Abstract：As China advances its dual carbon strategy, integrating new energy sources into power grids has grown significantly, making power system operations more complex and dynamic. For deep learning-based models used in transient stability assessment to be reliable, the training data and the data encountered in real-world applications must be independent and identically distributed. However, because power systems are time-varying and uncertain, models trained offline may not perform well in new operational scenarios. This paper proposes a transient stability assessment-discriminative domain adaptive (TSA-DDA) framework to address variations in operating scenarios. Firstly, an inter-domain dual distribution adaptation method was proposed. While aligning the marginal probability distributions of the source and target domains, this method also used Bayes' theorem to align the conditional probability distributions, achieving optimal domain adaptation. Secondly, both mean and variance differences between the source and target domains were comprehensively considered in the domain adaptation process. A new transfer regularization term was constructed to measure the inter-domain distribution differences, improving the model's domain adaptation capability. Finally, a discriminant Softmax function with adjustable parameters was developed to make intra-class sample features more compact while keeping inter-class sample features away by adjusting the parameters. This improvement can enhance the applicability of the assessment model to power grids. In the case studies, the TSA-DDA framework's ability to address variations in operational scenarios was first validated on the New England 10-machine 39-bus system. Subsequently, four alternative TSA-DDA frameworks, each with specific modules removed, were established to evaluate the effectiveness of individual components. The prediction accuracy of the target and source domain test sets was compared using a fine-tuning algorithm and the TSA-DDA. The TSA-DDA’s capacity for continual learning is confirmed. The TSA-DDA was then benchmarked against mainstream transferred learning approaches to verify its effectiveness in scenarios with limited new data. Finally, to assess the generalization capability of the proposed scheme, experiments were conducted on a larger and more complex provincial power grid in Southwest China. The experimental simulations utilized the PSD Power Tools and Dynamic Simulation Program to offer high-fidelity power system simulation data for model training and testing. The conclusions of this paper are given as follows. (1) The inter-domain dual distribution adaptation method comprehensively measures differences in marginal and conditional probability distributions between domains from both mean and variance perspectives. It constantly forces the feature extractor to narrow these differences, ensuring effective feature alignment across domains and enhancing the model’s adaptability. (2) The discriminant Softmax function improves the model’s learning of discriminative features by compacting intra-class features and separating inter-class features, which enhances the performance of the domain adaptation framework in transient stability assessment tasks. (3) Using voltage trajectory clusters with clustering and convergence properties as model inputs, the proposed framework ensures effective transferability across systems with varying structures and scales.
