Power System Inertia Estimation Strategy Based on Deep Feature Learning and Optimized Regression Modeling

doi:10.3969/j.issn.1008-0198.2026.01.014

Abstract

Abstract: Power system inertia estimation is crucial to ensure the stability of the power grid and to cope with unexpected events. A Bird-mating Convolutional XGBoost Network(BCXNet) algorithm is proposed to accurately estimate the inertia value of the power system. Firstly, a convolutional neural network(CNN) is used to extract features of system inertia and construct high-level time series data features containing multidimensional features. Secondly, the eXtreme gradient boosting(XGBoost) is used for inertia regression analysis, and the XGBoost hyperparameters are optimized by combining the bird-mating optimizer(BMO), thereby further improving the accuracy of inertia estimation. Finally, the accuracy of inertia estimation by the proposed method is verified through experiments, and the coefficient of determination(R²) reaches 0.987 3, the root mean square error(RMSE) is 0.079 7, and the mean absolute percentage error(MPAE) is 2.6%, which indicates that the estimated model output is in high agreement with the real value.

Key words: power system, inertia estimation, feature extraction, eXtreme gradient boosting(XGBoost), hyperparameter tuning

CLC Number:

TM712

YANG Siran, YANG Ling, LI Yibo, XU Zhaoyang. Power System Inertia Estimation Strategy Based on Deep Feature Learning and Optimized Regression Modeling[J]. Hunan Electric Power, 2026, 46(1): 107-113.

References

[1] 张武其,文云峰,迟方德,等. 电力系统惯量评估研究框架与展望[J]. 中国电机工程学报,2021,41(20):6842-6855.
[2] 刘硕,马兆兴,刘金鑫,等. 面向新能源消纳的新型电力系统优化运行策略[J]. 湖南电力,2024,44(1):59-66.
[3] 鲁宗相,姜继恒,乔颖,等. 新型电力系统广义惯量分析与优化研究综述[J]. 中国电机工程学报,2023,43(5):1754-1776.
[4] 孙华东,王宝财,李文锋,等. 高比例电力电子电力系统频率响应的惯量体系研究[J]. 中国电机工程学报,2020,40(16):5179-5192.
[5] 马覃峰,安甦,刘明顺,等. 考虑风光储调频贡献度的新型电力系统频率特性[J]. 南方电网技术,2024,18(11):129-140.
[6] 曾繁宏,张俊勃. 电力系统惯性的时空特性及分析方法[J]. 中国电机工程学报,2020,40(1):50-58,373.
[7] 李世春,宋秋爽,薛臻瑶,等. 含风电虚拟惯性响应的新能源电力系统惯量估计[J]. 电力工程技术,2023,42(2):84-93.
[8] 刘永刚,汪婧文,吴晋波,等. 基于增广递推最小二乘的电网等效惯量在线估计方法[J]. 湖南电力,2024,44(4):40.
[9] ULBIG A,BORSCHE T S,ANDERSSON G.Impact of low rotational inertia on power system stability and operation[J]. IFAC Proceedings Volumes,2014,47(3):7290-7297.
[10] 陈义宣,冯帅帅,李玲芳,等. 基于常规扰动数据的电网分区及惯量在线辨识方法[J]. 南方电网技术,2023,17(7):83-94.
[11] ZHANG J B,XU H C.Online identification of power system equivalent inertia constant[J]. IEEE Transactions on Industrial Electronics,2017,64(10):8098-8107.
[12] 彭彪,陈锴锋. 基于大数据和机器学习的电网故障预测与诊断系统[J]. 电工技术,2025(4):88-90.
[13] POUDYAL A,FOURNEY R,TONKOSKI R,et al. Convolutional neural network-based inertia estimation using local frequency measurements[C]//2020 52nd North American Power Symposium(NAPS). Tempe,AZ,USA. IEEE,2021:1-6.
[14] LINARO D,BIZZARRI F,DEL GIUDICE D,et al.Continuous estimation of power system inertia using convolutional neural networks[J]. Nature Communications,2023,14:4440.
[15] TANG Z,HAO L,LI J,et al.Power System Inertia Estimation Based on Long Short Term Memory Network[C]//2021 IEEE Sustainable Power and Energy Conference (iSPEC). Nanjing,China. IEEE,2021:2542-2547.
[16] SCHMITT A,LEE B.Steady-state inertia estimation using a neural network approach with modal information[C]//2017 IEEE Power & Energy Society General Meeting. IEEE,2017:1-5.
[17] PAIDI E S N R,MARZOOGHI H,YU J,et al. Development and validation of artificial neural network-based tools for forecasting of power system inertia with wind farms penetration[J]. IEEE Systems Journal,2020,14(4):4978-4989.
[18] 张磊,李海涛,熊致知,等. 基于可解释性XGBoost的电力系统惯量短期预测方法[J]. 电力建设,2023,44(8):22-30.
[19] 孙厚举. 基于BMO算法混合神经网络的短时交通流预测[J]. 信息与电脑(理论版),2023,35(3):108-112.
[20] 张晶,高岳林. SOA和BMO的柔性分层次车间调度研究[J]. 计算机工程与应用,2017,53(17):254-259.
[21] LI G,LOU W,DING L,et al.Equivalent Virtual Inertia Estimation of Wind Turbines Based on GS-LSTM[C]//2023 International Conference on Power System Technology (PowerCon). Jinan,China. IEEE,2023:1-5.
[22] 李东辉,臧晓明,鞠平,等. 电力系统频率响应的改进模型与参数估计[J]. 电力工程技术,2019,38(5):85-90.
[23] HUANG H,JU P,JIN Y Q,et al.Generic system frequency response model for power grids with different generations[J]. IEEE Access,2020,8:14314-14321.
[24] 姜建,刘海琼,李衡,等. 基于XGBoost的配电网线路峰值负荷预测方法[J]. 电力系统保护与控制,2021,49(16):119-127.
[25] 刘瑾,赵晶,冯瑛敏,等. 基于梯度提升决策树的电力物联网用电负荷预测[J]. 智慧电力,2022,50(8):46-53.
[26] 李逸欣,吴伟杰,张伊宁,等. 大规模新能源接入的电力系统惯量缺失机理及惯量水平评估[J]. 南方能源建设,2024,11(5):132-139.
[27] TAN B,ZHAO J,NETTO M,et al.Power system inertia estimation:Review of methods and the impacts of converter-interfaced generations[J]. International Journal of Electrical Power & Energy Systems,2022,134:107362.