基于时空图卷积网络和自注意机制的频率稳定性预测

doi:10.19595/j.cnki.1000-6753.tces.230858

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (5566 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Power system frequency dynamic characteristics serve for system stability evaluation and reflects the specific change of frequency when there is a power imbalance between generation and load. On the one hand, the distribution of topology is closely connected with the stability of the power grid in the frequency stability prediction (FSP) problem and the topology of the power grid is typically altered by the random events. On the other hand, the frequency stability characteristics are mirrored in the post-fault response trajectory, so that the time-varying features and dynamic topologies may contribute to the nonlinear spatial-temporal dynamics of FSP. However, the traditional data-driven methods fail to effectively incorporate the system spatial-temporal characteristics into the model training, and suffers from insufficient utilization of system information, poor generalization ability in the face of new topology and interpretability. In addition, the machine learning (ML) model employed for prediction resembles a "black box" internally, and lack of interpretability is one of the primary challenges to ML application in the FSP field. To give a highly accurate FSP reference and denote the potential security hazards of the system, the model is required to identify the major factors that influence the FSP and clarify the decision-making process of model learning.
To address these issues, this paper proposes a FSP prediction method that combines the self-attention mechanism (SAM) and the spatial-temporal graph convolutional network (STGCN). Firstly, the proposed STGCN prediction method utilizes a one-dimensional temporal convolutional layer to extract system temporal information. In addition, it employs Chebyshev graph convolution to approximate the Laplacian matrix through polynomial functions, enabling graph convolution operations to capture the topological structure information of each bus and its neighbors. After that, a differentiable self-attention graph pooling (SAGPooling) layer based on SAM is employed to enhance the generalization ability and robustness of the STGCN model. The layer allows the model to reduce the dimensionality of the feature vectors in order to decrease the number of parameters and avoid overfitting. The hierarchical pooling strategy enables the model to preserve valuable node features as much as possible and effectively allocate nodes based on the preserved features and changing topology to enhance the generalization ability and robustness of the STGCN. Meanwhile, the attention scores of each node can be uniformly extracted. Finally, through the SAM, the attention scores of nodes are obtained according to the active power to perform the interpretability analysis of the STGCN model. In summary, this model converts input data into high-level representations of graphics through graph convolution, time convolution, and SAGPooling to integrate the complete spatiotemporal dynamics of FSP. Therefore, the accuracy, generalization ability, and robustness of the proposed STGCN have been improved, and the interpretable analysis of the model decision-making process can be carried out. The testing results on the modified New England 39-bus system and the modified ACTIVSg500 system, which incorporate renewable energy sources, validate the effectiveness of the proposed STGCN. Among all the tested methods, the STGCN has higher prediction accuracy, better robustness, and generalization capability. In addition, the STGCN can provide critical influence factors of different buses on the prediction results in this work.

Key words： Frequency stability prediction deep learning spatial-temporal graph neural networks self-attention mechanism interpretability analysis

Received: 06 June 2023

PACS:

TM712

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Du Donglai
	Han Song
	Rong Na

Cite this article:

Du Donglai,Han Song,Rong Na. Frequency Stability Prediction Method Based on Modified Spatial Temporal Graph Convolutional Networks and Self-Attention[J]. Transactions of China Electrotechnical Society, 2024, 39(16): 4985-4995.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.230858 OR https://dgjsxb.ces-transaction.com/EN/Y2024/V39/I16/4985

