基于卷积神经网络综合模型和稳态特征量的电力系统暂态稳定评估
|
摘要
为了提高卷积神经网络(convolutional neural network,CNN)的分类性能,提出CNN综合模型,以及CNN与时域仿真相结合的暂态稳定评估解决思路。首先,构建若干个具有相同结构、不同参数的CNN模型进行训练和预测;然后根据一定的结果综合原则对若干个CNN模型的预测结果进行综合,得到"稳定"、"不稳定"和"不确定"3种分类预测结果;最后将结果不确定的样本送入时域仿真进行稳定评估。采用某省级电网算例进行了分类效果验证。结果表明,对于某故障形式,所提出的CNN综合模型,确定样本实现了100%的正确率,而结果不确定的样本占总样本的比例在6%以内,说明该模型具有良好的故障筛选性能。
A comprehensive convolutional neural network(CNN) model and transient stability assessment based on CNN combined with time-domain simulation were presented in the paper, to improve the performance of CNN classification. First,several CNN models with same structure and different parameters were built, trained and used to forecast power system stability; then the results were synthesized according to some certain principles of result synthesis and 3 kinds of classification prediction results were obtained: "stable","unstable" and "uncertain"; finally the "uncertain" samples were sent to time-domain simulation for stability assessment. A certain provincial power grid was analyzed to verify the effectiveness of the method. Analysis results show that with the presented method 100% accuracy rate was realized for"certain" samples and the proportion of samples with uncertain results to total samples was less than 6% for a certain contingency, which proved that the comprehensive CNN model has excellent contingency screening performance.
A comprehensive convolutional neural network(CNN) model and transient stability assessment based on CNN combined with time-domain simulation were presented in the paper, to improve the performance of CNN classification. First,several CNN models with same structure and different parameters were built, trained and used to forecast power system stability; then the results were synthesized according to some certain principles of result synthesis and 3 kinds of classification prediction results were obtained: "stable","unstable" and "uncertain"; finally the "uncertain" samples were sent to time-domain simulation for stability assessment. A certain provincial power grid was analyzed to verify the effectiveness of the method. Analysis results show that with the presented method 100% accuracy rate was realized for"certain" samples and the proportion of samples with uncertain results to total samples was less than 6% for a certain contingency, which proved that the comprehensive CNN model has excellent contingency screening performance.
引文
[1]Tada Y,Chiang H D.Design and implementation of online dynamic security assessment[J].IEEJ Transactions on Electrical and Electronic Engineering,2009,4(3):313-321.
[2]Tirado C,Romo S.Online security assessment in Mexican power systems[C]//The 45th Conference of CIGRE.Paris:CIGRE,2014:C2-118.
[3]严剑峰,于之虹,田芳,等.电力系统在线动态安全评估和预警系统[J].中国电机工程学报,2008,28(34):87-93.Yan Jianfeng,Yu Zhihong,Tian Fang,et al.Dynamic security assessment&early warning system of power system[J].Proceedings of the CSEE,2008,28(34):87-93(in Chinese).
[4]Neto C A S,Quadros M A,Santos M G,et a1.Brazilian system operator online security assessment system[C]//IEEE Power and Energy Society General Meeting.Minneapolis:IEEE,2010:1-7.
[5]Dudurych I M,Rogers A,Aherne R,et a1.Safety in numbers:online security analysis of power grids with high wind penetration[J].IEEE Power and Energy Magazine,2012,10(2):62-70.
[6]Geeganage J,Annakkage U D,Weekes T,et al.Application of energy-based power system features of dynamic security assessment[J].IEEE Transactions on Power Systems,2015,30(4):1957-1965.
[7]戴远航,陈磊,张玮灵,等.基于多支持向量机综合的电力系统暂态稳定评估[J].中国电机工程学报,2016,36(5):1173-1180.Dai Yuanhang1,Chen Lei,Zhang Weiling,et al.Power system transient stability assessment based on multi-support vector machines[J].Proceedings of the CSEE,2016,36(5):1173-1180(in Chinese).
