融合拓扑信息的配电网电压-功率灵敏度估计数据驱动方法

doi:10.16183/j.cnki.jsjtu.2022.485

上海交通大学学报 ›› 2024, Vol. 58 ›› Issue (6): 855-862.doi: 10.16183/j.cnki.jsjtu.2022.485

• 新型电力系统与综合能源 • 上一篇下一篇

融合拓扑信息的配电网电压-功率灵敏度估计数据驱动方法

刘舒¹, 周敏¹, 高元海²^,³, 徐潇源²^,³(), 严正²^,³

1.国网上海市电力公司电力科学研究院,上海 200437
2.上海交通大学电力传输与功率变换控制教育部重点实验室,上海 200240
3.上海非碳基能源转换与利用研究院, 上海 200240

收稿日期:2022-11-28 修回日期:2022-12-27 接受日期:2023-02-02 出版日期:2024-06-28 发布日期:2024-07-05
通讯作者: 徐潇源,副教授,博士生导师,电话(Tel.):021-34204603;E-mail: xuxiaoyuan@sjtu.edu.cn.
作者简介:刘舒(1987-),高级工程师,从事智能配电网、分布式能源接入技术研究.
基金资助:
国网上海市电力公司科技项目(52094022003R)

A Data-Driven Method Embedded with Topological Information for Voltage-Power Sensitivity Estimation in Distribution Network

LIU Shu¹, ZHOU Min¹, GAO Yuanhai²^,³, XU Xiaoyuan²^,³(), YAN Zheng²^,³

1. State Grid Shanghai Electric Power Research Institute, Shanghai 200437, China
2. Key Laboratory of Control of Power Transmission and Conversion of the Ministry of Education, Shanghai Jiao Tong University, Shanghai 200240, China
3. Shanghai Non-Carbon Energy Conversion and Utilization Institute, Shanghai 200240, China

Received:2022-11-28 Revised:2022-12-27 Accepted:2023-02-02 Online:2024-06-28 Published:2024-07-05

1. 2022-485-附录.pdf(1114KB)

摘要/Abstract

摘要：

为解决配电网量测数据多重共线性导致电压-功率灵敏度估计精度低的问题,提出融合拓扑信息的数据驱动方法.首先,将电压-功率灵敏度矩阵分解为主成分矩阵和次成分矩阵两部分,其中主成分与配电网拓扑密切相关,次成分为主成分与实际值的误差.然后,分两阶段依次估计主成分和次成分,分别建立基于二次规划的数据驱动模型.第一阶段模型的关键是基于配电网拓扑信息的约束,第二阶段模型的关键是次成分与主成分比值为微小量的约束.最后,采用实际配电网量测数据和IEEE 33节点系统验证所提方法的精度和效率,并与常规最小二乘回归、岭回归、LASSO回归方法对比,仿真结果表明所提方法的精度具有数量级的显著提升.

关键词: 电压-功率灵敏度, 配电网拓扑, 多重共线性, 数据驱动, 主成分

Abstract:

The multicollinearity of measurement data leads to the low accuracy of the data-driven methods for estimating voltage-power sensitivity in distribution networks. In this paper, a data-driven method embedded with topological information is proposed to address the problem. First, the voltage-power sensitivity matrix is decomposed into principal and secondary components, where the principal component is closely related to the distribution network topology and the secondary component is the error between the principal component and the actual value. Then, the principal and secondary components are estimated sequentially in two stages, and their data-driven estimation models based on quadratic programming are established, respectively. The key of the model in the first stage is the constraint based on the distribution network topology information, and the key of the model in the second stage is the constraint that the ratio of the secondary component to the principal component is tiny. Finally, the accuracy and efficiency of the proposed method is validated in the IEEE 33-bus system with a set of measurement data, and comparisons are made with ordinary least square regression, ridge regression, and LASSO regression. The simulation results show that the accuracy of the proposed method is significantly improved by orders of magnitude.

Key words: voltage-power sensitivity, distribution network topology, multicollinearity, data-driven, principal component

中图分类号:

TM732

刘舒, 周敏, 高元海, 徐潇源, 严正. 融合拓扑信息的配电网电压-功率灵敏度估计数据驱动方法[J]. 上海交通大学学报, 2024, 58(6): 855-862.

