Transient Power Angle Stability Evaluation and Interpretability Analysis of AC/DC Hybrid Power System

doi:10.12204/j.issn.1000-7229.2024.02.001

Abstract

Abstract:

Compared with traditional power systems, the structure of an AC/DC hybrid system with new energy sources is more complex, its stability evaluation is more difficult, and the identification and interpretation of stability influencing factors are poor. Given the above problems, this study first selects new energy and DC features as the input of the stability evaluation model and obtains the relationship between the sample prediction value and the stability result using the sigmoid function. A transient power-angle stability evaluation method for an AC/DC hybrid system based on extreme gradient Boosting (XGBoost) was proposed. To further analyze the influence of features on the transient power angle stability of the system, an interpretable analysis method of features based on SHAP is proposed, which explains the importance of new energy and DC features from a global perspective, which reflects the relationship between the size of each feature itself and the promotion and inhibition of stability results from the perspective of all samples, and then obtains the influence of features on the stability results of a single sample from a local perspective. Finally, simulation verification was performed on a 500 kV actual AC/DC hybrid system, which proves that the accuracy of the evaluation method is high and that SHAP can effectively explain the influence of new energy and DC features on the transient power angle stability of the AC/DC hybrid system.

Key words: AC/DC hybrid system, transient power angle stability, features, interpretability

CLC Number:

TM73

LI Yahan, XIA Shiwei, MA Linlin, ZHAO Kang, LI Xin. Transient Power Angle Stability Evaluation and Interpretability Analysis of AC/DC Hybrid Power System[J]. ELECTRIC POWER CONSTRUCTION, 2024, 45(2): 1-9.