[8]张玮灵,胡伟,闵勇,等.稳定域概念下考虑保守性的电力系统在线暂态稳定评估方法[J].电网技术,2016,40(4):992-998.Zhang Weiling,Hu Wei,Min Yong,et al.Conservative online transient stability assessment in power system based on concept of stability region[J].Power System Technology,2016,40(4):992-998(in Chinese).
[9]田芳,周孝信,于之虹.基于支持向量机综合分类模型和关键样本集的电力系统暂态稳定评估[J].电力系统保护与控制,2017,45(22):1-8.Tian Fang,Zhou Xiaoxin,Yu Zhihong.Power system transient stability assessment based on comprehensive SVM classification model and key sample set[J].Power System Protection and Control,2017,45(22):1-8(in Chinese).
[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]王康,孙宏斌,张伯明,等.基于二维组合属性决策树的暂态稳定评估[J].中国电机工程学报,2009,29(S):17-24.Wang Kang,Sun Hongbin,Zhang Boming,et al.Transient stability assessment based on 2D combined attribute decision tree[J].Proceedings of the CSEE,2009,29(S):17-24(in Chinese).
[12]Eltigani D M,Ramadan K,Zakaria E.Implementation of transient stability assessment using artificial neural networks[C]//International Conference on Computing,Electrical and Electronics Engineering.Khartoum:IEEE,2013:659-662.
[13]姚德全,贾宏杰,赵帅.基于复合神经网络的电力系统暂态稳定评估和裕度预测[J].电力系统自动化,2013,37(20):41-46.Yao Dequan,Jia Hongjie,Zhao Shuai.Power system transient stability assessment and stability margin prediction based on compound neural network[J].Automation of Electric Power Systems,2013,37(20):41-46(in Chinese).
[14]胡伟,郑乐,闵勇,等.基于深度学习的电力系统故障后暂态稳定评估研究[J].电网技术,2017,11(10):3140-3146.Hu Wei,Zheng Le,Min Yong,et al.Research on power system transient stability assessment based on deep learning of big data technique[J].Power System Technology,2017,11(10):3140-3146(in Chinese).
[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(in Chinese).
[16]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.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(in Chinese).
[17]Balasubramaniam K,Watson N.CNN based power system transient stability margin and voltage stability index prediction[C]//2013 IEEE Computational Intelligence Applications in Smart Grid(CIASG).Singapore:IEEE,2013:13-20.
[18]Tan Bendong,Yang Jun,Pan Xueli,et al.Representational learning approach for power system transient stability assessment based on convolutional neural network[C]//The 6th International Conference on Renewable Power Generation(RPG).Wuhan:IET,2017:1847-1850.
[19]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[20]Krizhevsky A,Sutskever I,Hinton G E.Image net classification with deep convolutional neural networks[C]//The 25th International Conference on Neural Information Prosessing systems.Lake Tahoe:Curran Assocites Inc.,2012:1097-1105.
[21]Parkhi O M,Vedaldi A,Zisserman A.Deep face recognition[C]//British Machine Vision Conference.Swansea:British Machine Vision Association,2015:41-42.
[22]Szegedy C,Liu W,Jia Y Q,et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015:1-9.
[23]李彦冬,郝宗波,雷航.卷积神经网络研究综述[J].计算机应用,2016,36(9):2508-2515,2565.Li Yandong,Hao Zongbo,Lei Hang.Survey of convolutional neural network[J].Journal of Computer Applications,2016,36(9):2508-2515,2565(in Chinese).
[24]Chang C C,Lin C J.LIBSVM:A library for support vector machines[J].ACM Transactions on Intelligent System Technology,2011,2(3):389-396.