LIU Shu, ZHOU Min, GAO Yuanhai, XU Xiaoyuan, YAN Zheng. A Data-Driven Method Embedded with Topological Information for Voltage-Power Sensitivity Estimation in Distribution Network[J]. Journal of Shanghai Jiao Tong University, 2024, 58(6): 855-862.

图/表 11

图1

图2

图3

图4

图5

图6

图7

表1

表2

表3

表4

参考文献 19

[1]	胡宏, 陈新仪, 王利峰, 等. 面向新型电力系统的华东电网运行备用体系构建方法[J]. 上海交通大学学报, 2021, 55(12): 1640-1649. doi: 10.16183/j.cnki.jsjtu.2021.273
	HU Hong, CHEN Xinyi, WANG Lifeng, et al. Construction method of an operating reserve system for East China power grid oriented to new power systems[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1640-1649.
[2]	黄强, 郭怿, 江建华, 等. “双碳” 目标下中国清洁电力发展路径[J]. 上海交通大学学报, 2021, 55(12): 1499-1509. doi: 10.16183/j.cnki.jsjtu.2021.272
	HUANG Qiang, GUO Yi, JIANG Jianhua, et al. Development pathway of China’s clean electricity under carbon peaking and carbon neutrality goals[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1499-1509.
[3]	曾博, 穆宏伟, 董厚琦, 等. 考虑5G基站低碳赋能的主动配电网优化运行[J]. 上海交通大学学报, 2022, 56(3): 279-292. doi: 10.16183/j.cnki.jsjtu.2021.367
	ZENG Bo, MU Hongwei, DONG Houqi, et al. Optimization of active distribution network operation considering decarbonization endowment from 5G base stations[J]. Journal of Shanghai Jiao Tong University, 2022, 56(3): 279-292.
[4]	徐志成, 赵波, 丁明, 等. 基于电压灵敏度的配电网光伏消纳能力随机场景模拟及逆变器控制参数优化整定[J]. 中国电机工程学报, 2016, 36(6): 1578-1587.
	XU Zhicheng, ZHAO Bo, DING Ming, et al. Photovoltaic hosting capacity evaluation of distribution networks and inverter parameters optimization based on node voltage sensitivity[J]. Proceedings of the CSEE, 2016, 36(6): 1578-1587.
[5]	熊正勇, 陈天华, 杜磊, 等. 基于改进灵敏度分析的有源配电网智能软开关优化配置[J]. 电力系统自动化, 2021, 45(8): 129-137.
	XIONG Zhengyong, CHEN Tianhua, DU Lei, et al. Optimal allocation of soft open point in active distribution network based on improved sensitivity analysis[J]. Automation of Electric Power Systems, 2021, 45(8): 129-137.
[6]	屈尹鹏, 孙元章, 徐箭, 等. 基于解析灵敏度的不平衡配电系统分布式发电出力优化[J]. 电力系统自动化, 2021, 45(19): 117-125.
	QU Yinpeng, SUN Yuanzhang, XU Jian, et al. Optimization of distributed generation output in unbalanced distribution system based on analytical sensitivity[J]. Automation of Electric Power Systems, 2021, 45(19): 117-125.
[7]	李振坤, 陈思宇, 符杨, 等. 基于时序电压灵敏度的有源配电网储能优化配置[J]. 中国电机工程学报, 2017, 37(16): 4630-4640.
	LI Zhenkun, CHEN Siyu, FU Yang, et al. Optimal allocation of ESS in distribution network containing DG base on timing-voltage-sensitivity analysis[J]. Proceedings of the CSEE, 2017, 37(16): 4630-4640.
[8]	刘琪, 王守相, 吉兴全. 主动配电网宽适应性潮流灵敏度分析模型[J]. 电力系统自动化, 2020, 44(13): 81-88.