Figures/Tables 10

Fig.1 Interpretability of features

Table 1 Features of TASA

Table 2 Confusion matrix of TASA

Fig.2 Flow chart of TASA

Fig.3 Example topology

Table 3 Performance comparison of classification method

Fig.4 Importance ranking of features

Fig.5 Shapley value of features

Fig.6 Prediction result of single stable sample

Fig.7 Prediction result of single unstable sample

References 30

[1]	江琴, 刘天琪, 曾雪洋, 等. 大规模风电与直流综合作用对送端系统暂态稳定影响机理[J]. 电网技术, 2018, 42(7): 2038-2046.
	JIANG Qin, LIU Tianqi, ZENG Xueyang, et al. Influence mechanism of comprehensive action of large-scale wind power and HVDC transmission system on sending system transient stability[J]. Power System Technology, 2018, 42(7): 2038-2046.
[2]	JI L Y, WU J Y, ZHOU Y Z, et al. Using trajectory clusters to define the most relevant features for transient stability prediction based on machine learning method[J]. Energies, 2016, 9: 1-19. doi: 10.3390/en9010001 URL
[3]	ZHU L P, HILL D J. Networked time series shapelet learning for power system transient stability assessment[J]. IEEE Transactions on Power Systems, 2022, 37(1): 416-428. doi: 10.1109/TPWRS.2021.3093423 URL
[4]	叶圣永, 王晓茹, 刘志刚, 等. 基于支持向量机增量学习的电力系统暂态稳定评估[J]. 电力系统自动化, 2011, 35(11): 15-19.
	YE Shengyong, WANG Xiaoru, LIU Zhigang, et al. Power system transient stability assessment based on support vector machine incremental learning method[J]. Automation of Electric Power Systems, 2011, 35(11): 15-19.
[5]	ZHOU Y Z, WU J Y, HAO L L, et al. Transient stability prediction of power systems using post-disturbance rotor angle trajectory cluster features[J]. Electric Power Components and Systems, 2016, 44(17): 1879-1891. doi: 10.1080/15325008.2016.1204373 URL
[6]	刘信彤, 辛业春, 王长江, 等. 基于Smo-PinSVM的含新能源电力系统暂态稳定评估[J]. 太阳能学报, 2021, 42(5): 98-104.
	LIU Xintong, XIN Yechun, WANG Changjiang, et al. Transient stability assessment in bulk power grid with renewable energy using smo-pinsvm[J]. Acta Energiae Solaris Sinica, 2021, 42(5): 98-104.
[7]	张业宇, 曾平良, 赵兵, 等. 基于深度神经网络的交直流电力系统暂态稳定评估方法[J]. 电力科学与工程, 2020, 36(9): 8-15. doi: 1672-0792(2020)09-0008-08
	ZHANG Yeyu, ZENG Pingliang, ZHAO Bing, et al. A new transient stability analysis approach for hybrid AC/DC systems based on deep neural network method[J]. Electric Power Science and Engineering, 2020, 36(9): 8-15. doi: 1672-0792(2020)09-0008-08
[8]	杨博, 陈义军, 姚伟, 等. 基于新一代人工智能技术的电力系统稳定评估与决策综述[J]. 电力系统自动化, 2022, 46(22): 200-223.
	YANG Bo, CHEN Yijun, YAO Wei, et al. Review on stability assessment and decision for power systems based on new-generation artificial intelligence technology[J]. Automation of Electric Power Systems, 2022, 46(22): 200-223.
[9]	史法顺, 吴俊勇, 吴昊衍, 等. 基于深度学习的电力系统暂态功角与暂态电压稳定裕度一体化评估[J]. 电网技术, 2023, 47(2): 731-740.
	SHI Fashun, WU Junyong, WU Haoyan, et al. Integrated evaluation of power system transient power angle and transient voltage stability margin based on deep learning[J]. Power System Technology, 2023, 47(2): 731-740.
[10]	邵美阳, 吴俊勇, 李宝琴, 等. 基于两阶段集成深度置信网络的电力系统暂态稳定评估[J]. 电网技术, 2020, 44(5): 1776-1787.
	SHAO Meiyang, WU Junyong, LI Baoqin, et al. Transient stability assessment of power system based on two-stage ensemble deep belief network[J]. Power System Technology, 2020, 44(5): 1776-1787.
[11]	李楠, 朱嫄, 崔莹. 考虑代价敏感的AC-LSTM暂态稳定评估[J]. 电力系统保护与控制, 2022, 50(22): 160-169.
	LI Nan, ZHU Yuan, CUI Ying. AC-LSTM transient stability assessment considering cost-sensitivity[J]. Power System Protection and Control, 2022, 50(22): 160-169.
[12]	尹雪燕. 基于深度学习的交直流混联系统暂态稳定评估研究[D]. 济南: 山东大学, 2019.
	YIN Xueyan. Study on transient stability evaluation of AC-DC hybrid system based on deep learning[D]. Jinan: Shandong University, 2019.
[13]	刘鸣, 王长江, 李斌, 等. 基于轨迹簇和MBLDA的受端电网暂态电压稳定评估[J]. 电力系统保护与控制, 2021, 49(19): 27-37.
	LIU Ming, WANG Changjiang, LI Bin, et al. Transient voltage stability evaluation of a receiving-end power grid based on a trajectory cluster and MBLDA[J]. Power System Protection and Control, 2021, 49(19): 27-37.