[1] 顾雪平, 刘彤, 李少岩, 等. 基于改进双延迟深度确定性策略梯度算法的电网有功安全校正控制[J]. 电工技术学报, 2023, 38(8): 2162-2177. Gu Xueping, Liu Tong, Li Shaoyan, et al.Active power correction control of power grid based on improved twin delayed deep deterministic policy gradient algorithm[J]. Transactions of China Electro- technical Society, 2023, 38(8): 2162-2177. [2] 杨金洲, 李业成, 熊鸿韬, 等. 基于阻抗的新能源接入的受端电网暂态电压失稳高风险故障快速筛选方法[J]. 电工技术学报, 2024, 39(21): 6746-6758. Yang Jinzhou, Li Yecheng, Xiong Hongtao, et al.A fast screening method for the high-risk faults with transient voltage instability in receiving-end power grids interconnected with new energy based on impedance[J]. Journal of Electrical Engineering Technology, 2024, 39(21): 6746-6758. [3] 钱倍奇, 陈谦, 张政伟, 等. 基于异构数据特征级融合的多任务暂态稳定评估[J]. 电力系统自动化, 2023, 47(9): 118-128. Qian Beiqi, Chen Qian, Zhang Zhengwei, et al.Multi- task transient stability assessment based on feature- level fusion of heterogeneous data[J]. Automation of Electric Power Systems, 2023, 47(9): 118-128. [4] 褚旭, 鲍泽宏, 许立强, 等. 基于时序卷积残差网络的主动配电系统线路短路故障诊断方案[J]. 电工技术学报, 2023, 38(8): 2178-2190. Chu Xu, Bao Zehong, Xu Liqiang, et al.Fault line diagnosis scheme of active distribution system based on time-sequence convolution residual network[J]. Transactions of China Electrotechnical Society, 2023, 38(8): 2178-2190. [5] Zadkhast P, Jatskevich J, Vaahedi E.A multi- decomposition approach for accelerated time-domain simulation of transient stability problems[J]. IEEE Transactions on Power Systems, 2015, 30(5): 2301-2311. [6] Vu T L, Turitsyn K.Lyapunov functions family approach to transient stability assessment[J]. IEEE Transactions on Power Systems, 2016, 31(2): 1269-1277. [7] 李宝琴, 吴俊勇, 邵美阳, 等. 基于集成深度置信网络的精细化电力系统暂态稳定评估[J]. 电力系统自动化, 2020, 44(6): 17-26. Li Baoqin, Wu Junyong, Shao Meiyang, et al.Refined transient stability evaluation for power system based on ensemble deep belief network[J]. Automation of Electric Power Systems, 2020, 44(6): 17-26. [8] 杨景刚, 赵科, 腾云, 等. 基于奇异谱分析与决策树的GIS振动缺陷检测方法研究[J]. 高压电器, 2024, 60(6): 33-42. Yang Jinggang, Zhao Ke, Teng Yun, et al.Research on vibration defect detection method of GIS based on singular spectrum analysis and decision tree[J]. High Voltage Apparatus, 2024, 60(6): 33-42. [9] 魏银图, 张旸, 温步瀛, 等. 基于支持向量机的模块化多电平换流器子模块开路故障诊断方法[J]. 电气技术, 2023, 24(10): 1-7. Wei Yintu, Zhang Yang, Wen Buying, et al.Open circuit fault diagnosis method for modular multilevel converter submodule based on support vector machine[J]. Electrical Engineering, 2023, 24(10): 1-7. [10] Kamwa I, Samantaray S R, Joos G.Catastrophe predictors from ensemble decision-tree learning of wide-area severity indices[J]. IEEE Transactions on Smart Grid, 2010, 1(2): 144-158. [11] 叶圣永, 王晓茹, 刘志刚, 等. 基于受扰严重机组特征及机器学习方法的电力系统暂态稳定评估[J]. 中国电机工程学报, 2011, 31(1): 46-51. Ye Shengyong, Wang Xiaoru, Liu Zhigang, et al.Power system transient stability assessment based on severely disturbed generator attributes and machine learning method[J]. Proceedings of the CSEE, 2011, 31(1): 46-51. [12] 房佳姝, 刘崇茹, 苏晨博, 等. 基于自注意力Transformer编码器的多阶段电力系统暂态稳定评估方法[J]. 中国电机工程学报, 2023, 43(15): 5745-5758. Fang Jiashu, Liu Chongru, Su Chenbo, et al.Multi- stage power system transient stability evaluation method based on self-attention Transformer encoder[J]. Proceedings of the CSEE, 2023, 43(15): 5745-5758. [13] 朱乔木, 陈金富, 李弘毅, 等. 基于堆叠自动编码器的电力系统暂态稳定评估[J]. 中国电机工程学报, 2018, 38(10): 2937-2946, 3144. Zhu Qiaomu, Chen Jinfu, Li Hongyi, et al.Transient stability assessment based on stacked autoencoder[J]. Proceedings of the CSEE, 2018, 38(10): 2937-2946, 3144. [14] 赵恺, 石立宝. 基于改进一维卷积神经网络的电力系统暂态稳定评估[J]. 电网技术, 2021, 45(8): 2945-2957. Zhao Kai, Shi Libao.Transient stability assessment of power system based on improved one-dimensional convolutional neural network[J]. Power System Technology, 2021, 45(8): 2945-2957. [15] 朱乔木, 党杰, 陈金富, 等. 基于深度置信网络的电力系统暂态稳定评估方法[J]. 中国电机工程学报, 2018, 38(3): 735-743. Zhu Qiaomu, Dang Jie, Chen Jinfu, et al.A method for power system transient stability assessment based on deep belief networks[J]. Proceedings of the CSEE, 2018, 38(3): 735-743. [16] Yu J J Q, Hill D J, Lam A Y S, et al. Intelligent time-adaptive transient stability assessment system[J]. IEEE Transactions on Power Systems, 2018, 33(1): 1049-1058. [17] 张若愚, 吴俊勇, 李宝琴, 等. 