	LIU Qi, WANG Shouxiang, JI Xingquan. Power flow sensitivity analysis model with wide adaptability for active distribution networks[J]. Automation of Electric Power Systems, 2020, 44(13): 81-88.
[9]	严正, 孔祥瑞, 徐潇源, 等. 微型同步相量测量单元在智能配电网运行状态估计中的应用[J]. 上海交通大学学报, 2018, 52(10): 1195-1205. doi: 10.16183/j.cnki.jsjtu.2018.10.007
	YAN Zheng, KONG Xiangrui, XU Xiaoyuan, et al. Applications of micro synchronous phasor measurement units in state estimation of smart distribution network[J]. Journal of Shanghai Jiao Tong University, 2018, 52(10): 1195-1205.
[10]	CHEN Y C, WANG J H, DOMÍNGUEZ-GARCÍA A D, et al. Measurement-based estimation of the power flow Jacobian matrix[J]. IEEE Transactions on Smart Grid, 2016, 7(5): 2507-2515.
[11]	李鹏, 宿洪智, 王成山, 等. 基于PMU量测的智能配电网电压-功率灵敏度鲁棒估计方法[J]. 电网技术, 2018, 42(10): 3258-3267.
	LI Peng, SU Hongzhi, WANG Chengshan, et al. Robust estimation method of voltage to power sensitivity for smart distribution networks based on PMU measurements[J]. Power System Technology, 2018, 42(10): 3258-3267.
[12]	ZHANG J B, ZHENG X T, WANG Z, et al. Power system sensitivity identification—Inherent system properties and data quality[J]. IEEE Transactions on Power Systems, 2017, 32(4): 2756-2766.
[13]	ZHANG J B, WANG Z, ZHENG X T, et al. Locally weighted ridge regression for power system online sensitivity identification considering data collinearity[J]. IEEE Transactions on Power Systems, 2018, 33(2): 1624-1634.
[14]	DA SILVA E L, LIMA A M N, DE ROSSITER CORRÊA M B, et al. Data-driven sensitivity coefficients estimation for cooperative control of PV inverters[J]. IEEE Transactions on Power Delivery, 2020, 35(1): 278-287.
[15]	CHANG J W, KANG M, OH S. Data-driven estimation of voltage-to-power sensitivities considering their mutual dependency in medium voltage distribution networks[J]. IEEE Transactions on Power Systems, 2022, 37(4): 3173-3176.
[16]	SAUNDERS C, GAMMERMAN A, VOVK V. Ridge regression learning algorithm in dual variables[C]//Proceedings of the Fifteenth International Conference on Machine Learning. Madison, USA: University of Wisconsin-Madison, 1998: 515-521.
[17]	TIBSHIRANI R. Regression shrinkage and selection via the lasso: A retrospective[J]. Journal of the Royal Statistical Society Series B: Statistical Methodology, 2011, 73(3): 273-282.
[18]	BARAN M, WU F F. Optimal sizing of capacitors placed on a radial distribution system[J]. IEEE Transactions on Power Delivery, 1989, 4(1): 735-743.
[19]	DEKA D, BACKHAUS S, CHERTKOV M. Structure learning in power distribution networks[J]. IEEE Transactions on Control of Network Systems, 2018, 5(3): 1061-1074.