[14]	张晨宇, 王慧芳, 叶晓君. 基于XGBoost算法的电力系统暂态稳定评估[J]. 电力自动化设备, 2019, 39(3): 77-83, 89.
	ZHANG Chenyu, WANG Huifang, YE Xiaojun. Transient stability assessment of power system based on XGBoost algorithm[J]. Electric Power Automation Equipment, 2019, 39(3): 77-83, 89.
[15]	胡润滋, 马晓忱, 孙博, 等. 基于特征选择的暂态安全评估方法及其可解释性研究[J]. 电网技术, 2023, 47(2): 755-763.
	HU Runzi, MA Xiaochen, SUN Bo, et al. Transient safety assessment and its interpretability based on feature selection[J]. Power System Technology, 2023, 47(2): 755-763.
[16]	朱利鹏, 陆超, 黄河, 等. 基于时序轨迹特征学习的暂态电压稳定评估[J]. 电网技术, 2019, 43(6): 1922-1931.
	ZHU Lipeng, LU Chao, HUANG He, et al. Transient voltage stability assessment based on sequential trajectory feature learning[J]. Power System Technology, 2019, 43(6): 1922-1931.
[17]	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.
[18]	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. doi: 10.3969/j.issn.1000-7229.2018.02.013
	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. doi: 10.3969/j.issn.1000-7229.2018.02.013
[19]	刘颂凯, 袁铭洋, 杨超, 等. 基于XGBoost和ASPSO的电力系统暂态稳定预防控制方法[J]. 电网与清洁能源, 2023, 39(10): 9-18.
	LIU Songkai, YUAN Mingyang, YANG Chao, et al. A transient stability preventive control method of power systems based on XGBoost and ASPSO[J]. Power System and Clean Energy, 2023, 39(10): 9-18.
[20]	郭培, 陈波, 高云超, 等. 基于XGBOOST-PSO提高受端电网电压暂态稳定的发电机无功优化方法[J]. 电力系统保护与控制, 2023, 51(13): 148-158.
	GUO Pei, CHEN Bo, GAO Yunchao, et al. A generator reactive power optimization method based on XGBOOST-PSO to improve the voltage transient stability of a receiving terminal network[J]. Power System Protection and Control, 2023, 51(13): 148-158.
[21]	LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. ACM, 2017: 4765-4774.
[22]	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.
[23]	郭小江, 赵丽莉, 汤奕, 等. 风火打捆交直流外送系统功角暂态稳定研究[J]. 中国电机工程学报, 2013, 33(22): 19-25.
	GUO Xiaojiang, ZHAO Lili, TANG Yi, et al. Study on angle transient stability for wind-thermal-bundled power transmitted by AC/DC system[J]. Proceedings of the CSEE, 2013, 33(22): 19-25.
[24]	PHILIP CHEN C L, LIU Z L, FENG S. Universal approximation capability of broad learning system and its structural variations[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(4): 1191-1204. doi: 10.1109/TNNLS.2018.2866622 pmid: 30207965
[25]	孙黎霞, 彭嘉杰, 田屹昀, 等. 基于混合门控循环单元子层的多任务暂态稳定评估[J]. 电力建设, 2022, 43(2): 63-69. doi: 10.12204/j.issn.1000-7229.2022.02.008
	SUN Lixia, PENG Jiajie, TIAN Yiyun, et al. Multi-task transient stability assessment based on sub-layer of hybrid gated recurrent unit[J]. Electric Power Construction, 2022, 43(2): 63-69. doi: 10.12204/j.issn.1000-7229.2022.02.008
[26]	高发骏, 王怀远, 党然. 基于Transformer的暂态稳定评估模型的可解释性分析与模型更新研究[J]. 电力系统保护与控制, 2023, 51(17): 15-25.
	GAO Fajun, WANG Huaiyuan, DANG Ran. Interpretability analysis and model update research of a transient stability assessment model based on Transformer[J]. Power System Protection and Control, 2023, 51(17): 15-25.
[27]	WANG H M, LI Z S. An AdaBoost-based tree augmented naive Bayesian classifier for transient stability assessment of power systems[J]. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 2022, 236(3): 495-507. doi: 10.1177/1748006X211047308 URL
[28]	张哲, 李升, 王徐彬. 基于KM-RF算法的电力系统暂态稳定评估[J]. 电气自动化, 2021, 43(5): 72-74.
	ZHANG Zhe, LI Sheng, WANG Xubin. Power system transient stability assessment based on KM-RF algorithm[J]. Electrical Automation, 2021, 43(5): 72-74.
[29]	TIAN F, ZHOU X X, YU Z H, et al. A preventive transient stability control method based on support vector machine[J]. Electric Power Systems Research, 2019, 170: 286-293. doi: 10.1016/j.epsr.2019.01.030 URL
[30]	叶圣永, 王晓茹, 刘志刚, 等. 基于Stacking元学习策略的电力系统暂态稳定评估[J]. 电力系统保护与控制, 2011, 39(6): 12-16, 23.
	YE Shengyong, WANG Xiaoru, LIU Zhigang, et al. Power system transient stability assessment based on Stacking meta-learning strategy[J]. Power System Protection and Control, 2011, 39(6): 12-16, 23.