基于改进长短期记忆网络模型的电力系统惯性时间常数估计方法

doi:10.3969/j.issn.1008-0198.2026.05.004

湖南电力 ›› 2026, Vol. 46 ›› Issue (5): 24-32.doi: 10.3969/j.issn.1008-0198.2026.05.004

基于改进长短期记忆网络模型的电力系统惯性时间常数估计方法

郑锦, 张登极, 李毅博, 连晨曦, 杨苓

广东工业大学自动化学院,广东广州 510006

收稿日期:2026-06-24 修回日期:2026-07-21 发布日期:2026-11-06
通信作者: 杨苓(1992),女,副教授,研究方向为新型电力系统的稳定运行与控制。
基金资助:
广东省基础与应用基础研究基金项目（2026A1515010066）; 电能高效高质转化全国重点实验室开放基金（2024KF008）

Estimation Method of Inertial Time Constant in Power System Based on Improved Long Short-Term Memory Network Model

ZHENG Jin, ZHANG Dengji, LI Yibo, LIAN Chenxi, YANG Ling

School of Automation, Guangdong University of Technology, Guangzhou 510006, China

Received:2026-06-24 Revised:2026-07-21 Published:2026-11-06

摘要/Abstract

摘要： 随着可再生能源的不断接入,电力系统的惯性时间常数有所下降,精确估计惯性时间常数,对电网安全稳定运行具有重要意义。本文提出一种食肉植物算法(carnivorous plant algorithm,CPA)和长短期记忆网络(long short-term memory network,LSTM)模型相结合的电力系统惯性时间常数估计方法,采用CPA改进LSTM模型,实现模型超参数的自动调优,从而具备更高的寻优精度和更强的全局搜索能力。搭建IEEE 10机39节点系统进行实验验证,相比4种LSTM模型惯性时间常数估计方法,本文提出的方法具有更高的估计精度和更快的收敛速度。

关键词: 新型电力系统, 惯性时间常数估计, 长短期记忆网络模型, 食肉植物算法

Abstract: With the continuous integration of renewable energy, the inertia time constant of the power system has decreased, and accurate estimation of the inertia time constant is becoming increasingly important for the stable and safe operation of the power grid. This article proposes a method for estimating the inertia time constant of power systems by combining the carnivorous plant algorithm (CPA) and long short-term memory network (LSTM) model. The CPA is used to improve the LSTM model and achieve automatic tuning of model hyperparameters, resulting in higher optimization accuracy and stronger global search capability. Finally, the standard IEEE 10-machine 39-bus test system is estabished for verification. Compared with four conventional LSTM-based model inertia time constant estimation methods, the method proposed in this paper has higher estimation accuracy and faster convergence speed.

Key words: new power system, inertia time constant estimation, long short-term memory network model, carnivorous plant algorithm

中图分类号:

TM712

郑锦, 张登极, 李毅博, 连晨曦, 杨苓. 基于改进长短期记忆网络模型的电力系统惯性时间常数估计方法[J]. 湖南电力, 2026, 46(5): 24-32.

ZHENG Jin, ZHANG Dengji, LI Yibo, LIAN Chenxi, YANG Ling. Estimation Method of Inertial Time Constant in Power System Based on Improved Long Short-Term Memory Network Model[J]. Hunan Electric Power, 2026, 46(5): 24-32.

