[1]张建华,程小轩,黄德豪.基于核注意力-Transformer的电力系统惯量估计方法[J].郑州大学学报(工学版),2026,47(3):143-150.[doi:10.13705/j.issn.1671-6833.2026.03.004]
　ZHANG Jianhua,CHENG Xiaoxuan,HUANG Dehao.A Method for Estimating the Inertia of Interconnected New Energy Power Systems Based on KAN-Transformer[J].Journal of Zhengzhou University (Engineering Science),2026,47(3):143-150.[doi:10.13705/j.issn.1671-6833.2026.03.004]
点击复制

基于核注意力-Transformer的电力系统惯量估计方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
47
期数:
2026年3期
页码:
143-150
栏目:
出版日期:
2026-05-27

文章信息/Info

Title:
A Method for Estimating the Inertia of Interconnected New Energy Power Systems Based on KAN-Transformer
文章编号:
1671-6833(2026)03-0143-08
作者:
张建华1,2, 程小轩1, 黄德豪1
1.华北电力大学 控制与计算机工程学院,北京 102206;2.新能源电力系统全国重点实验室,北京 102206
Author(s):
ZHANG Jianhua1,2, CHENG Xiaoxuan1, HUANG Dehao1
1.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China;2.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, Beijing 102206, China
关键词:
互联区域惯量估计;  低惯性;  深度学习网络;  Transformer;  KAN;  惯性分布可视化
Keywords:
interconnected inertia estimation;  low-inertia;  deep learning network;  Transformer;  KAN;  inertia distribution visualization
分类号:
TP29:TM715
DOI:
10.13705/j.issn.1671-6833.2026.03.004
文献标志码:
A
摘要:
针对高比例可再生能源并网的区域互联电力系统惯量估计问题,提出了一种基于Transformer与核注意力网络相结合的新型核注意力-Transformer估计算法,旨在精准高效估计系统区域惯量。首先,构建含可再生能源的区域电力系统动态响应模型;其次,利用Transformer的自注意力机制提取系统动态特征,并结合KAN的核注意力机制替代传统全连接层和softmax层,增强了模型对复杂非线性及强随机性数据的适应性与鲁棒性;最后,通过惯性分布的可视化,实现了惯量变化的实时监测,为系统运行人员提供了直观的决策依据。在改进的Australian 14机59节点系统中进行验证,与传统RNN、LSTM、GRU及Transformer相比,所提的核注意力-Transformer算法在不同仿真背景下,噪声过滤能力和估计精度均有显著提升。同时,惯量分布的可视化结果清晰呈现了系统惯量的时空变化特征,为电力系统的安全稳定运行提供了有力支撑。
Abstract:
Aiming at the problem of inertia estimation of regional interconnected power systems with a high proportion of renewable energy connected to the grid, a new estimation algorithm named kernel-Attention-Transformer based on the combination of Transformer and kernel attention network was proposed to accurately and efficiently estimate the regional inertia of the system. Then, the self-attention mechanism of Transformer was used to extract the dynamic features of the system, and KAN’s kernel attention mechanism was combined to replace the traditional fully connected layer and softmax layer, which enhanced the adaptability and robustness of the model for complex nonlinear and strong random data. In addition, through the visualization of inertia distribution, real-time monitoring of inertia changes was realized, which provided intuitive decision-making basis for system operators. Verified in the improved Australian 14-machine 59-node system, compared with the traditional RNN, LSTM, GRU and Transformer, the proposed kernel attention-Transformer algorithm significantly improved the noise filtering ability and estimation accuracy under different simulation backgrounds. At the same time, the visualization results of inertia distribution clearly showed the spatio-temporal variation characteristics of the system inertia, which provided strong support for the safe and stable operation of the power system.

参考文献/References:

[1]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.

