Interval Prediction Method for Natural Frequency Characteristic Coefficient of Power System

doi:10.12204/j.issn.1000-7229.2021.09.011

Abstract

Abstract:

The natural frequency characteristic coefficient (β) of the power system is a significant basis for setting the frequency bias coefficient (B) in the automatic generation control (AGC) strategy. Setting B equal to β is the ideal principle of the B coefficient setting, because the AGC power adjustment is able to exactly reflect the power mismatch under this circumstance. However, the β coefficient is nonlinear and time-varying. The existing B coefficient setting methods cannot effectively track the changes of the β coefficient. In this regard, the interval prediction method for the β coefficient based on deep neural network (DNN) and Bootstrap is proposed. With the powerful capability of nonlinear feature extracting, DNN is utilized to establish the mapping relationship among power disturbance, reserve capacity, unit commitment, and the β coefficient. Thus, the prediction of the β coefficient can be achieved. In addition, combined with the Bootstrap method, the confidence interval of the predicted β coefficient is further obtained, which provides great supports for setting the B coefficient. Finally, simulation results verify the effectiveness and robustness of the proposed method.

Key words: natural frequency characteristic coefficient, frequency bias coefficient, interval prediction, deep neural network (DNN), Bootstrap method

CLC Number:

TM712

MENG Yongping, ZHANG Mingmei, XIANG Mingxu, YANG Yulu, HUANG Junkai, YANG Zhifang. Interval Prediction Method for Natural Frequency Characteristic Coefficient of Power System[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(9): 105-111.

Figures/Tables 6

Fig.1 Variation of the natural frequency characteristic coefficient with the power disturbance

Table 1 Impact of the system reserve allocation on the natural frequency characteristic coefficient

Table 2 Impact of the unit commitment on the natural frequency characteristic coefficient

