基于贝叶斯优化弹性网络回归的谐波状态估计方法

doi:10.11930/j.issn.1004-9649.202101017

中国电力 ›› 2022, Vol. 55 ›› Issue (8): 104-112.DOI: 10.11930/j.issn.1004-9649.202101017

基于贝叶斯优化弹性网络回归的谐波状态估计方法

马思棋, 王忠

四川大学电气工程学院，四川成都 610065

收稿日期:2021-01-05 修回日期:2021-12-08 发布日期:2022-08-18
作者简介:马思棋（1995—），女，硕士，从事电力系统谐波状态估计研究，E-mail：819046672@ qq.com;王忠（1964—），男，副教授，博士，从事网络与无线通信理论与技术、大数据与云计算理论与技术、无线电导航与定位等研究，E-mail：1648277629@163.com
基金资助:
国家自然科学基金资助项目(49901013)。

Harmonic State Estimation Method Based on Bayesian Optimized Elastic Network Regression

MA Siqi, WANG Zhong

School of Electrical Engineering, Sichuan University, Chengdu 610065, China

Received:2021-01-05 Revised:2021-12-08 Published:2022-08-18
Supported by:
This work is supported by National Natural Science Foundation of China (No.49901013).

摘要/Abstract

摘要： 回归类算法在估计系统谐波状态时，谐波源间的高度相关性会引起法矩阵的病态，从而显著影响谐波估计精度。为了更加准确地估计系统谐波状态，提出一种基于贝叶斯优化弹性网络回归的谐波状态估计方法。首先，在用最小二乘法进行谐波状态估计时，将带权值的1范数和2范数同时加入惩罚函数中；另外，为了更加高效准确地估计系统谐波状态，将高斯过程和贝叶斯优化应用于1范数和2范数的权值选取；最后，在IEEE 14节点中验证了所提方法的有效性。结果表明：在谐波源间存在相关性时，所提方法仍能实现合理的谐波源定位及谐波责任划分。

关键词: 谐波状态估计, 多重共线性, 弹性网络回归, 贝叶斯优化, 高斯过程

Abstract: When the regression algorithm is used to estimate the harmonic state of power system, the high correlation between harmonic sources will cause the ill condition of the normal matrix, which will significantly affect the accuracy of harmonic estimation. In order to accurately estimate the harmonic state of the power system, a harmonic state estimation method is proposed based on Bayesian optimization elastic network regression. Firstly, when the least square method is used to estimate the harmonic state, the weighted 1-norm and 2-norm are added to the penalty function at the same time; In addition, in order to estimate the harmonic state more efficiently and accurately, the Gaussian process and Bayesian optimization are applied to select the weight of 1-norm and 2-norm; Finally, the effectiveness of the proposed method is verified in IEEE14 node. When there is correlation between harmonic sources, the proposed method can still achieve reasonable harmonic source location and harmonic responsibility division.

Key words: harmonic state estimation, multicollinearity, elastic network regression, Bayesian optimization, Gaussian process

马思棋, 王忠. 基于贝叶斯优化弹性网络回归的谐波状态估计方法[J]. 中国电力, 2022, 55(8): 104-112.

MA Siqi, WANG Zhong. Harmonic State Estimation Method Based on Bayesian Optimized Elastic Network Regression[J]. Electric Power, 2022, 55(8): 104-112.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202101017