[1] 李兆伟, 方勇杰, 吴雪莲, 等. 频率紧急控制中动作时延和措施量对低惯量系统控制有效性的影响分析[J/OL]. 电工技术学报, 2023: 1-13[2023-10-24]. https://doi.org/10.19595/j.cnki.1000-6753.tces.231175.
Li Zhaowei, Fang Yongjie, Wu Xuelian, et al. Influence of action delay and amount on the control effectiveness of low inertia systems in frequency emergency control[J/OL]. Transactions of China Electrotechnical Society, 2023: 1-13[2023-10-24]. https://doi.org/10.19595/j.cnki.1000-6753.tces.231175.
[2] 柯德平, 冯帅帅, 刘福锁, 等. 新能源发电调控参与的送端电网直流闭锁紧急频率控制策略快速优化[J]. 电工技术学报, 2022, 37(5): 1204-1218.
Ke Deping, Feng Shuaishuai, Liu Fusuo, et al.Rapid optimization for emergent frequency control strategy with the power regulation of renewable energy during the loss of DC connection[J]. Transactions of China Electrotechnical Society, 2022, 37(5): 1204-1218.
[3] 李锡林, 查晓明, 田震, 等. 频率突变影响下基于Lyapunov法的孤岛微电网暂态稳定性分析[J]. 电工技术学报, 2023, 38(增刊1): 18-31.
Li Xilin, Zha Xiaoming, Tian Zhen, et al.Lyapunov based transient stability analysis of islanded microgrid under the influence of frequency abrupt change[J]. Transactions of China Electrotechnical Society, 2023, 38(S1): 18-31.
[4] 关中杰, 鲁效平, 李钢强, 等. 基于风速模型的风电机组动态转矩前馈控制技术[J]. 电工技术学报, 2018, 33(22): 5338-5345.
Guan Zhongjie, Lu Xiaoping, Li Gangqiang, et al.Dynamic torque feed forward control technology of wind turbine based on wind speed model[J]. Transactions of China Electrotechnical Society, 2018, 33(22): 5338-5345.
[5] Azizi S, Sun Mingyu, Liu Gaoyuan, et al.Local frequency-based estimation of the rate of change of frequency of the center of inertia[J]. IEEE Transactions on Power Systems, 2020, 35(6): 4948-4951.
[6] 陈宗遥, 卜旭辉, 郭金丽. 基于神经网络的数据驱动互联电力系统负荷频率控制[J]. 电工技术学报, 2022, 37(21): 5451-5461.
Chen Zongyao, Bu Xuhui, Guo Jinli.Neural network based data-driven load frequency control for interconnected power systems[J]. Transactions of China Electrotechnical Society, 2022, 37(21): 5451-5461.
[7] 苏玉刚, 颜志琼, 胡宏晟, 等. 基于频率切换实现恒流/恒压输出的电场耦合无线电能传输系统[J]. 中国电机工程学报, 2024, 44(4): 1553-1565.
Su Yugang, Yan Zhiqiong, Hu Hongsheng, et al.Electric-field coupled power transfer system with constant current/constant voltage output characteristics based on frequency switching[J]. Proceedings of the CSEE, 2024, 44(4): 1553-1565.
[8] Cao Yongji, Zhang Hengxu, Zhang Yi, et al.Extending SFR model to incorporate the influence of thermal states on primary frequency response[J]. IET Generation, Transmission & Distribution, 2020, 14(19): 4069-4078.
[9] 石访, 张林林, 胡熊伟, 等. 基于多属性决策树的电网暂态稳定规则提取方法[J]. 电工技术学报, 2019, 34(11): 2364-2374.
Shi Fang, Zhang Linlin, Hu Xiongwei, et al.Power system transient stability rules extraction based on multi-attribute decision tree[J]. Transactions of China Electrotechnical Society, 2019, 34(11): 2364-2374.
[10] 马良玉, 程善珍. 基于支持向量数据描述和XGBoost的风电机组异常工况预警研究[J]. 电工技术学报, 2022, 37(13): 3241-3249.
Ma Liangyu, Cheng Shanzhen.Abnormal state early warning of wind turbine generator based on support vector data description and XGBoost[J]. Transactions of China Electrotechnical Society, 2022, 37(13): 3241-3249.
[11] 叶瑞丽, 郭志忠, 刘瑞叶, 等. 基于小波包分解和改进Elman神经网络的风电场风速和风电功率预测[J]. 电工技术学报, 2017, 32(21): 103-111.
Ye Ruili, Guo Zhizhong, Liu Ruiye, et al.Wind speed and wind power forecasting method based on wavelet packet decomposition and improved Elman neural network[J]. Transactions of China Electrotechnical Society, 2017, 32(21): 103-111.
[12] 崔昊, 冯双, 陈佳宁, 等. 基于自编码器与长短期记忆网络的宽频振荡广域定位方法[J]. 电力系统自动化, 2022, 46(12): 194-201.