Fig.2 Structure of DNN

Table 3 Comparison of interval prediction results

Table 4 Robustness of M1 to the forecast error of power disturbance %

References 24

[1]	朱全胜, 常烨骙, 张振安, 等. 面向各类功率扰动的频率控制及评估问题探讨[J]. 电力建设, 2018, 39(9):129-136.
	ZHU Quansheng, CHANG Yekui, ZHANG Zhen'an, et al. Discussion on frequency control and evaluation concerning all kinds of power disturbances[J]. Electric Power Construction, 2018, 39(9):129-136.
[2]	TAN C, LI Y, LAN Q, et al. Multi-area automatic generation control scheme considering frequency quality in southwest China grid: Challenges and solutions[J]. IEEE Access, 2020, 8:199813-199828. doi: 10.1109/Access.6287639 URL
[3]	刘乐, 刘娆, 李卫东, 等. 目标可控的超前频率偏差系数确定方法设计[J]. 电力系统自动化, 2007, 31(5):40-45.
	LIU Le, LIU Rao, LI Weidong, et al. Design of object-controllable and ahead frequency bias coefficient setting[J]. Automation of Electric Power Systems, 2007, 31(5):40-45.
[4]	刘乐, 刘娆, 李卫东. 自动发电控制中频率偏差系数确定方法的探讨[J]. 电力系统自动化, 2006, 30(6):42-47.
	LIU Le, LIU Rao, LI Weidong. Probe into frequency bias coefficient setting in automatic generation control[J]. Automation of Electric Power Systems, 2006, 30(6):42-47.
[5]	徐兴伟, 林伟, 金昌文. 东北电网联络线和频率控制偏差系数的选择[J]. 沈阳电力高等专科学校学报, 2002(2):22-24.
	XU Xingwei, LIN Wei, JIN Changwen. Bias coefficient selection of Tie-line & frequency control in north-east power system[J]. Journal of Shenyang Electric Power Institute, 2002(2):22-24.
[6]	VANSLYCK L S, JALEELI N, KELLEY W R. Implications of frequency control bias settings on interconnected system operation and inadvertent energy accounting[J]. IEEE Transactions on Power Systems, 1989, 4(2):712-723. doi: 10.1109/59.193847 URL
[7]	文丽, 王坚, 陈明辉, 等. 三段式频率偏差系数及其在互联电网调频中的应用[J]. 电力系统自动化, 2010, 34(19):59-63.
	WEN Li, WANG Jian, CHEN Minghui, et al. Three-stage frequency bias coefficient and its application in frequency control of interconnected power system[J]. Automation of Electric Power Systems, 2010, 34(19):59-63.
[8]	JALEELI N, VANSLYCK L S. NERC's new control performance standards[J]. IEEE Transactions on Power Systems, 1999, 14(3):1092-1099. doi: 10.1109/59.780932 URL
[9]	王茂海, 徐正山, 谢开, 等. 基于WAMS的系统自然频率特性系数确定方法[J]. 电力系统自动化, 2007, 31(3):15-18.
	WANG Maohai, XU Zhengshan, XIE Kai, et al. Calculation of frequency characteristic coefficients for an interconnected power system based on WAMS[J]. Automation of Electric Power Systems, 2007, 31(3):15-18.
[10]	吴军, 刘涤尘. 基于灰色预测的电力系统静态频率特性系数计算[J]. 电力系统保护与控制, 2012, 40(6):97-103.
	WU Jun, LIU Dichen. Calculation of the coefficient of static frequency characteristics of power system based on gray system forecast[J]. Power System Protection and Control, 2012, 40(6):97-103.
[11]	梁姗姗, 吴军, 刘涤尘, 等. 基于曲面拟合的电力系统节点动态频率响应特性的影响因素[J]. 武汉大学学报(工学版), 2017, 50(2):228-232.
	LIANG Shanshan, WU Jun, LIU Dichen, et al. Analysis of factors influencing nodal dynamic frequency response characteristics based on curved surface fitting[J]. Engineering Journal of Wuhan University, 2017, 50(2):228-232.
[12]	刘乐. 自动发电控制中频率偏差系数研究[D]. 大连: 大连理工大学, 2008.
	LIU Le. Research on frequency bias coefficient in automatic generation control. Dalian, China: Dalian University of Technology, 2008.
[13]	XIANG M X, YU J, YANG Z F, et al. Probabilistic power flow with topology changes based on deep neural network[J]. International Journal of Electrical Power & Energy Systems, 2020, 117:105650. doi: 10.1016/j.ijepes.2019.105650 URL
[14]	周悦, 谭本东, 李淼, 等. 基于深度学习的电力系统暂态稳定评估方法[J]. 电力建设, 2018, 39(2):103-108.
	ZHOU Yue, TAN Bendong, LI Miao, et al. Transient stability assessment of power system based on deep learning technology[J]. Electric Power Construction, 2018, 39(2):103-108.
[15]	YANG Y, YANG Z F, YU J, et al. Fast calculation of probabilistic power flow: A model-based deep learning approach[J]. IEEE Transactions on Smart Grid, 2020, 11(3):2235-2244. doi: 10.1109/TSG.5165411 URL
[16]	WEN S L, WANG Y, TANG Y, et al. Proactive frequency control based on ultra-short-term power fluctuation forecasting for high renewables penetrated power systems[J]. IET Renewable Power Generation, 2019, 13(12):2166-2173. doi: 10.1049/rpg2.v13.12 URL
[17]	HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification[C]// 2015 IEEE International Conference on Computer Vision (ICCV). December 7-13, 2015, Santiago, Chile. IEEE, 2015: 1026-1034.
[18]	TIELEMAN T, HINTON G. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude[R]. COURSERA: Neural networks for machine learning, 2012.
[19]	WAN C, XU Z, PINSON P, et al. Probabilistic forecasting of wind power generation using extreme learning machine[J]. IEEE Transactions on Power Systems, 2014, 29(3):1033-1044. doi: 10.1109/TPWRS.2013.2287871 URL
[20]	MUTHÉN B. Moments of the censored and truncated bivariate normal distribution[J]. British Journal of Mathematical and Statistical Psychology, 1990, 43(1):131-143. doi: 10.1111/bmsp.1990.43.issue-1 URL
[21]	王焱, 汪震, 黄民翔, 等. 基于OS-ELM和Bootstrap方法的超短期风电功率预测[J]. 电力系统自动化, 2014, 38(6):14-19.
	WANG Yan, WANG Zhen, HUANG Minxiang, et al. Ultra-short-term wind power prediction based on OS-ELM and bootstrap method[J]. Automation of Electric Power Systems, 2014, 38(6):14-19.
[22]	宋建, 束洪春, 董俊, 等. 基于GM(1, 1)与BP神经网络的综合负荷预测[J]. 电力建设, 2020, 41(5):75-80.
	SONG Jian, SHU Hongchun, DONG Jun, et al. Comprehensive load forecast based on GM(1, 1) and BP neural network[J]. Electric Power Construction, 2020, 41(5):75-80.
[23]	HUANG G B, WANG D H, LAN Y. Extreme learning machines: A survey[J]. International Journal of Machine Learning and Cybernetics, 2011, 2(2):107-122. doi: 10.1007/s13042-011-0019-y URL
[24]	SHENG C Y, ZHAO J, WANG W, et al. Prediction intervals for a noisy nonlinear time series based on a bootstrapping reservoir computing network ensemble[J]. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(7):1036-1048. doi: 10.1109/TNNLS.2013.2250299 URL