基于迁移学习的电力系统暂态稳定自适应预测[J]. 电网技术, 2020, 44(6): 2196-2205. Zhang Ruoyu, Wu Junyong, Li Baoqin, et al.Self- adaptive power system transient stability prediction based on transfer learning[J]. Power System Tech- nology, 2020, 44(6): 2196-2205. [18] 贺兴, 潘美琪, 艾芊. 小样本学习技术在新型电力系统中的应用与挑战[J]. 电力系统自动化, 2024, 48(6): 74-82. He Xing, Pan Meiqi, Ai Qian.Applications and challenges of few-shot learning technologies in new power system[J]. Automation of Electric Power Systems, 2024, 48(6): 74-82. [19] 金亮, 闫银刚, 杨庆新, 等. 小样本条件下永磁同步电机深度迁移学习性能预测方法[J]. 电工技术学报, 2023, 38(18): 4921-4931. Jin Liang, Yan Yingang, Yang Qingxin, et al.Predi- ction method of deep transfer learning performance of permanent magnet synchronous motor under the con- dition of few-shot[J]. Transactions of China Electro- technical Society, 2023, 38(18): 4921-4931. [20] Pan S J, Yang Q.A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engin- eering, 2010, 22(1): 1345-1359. [21] Wen Long, Gao Liang, Li Xinyu.A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 49(1): 136-144. [22] 申锦鹏, 杨军, 李蕊, 等. 基于改进域对抗迁移学习的电力系统暂态稳定自适应评估[J]. 电力系统自动化, 2022, 46(23): 67-75. Shen Jinpeng, Yang Jun, Li Rui, et al.Self-adaptive transient stability assessment of power system based on improved domain adversarial transfer learning[J]. Automation of Electric Power Systems, 2022, 46(23): 67-75. [23] Ren Chao, Xu Yan, Dai Bijian, et al.An integrated transfer learning method for power system dynamic security assessment of unlearned faults with missing data[J]. IEEE Transactions on Power Systems, 2021, 36(5): 4856-4859. [24] 任佳星, 孙英云, 秦继朔, 等. 基于改进域对抗网络的新能源基地风光时序功率曲线生成方法[J]. 电网技术, 2024, 48(8): 3409-3417. Ren Jiaxing, Sun Yingyun, Qin Jishuo, et al.Method for generating wind and solar temporal power curves in new energy bases based on improved domain adversarial networks[J]. Grid Technology, 2024, 48(8): 3409-3417. [25] 李延珍, 王海鑫, 杨子豪, 等. 基于非侵入式负荷分解的家庭负荷两阶段超短期负荷预测模型[J]. 电工技术学报, 2024, 39(11): 3379-3391. Li Yanzhen, Wang Haixin, Yang Zihao, et al.Two- stage ultra-short-term load forecasting model of household appliances based on non-intrusive load disaggregation[J]. Transactions of China Electro- technical Society, 2024, 39(11): 3379-3391. [26] Long Mingsheng, Wang Jianmin, Ding Guiguang, et al.Transfer feature learning with joint distribution adaptation[C]//2013 IEEE International Conference on Computer Vision, Sydney, NSW, Australia, 2013: 2200-2207. [27] 杨柏, 关焕新, 王森, 等. 基于深层卷积神经网络电动飞机主驱动电机故障诊断方法[J]. 微电机, 2020, 53(3): 49-54. Yang Bo, Guan Huanxin, Wang Sen, et al.Fault diagnosis method for main drive motor of electric aircraft based on deep convolutional neural net- work[J]. Micromotors, 2020, 53(3): 49-54. [28] Wang Feng, Cheng Jian, Liu Weiyang, et al.Additive margin softmax for face verification[J]. IEEE Signal Processing Letters, 2018, 25(7): 926-930. [29] 武宇翔, 韩肖清, 牛哲文, 等. 基于变权重随机森林的暂态稳定评估方法及其可解释性分析[J]. 电力系统自动化, 2023, 47(14): 93-104. Wu Yuxiang, Han Xiaoqing, Niu Zhewen, et al.Transient stability assessment method based on variable weight random forest and its interpretability analysis[J]. Automation of Electric Power Systems, 2023, 47(14): 93-104. [30] 冀鲁豫, 吴俊勇, 周艳真, 等. 基于WAMS受扰电压轨迹簇特征的电力系统暂态稳定性预测[J]. 高电压技术, 2015, 41(3): 807-814. Ji Luyu, Wu Junyong, Zhou Yanzhen, et al.Transient stability prediction of power system based on WAMS characteristic of perturbed voltage trajectory clusters[J]. High Voltage Engineering, 2015, 41(3): 807-814. [31] 尹杰, 刘博, 孙国兵, 等. 基于迁移学习和降噪自编码器-长短时间记忆的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(1): 289-302. Yin Jie, Liu Bo, Sun Guobing, et al.Transfer learning denoising autoencoder-long short term memory for remaining useful life prediction of Li-ion batteries[J]. Transactions of China Electrotechnical Society, 2024, 39(1): 289-302.
2025, Vol. 40 