https://www.electricpower.com.cn/CN/Y2022/V55/I8/104

参考文献

[1] 张旭, 徐永海, 刘子腾, 等. 考虑系统侧谐波电压波动的光伏接入点谐波发射水平评估方法[J]. 中国电力, 2021, 54(3): 109–116
ZHANG Xu, XU Yonghai, LIU Ziteng, et al. A method for assessing harmonic emission level of photovoltaic access point considering system-side harmonic voltage fluctuations[J]. Electric Power, 2021, 54(3): 109–116
[2] 王炤宇, 随慧斌. 谐波源责任划分技术的工程应用[J]. 电力系统保护与控制, 2021, 49(14): 140–148
WANG Zhaoyu, SUI Huibin. Engineering application of harmonic source responsibility division technology[J]. Power System Protection and Control, 2021, 49(14): 140–148
[3] 李嘉彬, 杨建华, 张涛, 等. 电力电子设备谐波对配电网电压骤升的影响研究[J]. 智慧电力, 2021, 49(5): 35–41, 84
LI Jiabin, YANG Jianhua, ZHANG Tao, et al. Harmonic impact of power electronic devices upon voltage swell in distribution networks[J]. Smart Power, 2021, 49(5): 35–41, 84
[4] 毕悦, 方思瑞, 于舒祺. 含光伏并网的弱交流系统低频振荡协调控制策略[J]. 电力科学与技术学报, 2021, 36(4): 59–65
BI Yue, FANG Sirui, YU Shuqi. Coordinated control strategy for low frequency oscillations of weak AC grid connected PV systems[J]. Journal of Electric Power Science and Technology, 2021, 36(4): 59–65
[5] 张巍, 杨洪耕. 基于二元线性回归的谐波发射水平估计方法[J]. 中国电机工程学报, 2004, 24(6): 50–53
ZHANG Wei, YANG Honggeng. A method for assessing harmonic emission level based on binary linear regression[J]. Proceedings of the CSEE, 2004, 24(6): 50–53
[6] 贾秀芳, 华回春, 曹东升, 等. 基于复线性最小二乘法的谐波责任定量划分[J]. 中国电机工程学报, 2013, 33(4): 149–155
JIA Xiufang, HUA Huichun, CAO Dongsheng, et al. Determining harmonic contributions based on complex least squares method[J]. Proceedings of the CSEE, 2013, 33(4): 149–155
[7] 牛胜锁, 梁志瑞, 张建华, 等. 基于广义岭估计的电力系统谐波状态估计[J]. 电力自动化设备, 2012, 32(7): 94–98
NIU Shengsuo, LIANG Zhirui, ZHANG Jianhua, et al. Power system harmonic state estimation based on generalized ridge estimation[J]. Electric Power Automation Equipment, 2012, 32(7): 94–98
[8] 舒勤, 彭安庆, 徐方维, 等. 多直流馈入受端城市电网直流落点处系统侧谐波阻抗估计方法[J]. 高电压技术, 2020, 46(6): 2049–2056
SHU Qin, PENG Anqing, XU Fangwei, et al. Method for utility harmonic impedance estimation at DC terminals of multi-infeed urban power network[J]. High Voltage Engineering, 2020, 46(6): 2049–2056
[9] 孙媛媛, 尹志明. 基于M估计稳健回归的多谐波源责任区分[J]. 中国电机工程学报, 2012, 32(31): 166–173,233
SUN Yuanyuan, YIN Zhiming. Quantifying harmonic responsibilities of multiple harmonic sources based on M-estimation robust regression[J]. Proceedings of the CSEE, 2012, 32(31): 166–173,233
[10] 刘苏婕, 肖先勇, 刘亚梅, 等. 基于IGG权重函数复数域多元线性回归算法的谐波责任分摊方法[J]. 电力自动化设备, 2017, 37(3): 160–166
LIU Sujie, XIAO Xianyong, LIU Yamei, et al. Harmonic responsibility allocation method based on complex field multiple linear regression algorithm with IGG weight function[J]. Electric Power Automation Equipment, 2017, 37(3): 160–166
[11] 邱思语, 杨洪耕. 改进的加权支持向量机回归的谐波发射水平估计方法[J]. 电工技术学报, 2016, 31(5): 85–90
QIU Siyu, YANG Honggeng. Assessment method of harmonic emission level based on the improved weighted support vector machine regression[J]. Transactions of China Electrotechnical Society, 2016, 31(5): 85–90
[12] 惠锦, 杨洪耕, 叶茂清. 多谐波源条件下的谐波污染责任划分研究[J]. 中国电机工程学报, 2011, 31(13): 48–54
HUI Jin, YANG Honggeng, YE Maoqing. Research on the responsibility partition of harmonic pollution of multiple harmonic sources[J]. Proceedings of the CSEE, 2011, 31(13): 48–54
[13] 孟思雨, 肖先勇, 张逸, 等. 基于有效数据段选取的多谐波源责任划分方法[J]. 电网技术, 2017, 41(6): 2006–2011