参考文献

[1] 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):5179-5191.
[2] 葛睿,王坤,王轶禹,等. “9.28”及“2.8”南澳大利亚电网大停电事件对我国电网调度运行的启示[J]. 电器工业,2017,(8):66-71.
[3] 孙华东,许涛,郭强,等. 英国“8·9”大停电事故分析及对中国电网的启示[J]. 中国电机工程学报,2019,39(21):6183-6192.
[4] 徐波,章林炜,俞向栋,等. 基于系统辨识的电力系统惯量在线评估改进方法[J]. 电力系统保护与控制,2021,49(18):62-69.
[5] 程定一,马欢,秦昊,等. 基于准稳态数据的电力系统等效惯量评估方法[J]. 现代电力,2023,40(4):434-440.
[6] Qin H,Cao Y J,Zhang H X,et al.Quantitative inertia estimation method for wind farm based on AFF-RLS[C]//2022 8th International Conference on Control Science and Systems Engineering(ICCSSE). 2022:74-78.
[7] 叶洪波,姜阳,陈雪梅,等. 基于先验方差的发电机惯量辨识数据质量评估[J]. 电力工程技术,2022,41(2):201-208.
[8] 张磊,熊致知,叶婧,等. 考虑风电不确定性的电力系统惯量评估方法[J]. 电工电能新技术,2023,42(1):89-96.
[9] 刘志坚,洪朝飞,郭成,等. 基于WRLS-ARMAX系统辨识的新能源电力系统惯量评估[J]. 电机与控制应用,2024,51(7):84-93.
[10] Hartono J,Pramana P A A,Kusuma A A,et al. Power system inertia estimation based on frequency measurement[C]//2019 Asia Pacific Conference on Research in Industrial and Systems Engineering(APCoRISE). 2019:1-4.
[11] 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.
[12] Kisinga D A,Makolo P,Trodden P.A neural network-based online estimation of stochastic inertia in a power system[C]//2022 IEEE PES/IAS PowerAfrica.2022:1-5.
[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). 2021:1-6.
[14] 杨思燃,杨苓,李毅博,等. 基于深度特征学习与优化回归建模的电力系统惯量估计策略[J]. 湖南电力,2026,46(1):107-113.
[15] Das S,Chattopadhyay P.Data-driven inertia estimation of power systems using autoencoder based unsupervised feature learning[C]//2023 IEEE 3rd Applied Signal Processing Conference(ASPCON). 2023:222-226.
[16] Egbomwan O E,Liu S C,Chaoui H.Physics-informed neural network for inertia estimation of power system with inverter-based distributed generation[C]//2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems(ICPS). 2024:1-8.
[17] Tuo M J,Li X P.Long-term recurrent convolutional net-work-based inertia estimation using ambient measurements[C]//2022 IEEE Industry Applications Society Annual Meeting(IAS). 2022:1-6.
[18] 徐艳春,任建新,宋文宇,等. 基于1D-SE-ResNet的含风电电力系统动态分区惯量评估[J]. 南方电网技术,2025,19(6):119-132.
[19] Shen J P,Zhang Y Q,Ma M Y,et al.Data-driven equivalent inertia partition estimation of power systems[C]//2022 Power System and Green Energy Conference(PSGEC). 2022:744-748.
[20] Tang Z,Hao L H,Feng J.Power system inertia estimation based on 1-dimensional deep convolution neural network[C]//2022 9th International Conference on Power Electronics Systems and Applications(PESA). 2022:1-6.
[21] 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.
[22] 商恒博,陈立亮,曹征,等. 基于WOA-LSTM的风力发电功率短期预测方法[J]. 电工技术,2025(9):41-45.
[23] Liu X,Lv S X,Wei J M,et al.Equivalent inertia estimation method in new power system based on DTW and CNN-BiLSTM[C]//2024 4th International Conference on Smart Grid and Energy Internet(SGEI). 2024:372-376.
[24] Tang Z,Hao L H,Li J P,et al.Power system inertia estimation based on long short term memory network[C]//2021 IEEE Sustainable Power and Energy Conference(iSPEC). 2021:2542-2547.
[25] Li G K,Lou W B,Ding L,et al.Equivalent virtual inertia estimation of wind turbines based on GS-LSTM[C]//2023 International Conference on Power System Technology(PowerCon). 2023:1-5.
[26] Liu X C,Yang J,Pei Y Z,et al.Equivalent inertia evaluation of new power system considering transient stability based on PSO-LSTM[C]//2024 4th International Conference on Neural Networks,Information and Communication Engineering(NNICE 2024). 2024:1566-1569.
[27] Moeini A,Kamwa I,Brunelle P,et al.Open data IEEE test systems implemented in Sim Power Systems for education and research in power grid dynamics and control[C]//2015 50th International Universities Power Engineering Conference(UPEC). 2015:1-6.
[28] Ong K M,Ong P,Sia C K.A carnivorous plant algorithm for solving global optimization problems[J]. Applied Soft Computing,2021,98:106833.

基于改进长短期记忆网络模型的电力系统惯性时间常数估计方法

Estimation Method of Inertial Time Constant in Power System Based on Improved Long Short-Term Memory Network Model

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

[1]	田海平, 王辉斌, 周立华, 任再美, 徐用良. 大型混流式水电机组宽负荷灵活调节技术改造研究[J]. 湖南电力, 2025, 45(2): 69-73.
[2]	孙海波, 李莉, 刘雨欣, 陆珊珊, 吴润泽. 基于经济效用的配电网通算资源协同部署方法[J]. 湖南电力, 2025, 45(2): 137-142.
[3]	崔一阳, 黎灿兵, 潘斗南, 李振恺, 刘行. 高比例新能源电力系统中机组组合研究综述[J]. 湖南电力, 2025, 45(1): 37-45.
[4]	段俊峰, 李晨坤, 姚文轩, 郭思源. 基于人工智能赋能的新型电力系统关键技术综述[J]. 湖南电力, 2024, 44(1): 1-10.
[5]	张艺明, 谢荣焕, 陈孝莺. 面向新型电力系统的双有源桥变换器及其混合调制研究[J]. 湖南电力, 2023, 43(5): 16-22.
[6]	钟伟, 周宇杰, 王泽烨, 宋军英. 新型电力系统安全稳定运行分析[J]. 湖南电力, 2022, 42(3): 29-34.
[7]	张思远, 龙高翔, 周过海, 张啸宇, 刘敦楠, 高源. 新型电力系统下的调度智能平衡系统研究[J]. 湖南电力, 2022, 42(2): 29-36.