估计方法	x_NMSE	最大误差 (p.u.)	误差中位数(p.u.)
常规最小二乘回归	5.2×10^-1	1.1×10^-1	3.5×10^-3
岭回归	9.3×10^-2	3.5×10^-2	9.6×10^-4
LASSO回归	7.1×10^-2	2.8×10^-2	2.3×10^-3
本文	2.5×10^-3	9.2×10^-3	1.7×10^-4

参数组合	x_NMSE	参数组合	x_NMSE
λ=4, ξ=0	2.7×10^-3	λ=1, ξ=0.1	2.0×10^-3
λ=4, ξ=0.1	2.5×10^-3	λ=2, ξ=0.1	2.4×10^-3
λ=4, ξ=0.2	2.5×10^-3	λ=4, ξ=0.1	2.5×10^-3
λ=4, ξ=0.4	2.5×10^-3	λ=8, ξ=0.1	2.8×10^-3
λ=4, ξ=0.8	3.1×10^-3	λ=10, ξ=0.1	2.8×10^-3
λ=4, ξ=1.0	3.4×10^-3	λ=100, ξ=0.1	2.8×10^-3

岭回归	x_NMSE	LASSO回归	x_NMSE
β=2×10^-11	20.3×10^-2	γ=20	28.7×10^-2
β=4×10^-11	17.4×10^-2	γ=40	7.7×10^-2
β=8×10^-11	9.3×10^-2	γ=60	7.1×10^-2
β=16×10^-11	9.5×10^-2	γ=80	9.3×10^-2
β=32×10^-11	9.8×10^-2	γ=100	13.7×10^-2
β=64×10^-11	10.3×10^-2	γ=200	28.9×10^-2

估计方法	耗时/s
常规最小二乘回归	0.3
岭回归	0.3
LASSO回归	0.45
本文	0.54

融合拓扑信息的配电网电压-功率灵敏度估计数据驱动方法

A Data-Driven Method Embedded with Topological Information for Voltage-Power Sensitivity Estimation in Distribution Network

RichHTML

PDF (PC)

补充材料

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 19

相关文章 15

编辑推荐

Metrics

本文评价

[1]	唐震, 郝丽花, 冯静. 局部频率测量数据驱动的电力系统功率缺额在线评估方法[J]. 上海交通大学学报, 2023, 57(4): 403-411.
[2]	张恒睿. 需求导向的材料设计[J]. 上海交通大学学报, 2021, 55(Sup.1): 93-94.
[3]	巩伟峥, 许凌, 姚寅. 计及风速分布与机组惯量转化不确定性的风电场可用惯量估计[J]. 上海交通大学学报, 2021, 55(S2): 51-59.
[4]	李勇, 张梦骏, 仇栋, 范云锋, 苏智勇, 邱令存. 数据驱动的指控系统增强现实电子沙盘设计与开发[J]. 空天防御, 2021, 4(2): 27-.
[5]	徐巧宁，艾青林，杜学文，刘毅. 模型-数据联合驱动的船舶舵机电液伺服系统早期故障检测[J]. 上海交通大学学报, 2020, 54(5): 451-464.
[6]	来颜博, 阎高伟, 程兰, 陈泽华. 基于动态独立成分分析和动态主成分分析的测地线流式核无监督回归模型[J]. 上海交通大学学报, 2020, 54(12): 1269-1277.
[7]	王峥1，褚学宁1，陈汉斯1，张磊1，颜波1，刘航2. 运行数据驱动的手机性能需求推断与感知分析[J]. 上海交通大学学报（自然版）, 2018, 52(7): 777-783.
[8]	高雅1，王占永1，2，路庆昌1，彭仲仁1. 城市高架路沿侧细颗粒物的垂直分布特征研究[J]. 上海交通大学学报（自然版）, 2018, 52(6): 650-657.
[9]	吴军a, b，黎国强a，吴超勇a，程一伟c，邓超c. 数据驱动的滚动轴承性能衰退状态监测方法[J]. 上海交通大学学报（自然版）, 2018, 52(5): 538-544.
[10]	高筱婷，杨东升. 基于数据驱动的智能电器运行状态监测方法 [J]. 上海交通大学学报（自然版）, 2017, 51(9): 1104-1110.
[11]	余焕伟，叶震，张志芬，陈华斌，陈善本. Al-Mg合金钨极气体保护焊接电弧的光谱特征提取方法[J]. 上海交通大学学报（自然版）, 2013, 47(11): 1655-1660.
[12]	杨漪1，姚晓栋1，杨建国1，张余升2，袁峰2. 基于主成分分析与BP神经网络相结合的机床主轴热漂移误差建模[J]. 上海交通大学学报（自然版）, 2013, 47(05): 750-753.
[13]	李华怡, 刘炜. 基于主成分分析的磨矿旋流器机理模型[J]. 上海交通大学学报（自然版）, 2012, 46(12): 1936-1939.
[14]	张颖1, 李彩娟1, 邵惠鹤2. 基于主成分分析与模糊BP方法的藻类繁殖状态预测[J]. 上海交通大学学报（自然版）, 2012, 46(05): 785-789.
[15]	张光明, 李柠, 李少远. 一种数据驱动的预测控制器性能监控方法[J]. 上海交通大学学报（自然版）, 2011, 45(08): 1113-1118.