MENG Siyu, XIAO Xianyong, ZHANG Yi, et al. A valid data selection method in estimating harmonic impact of individual loads[J]. Power System Technology, 2017, 41(6): 2006–2011
[14] WANG Y, MAZIN H E, XU W, et al. Estimating harmonic impact of individual loads using multiple linear regression analysis[J]. International Transactions on Electrical Energy Systems, 2016, 26(4): 809–824.
[15] 许加柱, 庞丽忠, 张志文, 等. 多谐波源用户的谐波责任分摊的定量分析[J]. 电力自动化设备, 2012, 32(12): 38–42
XU Jiazhu, PANG Lizhong, ZHANG Zhiwen, et al. Quantitative analysis for harmonic responsibility proration among multiple harmonic sources[J]. Electric Power Automation Equipment, 2012, 32(12): 38–42
[16] 谷湘潜, 康红文, 曹鸿兴. 复数域内的最小二乘法[J]. 自然科学进展, 2006, 16(1): 49–54
[17] 杨源, 林圣, 臧天磊, 等. 基于改进稀疏表示法的谐波源定位[J]. 电网技术, 2013, 37(5): 1279–1284
YANG Yuan, LIN Sheng, ZANG Tianlei, et al. Improved sparse representation-based location of harmonic sources in power system[J]. Power System Technology, 2013, 37(5): 1279–1284
[18] 赵劲帅, 杨洪耕, 徐方维, 等. 基于稀疏成分分析的多直流馈入城市电网直流落点系统侧谐波阻抗计算方法[J]. 中国电机工程学报, 2019, 39(7): 2016–2025
ZHAO Jinshuai, YANG Honggeng, XU Fangwei, et al. Method of calculating system-side harmonic impedance for DC drop point in city grid with multi-infeed DC system based on sparse component analysis[J]. Proceedings of the CSEE, 2019, 39(7): 2016–2025
[19] 宗静静, 邱天爽. 稀疏表示中稀疏系数的l₁范数的特性分析[J]. 系统工程与电子技术, 2019, 41(12): 2692–2696
ZONG Jingjing, QIU Tianshuang. Characteristic analysis for the l₁ norm of sparse coefficients in sparse representation[J]. Systems Engineering and Electronics, 2019, 41(12): 2692–2696
[20] ABU-HASHIM R, BURCH R, CHANG G, et al. Test systems for harmonics modeling and simulation[J]. IEEE Transactions on Power Delivery, 1999, 14(2): 579–587.
[21] 李晓燕, 李弢, 马尽文. 高斯过程混合模型在含噪输入预测策略下的煤矿瓦斯浓度柔性预测[J]. 信号处理, 2021, 37(11): 2031–2040
LI Xiaoyan, LI Tao, MA Jinwen. Soft prediction of coal-mine gas concentration through the mixture of Gaussian processes under the noisy input prediction strategy[J]. Journal of Signal Processing, 2021, 37(11): 2031–2040
[22] 翟翠红, 汪建均, 冯泽彪. 基于高斯过程模型的多响应稳健参数设计[J]. 系统工程与电子技术, 2021, 43(12): 3683–3693
ZHAI Cuihong, WANG Jianjun, FENG Zebiao. Robust parameter design of multiple responses based on Gaussian process model[J]. Systems Engineering and Electronics, 2021, 43(12): 3683–3693
[23] 邓帅. 基于改进贝叶斯优化算法的CNN超参数优化方法[J]. 计算机应用研究, 2019, 36(7): 1984–1987
DENG Shuai. Hyper-parameter optimization of CNN based on improved Bayesian optimization algorithm[J]. Application Research of Computers, 2019, 36(7): 1984–1987
[24] 夏晶, 朱蓉军, 张昊, 等. 基于高斯过程的人臂可达运动臂位形预测[J]. 华中科技大学学报(自然科学版), 2021, 49(1): 17–23
XIA Jing, ZHU Rongjun, ZHANG Hao, et al. Arm configuration predicting based on Gaussian process for arm reachable motion[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2021, 49(1): 17–23
[25] 隋宗震, 王秋潇, 贾丹桐, 等. 基于AR模型与贝叶斯优化的SVM的结构损伤识别研究[J]. 低温建筑技术, 2020, 42(12): 74–76
SUI Zongzhen, WANG Qiuxiao, JIA Dantong, et al. Structural damage identification based on ar model and Bayesian optimization SVM[J]. Low Temperature Architecture Technology, 2020, 42(12): 74–76

基于贝叶斯优化弹性网络回归的谐波状态估计方法

Harmonic State Estimation Method Based on Bayesian Optimized Elastic Network Regression

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

模态框（Modal）标题

基于贝叶斯优化弹性网络回归的谐波状态估计方法

Harmonic State Estimation Method Based on Bayesian Optimized Elastic Network Regression

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics