and multi-stage risk pre-warning technology of power grid control system based on deep learning[J]. Journal of Shenyang University of Technology, 2021, 43(6): 601-607. doi: 10.7688/j.issn.1000-1646.2021.06.01
[28]	徐浩, 姜新雄, 刘志成, 等. 基于概率预测的电网静态安全运行风险评估及主动调控策略[J]. 电力系统自动化, 2022, 46(1): 182-191.
	XU Hao, JIANG Xinxiong, LIU Zhicheng, et al. Probability prediction based risk assessment and proactive regulation and control strategy for static operation safety of power grid[J]. Automation of Electric Power Systems, 2022, 46(1): 182-191.
[29]	徐特威, 鲁宗相, 乔颖, 等. 基于典型故障与环境场景关联识别的城市配电网运行风险预警方法[J]. 电网技术, 2017, 41(8): 2577-2584.
	XU Tewei, LU Zongxiang, QIAO Ying, et al. A risk warning method for urban distribution network based on associated recognition of typical fault and environment scenario[J]. Power System Technology, 2017, 41(8): 2577-2584.
[30]	谢尊贤, 蔡二柱, 徐宝. 基于云模型-模糊理论的养老机构火灾安全风险预警系统[J]. 安全与环境学报, 2022, 22(2): 588-598.
	XIE Zunxian, CAI Erzhu, XU Bao. Fire safety risk early warning system of elderly nursing homes based on cloud model-fuzzy theory[J]. Journal of Safety and Environment, 2022, 22(2): 588-598.
[31]	李晓蕾, 魏玲, 王忠强, 等. 基于改进随机森林的电力用户欠费风险分析预警[J]. 电测与仪表, 2019, 56(9): 56-62.
	LI Xiaolei, WEI Ling, WANG Zhongqiang, et al. Arrears risk analysis and early warning of electricity customers based on optimized random forest[J]. Electrical Measurement & Instrumentation, 2019, 56(9): 56-62.
[32]	杜晓东, 王立斌, 刘科研, 等. 基于随机森林的配电网故障分布特征预测方法[J]. 电网与清洁能源, 2023, 39(1): 70-77.
	DU Xiaodong, WANG Libin, LIU Keyan, et al. A prediction method of distribution network fault distribution characteristics based on random forest[J]. Power System and Clean Energy, 2023, 39(1): 70-77.

基于云模型和随机森林的韧性城市电网风险预警模型

Enhanced Risk Warning Model for Resilient Urban Power Grid Using Cloud Model and Random Forest

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 32

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张逸, 吴逸帆, 陈晶腾. 新型电力系统背景下电压暂降风险评估技术挑战与展望[J]. 电力建设, 2023, 44(2): 15-24.
[2]	杨志豪, 刘沆, 文明, 赵海彭, 廖菁, 苗世洪. 考虑综合需求响应混合不确定性的综合能源系统优化调度策略[J]. 电力建设, 2022, 43(9): 66-76.
[3]	刘凯奇, 李华强, 陆杨, 李旭翔. 基于安全性风险评估与保险机制的可用输电能力决策[J]. 电力建设, 2021, 42(8): 118-126.
[4]	王子馨, 胡俊杰, 刘宝柱. 基于长短期记忆网络的电力系统量测缺失数据恢复方法[J]. 电力建设, 2021, 42(5): 1-8.
[5]	李佳玮, 吴克河, 张波. 一种基于小生境遗传算法的电网信息安全风险评估模型[J]. 电力建设, 2021, 42(3): 89-96.
[6]	梁修锐，刘道伟，杨红英，李卫星，邵广惠，徐兴伟，王克非，李宗翰，赵高尚. 数据驱动的电力系统静态电压稳定态势评估[J]. 电力建设, 2020, 41(1): 126-132.
[7]	方金涛，龚庆武. 考虑运行风险的主动配电网分布式电源多目标优化配置[J]. 电力建设, 2019, 40(5): 128-.
[8]	徐铭铭，姚森，牛荣泽，胡博，徐恒博，谢开贵，周宁，郝钰. 配电网重复多发性停电风险辨识方法[J]. 电力建设, 2018, 39(8): 111-115.
[9]	任志超，程超，何仲潇，汪晓华，王枭. 基于电热耦合潮流的综合能源系统风险评估方法[J]. 电力建设, 2018, 39(12): 102-108.
[10]	崔力民, 李刚, 王天军, 石江红, 宋雨. 智能电网信息通信系统风险评估的模糊测度方法[J]. 电力建设, 2017, 38(5): 52-.
[11]	梁智，孙国强，卫志农，臧海祥. 基于变量选择与高斯过程回归的短期负荷预测[J]. 电力建设, 2017, 38(2): 122-.
[12]	刘琪琛, 雷景生, 郝珈玮,黄燕刚,李强,罗海波. 基于Spark平台和并行随机森林回归算法的短期电力负荷预测[J]. 电力建设, 2017, 38(10): 84-.
[13]	张晋，袁虎玲，周连俊. 基于风险评估的蒙东电力外送串补方案评价[J]. 电力建设, 2015, 36(2): 14-20.
[14]	莫若慧，左俊军，龙裕芳，兰飞，胡剑琛，李献，吴锋，祁永福，吴云亮. 适合风雨气候的电力系统风险评估模型与方法[J]. 电力建设, 2015, 36(2): 21-26.
[15]	董美玲，游大海，王刚，陈伟华. 基于云模型的输电网规划方案综合决策方法[J]. 电力建设, 2015, 36(10): 154-160.