LU Z X, JIANG J H, QIAO Y, et al. A review on generalized inertia analysis and optimization of new power systems[J]. Proceedings of the CSEE, 2023, 43(5): 17541776.
[2]王要强, 杨志伟, 王义, 等. 计及噪声和模型参数不确定的发电机动态状态估计[J]. 郑州大学学报(工学版), 2023, 44(6): 68-75.
WANG Y Q, YANG Z W, WANG Y, et al. Dynamic state estimation of generators considering noise and model parameter uncertainties[J]. Journal of Zhengzhou University (Engineering Science), 2023, 44(6): 68-75.
[3]TAN B D, ZHAO J B, 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.
[4]HEYLEN E, TENG F, STRBAC G. Challenges and opportunities of inertia estimation and forecasting in low-inertia power systems[J]. Renewable and Sustainable Energy Reviews, 2021, 147: 111176.
[5]HU P F, LI Y J, YU Y X, et al. Inertia estimation of renewable-energy-dominated power system[J]. Renewable and Sustainable Energy Reviews, 2023, 183: 113481.
[6]MAKOLO P, ZAMORA R, LIE T T. The role of inertia for grid flexibility under high penetration of variable renewables-A review of challenges and solutions[J]. Renewable and Sustainable Energy Reviews, 2021, 147: 111223.
[7]SCHIFFER J, ARISTIDOU P, ORTEGA R. Online estimation of power system inertia using dynamic regressor extension and mixing[J]. IEEE Transactions on Power Systems, 2019, 34(6): 4993-5001.
[8]YANG D Y, WANG B, CAI G W, et al. Data-driven estimation of inertia for multiarea interconnected power systems using dynamic mode decomposition[J]. IEEE Transactions on Industrial Informatics, 2021, 17(4): 2686-2695.
[9]ZHAO J B, TANG Y, TERZIJA V. Robust online estimation of power system center of inertia frequency[J]. IEEE Transactions on Power Systems, 2019, 34(1): 821-825.
[10] POUDYAL A, TAMRAKAR U, TREVIZAN R D, et al. Multiarea inertia estimation using convolutional neural networks and federated learning[J]. IEEE Systems Journal, 2022, 16(4): 6401-6412.
[11] HAN K, WANG Y H, CHEN H T, et al. A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 87-110.
[12] LIU Z M, WANG Y X, VAIDYA S, et al. KAN: Kolmogorov-arnold networks [EB/OL]. (2025-02-09)[2025-05-16]. https:∥arxiv.org/abs/2404.19756.
[13] LAVANYA L, SWARUP K S. Inertia monitoring in power systems: critical features, challenges, and framework[J]. Renewable and Sustainable Energy Reviews, 2024, 190: 114076.
[14] TUTTELBERG K, KILTER J, WILSON D, et al. Estimation of power system inertia from ambient wide area measurements[C]∥2019 IEEE Power & Energy Society General Meeting (PESGM). Piscataway: IEEE, 2019: 1.
[15]郭越, 徐飞, 郝玲, 等. 一次调频中的锅炉建模与参数在线确定[J]. 中国电机工程学报, 2023, 43(17): 6551-6562.
GUO Y, XU F, HAO L, et al. Boiler modeling and online parameters identification for primary frequency regulation[J]. Proceedings of the CSEE, 2023, 43(17): 6551-6562.
[16] ANDERSON P M, MIRHEYDAR M. A low-order system frequency response model[J]. IEEE Transactions on Power Systems, 1990, 5(3): 720-729.
[17] KRPAN M, KUZLE I. Introducing low-order system frequency response modelling of a future power system with high penetration of wind power plants with frequency support capabilities[J]. IET Renewable Power Generation, 2018, 12(13): 1453-1461.
[18]赵大伟, 马进, 钱敏慧, 等. 光伏电站参与大电网一次调频的控制增益研究[J]. 电网技术, 2019, 43(2): 425-435.
ZHAO D W, MA J, QIAN M H, et al. Research on control gain for photovoltaic power plants participating in primary frequency regulation of large power grid[J]. Power System Technology, 2019, 43(2): 425-435.
[19] MA H Z, LIU C Y, ZHAO H R, et al. A novel analytical unified energy flow calculation method for integrated energy systems based on holomorphic embedding[J]. Applied Energy, 2023, 344: 121163.
[20]王月, 申建建, 程春田, 等. 考虑电站集群与发电时变特性的风光出力描述方法[J]. 电网技术, 2023, 47(4): 1558-1572.
WANG Y, SHEN J J, CHENG C T, et al. Description of wind and solar power generation considering power plant clusters and time-varying power characteristics[J]. Power System Technology, 2023, 47(4): 1558-1572.
[21] SUPERCHI F, GIOVANNINI N, MOUSTAKIS A, et al. Optimization of the power output scheduling of a renewables-based hybrid power station using MILP approach: the case of Tilos island[J]. Renewable Energy, 2024, 220: 119685.
[22] CHICCO D, WARRENS M J, JURMAN G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. PeerJ Computer Science, 2021, 7: e623.

更新日期/Last Update: 2026-05-27