Cui Hao, Feng Shuang, Chen Jianing, et al.Wide-area location method of wide-band oscillations based on autoencoder and long short-term memory network[J]. Automation of Electric Power Systems, 2022, 46(12): 194-201.
[13] 王彦博, 吴俊勇, 季佳伸, 等. 基于深度残差收缩网络的电力系统暂态频率安全集成评估[J]. 电网技术, 2023, 47(2): 482-494.
Wang Yanbo, Wu Junyong, Ji Jiashen, et al.Integrated assessment of power system transient frequency security based on deep residual shrinkage network[J]. Power System Technology, 2023, 47(2): 482-494.
[14] 时纯, 刘君, 梁卓航, 等. 基于GAN和多通道CNN的电力系统暂态稳定评估[J]. 电网技术, 2022, 46(8): 3191-3202.
Shi Chun, Liu Jun, Liang Zhuohang, et al.Transient stability assessment of power system based on GAN and multi-channel CNN[J]. Power System Technology, 2022, 46(8): 3191-3202.
[15] 王铮澄, 周艳真, 郭庆来, 等. 考虑电力系统拓扑变化的消息传递图神经网络暂态稳定评估[J]. 中国电机工程学报, 2021, 41(7): 2341-2350.
Wang Zhengcheng, Zhou Yanzhen, Guo Qinglai, et al.Transient stability assessment of power system considering topological change: a message passing neural network-based approach[J]. Proceedings of the CSEE, 2021, 41(7): 2341-2350.
[16] Xie Jian, Sun Wei.A transfer and deep learning-based method for online frequency stability assessment and control[J]. IEEE Access, 2021, 9: 75712-75721.
[17] Zhan Xianwen, Han Song, Rong Na, et al.A two-stage transient stability prediction method using convolutional residual memory network and gated recurrent unit[J]. International Journal of Electrical Power & Energy Systems, 2022, 138: 107973.
[18] 韩天森, 陈金富, 李银红, 等. 电力系统稳定评估机器学习可解释代理模型研究[J]. 中国电机工程学报, 2020, 40(13): 4122-4131.
Han Tiansen, Chen Jinfu, Li Yinhong, et al.Study on interpretable surrogate model for power system stability evaluation machine learning[J]. Proceedings of the CSEE, 2020, 40(13): 4122-4131.
[19] 陈明华, 刘群英, 张家枢, 等. 基于XGBoost的电力系统暂态稳定预测方法[J]. 电网技术, 2020, 44(3): 1026-1034.
Chen Minghua, Liu Qunying, Zhang Jiashu, et al.XGBoost-based algorithm for post-fault transient stability status prediction[J]. Power System Technology, 2020, 44(3): 1026-1034.
[20] Yu Bing, Yin Haoteng, Zhu Zhanxing. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[J/OL]. ArXiv, 2017: 1709.04875. https://arxiv.org/abs/1709. 04875.pdf.
[21] Zhao Junbo, Tang Yi, Terzija V.Robust online estimation of power system center of inertia frequency[J]. IEEE Transactions on Power Systems, 2019, 34(1): 821-825.
[22] Lee J, Lee I, Kang J.Self-attention graph pooling[C]// Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA, 2019: 3734-3743.
[23] 赵荣臻, 文云峰, 叶希, 等. 基于改进堆栈降噪自动编码器的预想事故频率指标评估方法研究[J]. 中国电机工程学报, 2019, 39(14): 4081-4093.
Zhao Rongzhen, Wen Yunfeng, Ye Xi, et al.Research on frequency indicators evaluation of disturbance events based on improved stacked denoising autoencoders[J]. Proceedings of the CSEE, 2019, 39(14): 4081-4093.
[24] 赵冬梅, 郑亚锐, 谢家康, 等. 基于轻量级梯度提升机和生成对抗网络的含风电电力系统频率稳定评估[J]. 电网技术, 2022, 46(8): 3181-3193.
Zhao Dongmei, Zheng Yarui, Xie Jiakang, et al.Frequency stability evaluation of power system containing wind power based on light gradient boosting machine and generative adversarial network[J]. Power System Technology, 2022, 46(8): 3181-3193.
[25] 周挺, 杨军, 詹祥澎, 等. 一种数据驱动的暂态电压稳定评估方法及其可解释性研究[J]. 电网技术, 2021, 45(11): 4416-4425.
Zhou Ting, Yang Jun, Zhan Xiangpeng, et al.Data-driven method and interpretability analysis for transient voltage stability assessment[J]. Power System Technology, 2021, 45(11): 4416-4425.