[2]Tirado C,Romo S.Online security assessment in Mexican power systems[C]//The 45th Conference of CIGRE.Paris:CIGRE,2014:C2-118.
[3]严剑峰,于之虹,田芳,等.电力系统在线动态安全评估和预警系统[J].中国电机工程学报,2008,28(34):87-93.Yan Jianfeng,Yu Zhihong,Tian Fang,et al.Dynamic security assessment&early warning system of power system[J].Proceedings of the CSEE,2008,28(34):87-93(in Chinese).
[4]Neto C A S,Quadros M A,Santos M G,et a1.Brazilian system operator online security assessment system[C]//IEEE Power and Energy Society General Meeting.Minneapolis:IEEE,2010:1-7.
[5]Dudurych I M,Rogers A,Aherne R,et a1.Safety in numbers:online security analysis of power grids with high wind penetration[J].IEEE Power and Energy Magazine,2012,10(2):62-70.
[6]Geeganage J,Annakkage U D,Weekes T,et al.Application of energy-based power system features of dynamic security assessment[J].IEEE Transactions on Power Systems,2015,30(4):1957-1965.
[7]戴远航,陈磊,张玮灵,等.基于多支持向量机综合的电力系统暂态稳定评估[J].中国电机工程学报,2016,36(5):1173-1180.Dai Yuanhang1,Chen Lei,Zhang Weiling,et al.Power system transient stability assessment based on multi-support vector machines[J].Proceedings of the CSEE,2016,36(5):1173-1180(in Chinese).
[8]张玮灵,胡伟,闵勇,等.稳定域概念下考虑保守性的电力系统在线暂态稳定评估方法[J].电网技术,2016,40(4):992-998.Zhang Weiling,Hu Wei,Min Yong,et al.Conservative online transient stability assessment in power system based on concept of stability region[J].Power System Technology,2016,40(4):992-998(in Chinese).
[9]田芳,周孝信,于之虹.基于支持向量机综合分类模型和关键样本集的电力系统暂态稳定评估[J].电力系统保护与控制,2017,45(22):1-8.Tian Fang,Zhou Xiaoxin,Yu Zhihong.Power system transient stability assessment based on comprehensive SVM classification model and key sample set[J].Power System Protection and Control,2017,45(22):1-8(in Chinese).
[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]王康,孙宏斌,张伯明,等.基于二维组合属性决策树的暂态稳定评估[J].中国电机工程学报,2009,29(S):17-24.Wang Kang,Sun Hongbin,Zhang Boming,et al.Transient stability assessment based on 2D combined attribute decision tree[J].Proceedings of the CSEE,2009,29(S):17-24(in Chinese).
[12]Eltigani D M,Ramadan K,Zakaria E.Implementation of transient stability assessment using artificial neural networks[C]//International Conference on Computing,Electrical and Electronics Engineering.Khartoum:IEEE,2013:659-662.
[13]姚德全,贾宏杰,赵帅.基于复合神经网络的电力系统暂态稳定评估和裕度预测[J].电力系统自动化,2013,37(20):41-46.Yao Dequan,Jia Hongjie,Zhao Shuai.Power system transient stability assessment and stability margin prediction based on compound neural network[J].Automation of Electric Power Systems,2013,37(20):41-46(in Chinese).
[14]胡伟,郑乐,闵勇,等.基于深度学习的电力系统故障后暂态稳定评估研究[J].电网技术,2017,11(10):3140-3146.Hu Wei,Zheng Le,Min Yong,et al.Research on power system transient stability assessment based on deep learning of big data technique[J].Power System Technology,2017,11(10):3140-3146(in Chinese).
[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(in Chinese).
[16]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.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(in Chinese).
[17]Balasubramaniam K,Watson N.CNN based power system transient stability margin and voltage stability index prediction[C]//2013 IEEE Computational Intelligence Applications in Smart Grid(CIASG).Singapore:IEEE,2013:13-20.
[18]Tan Bendong,Yang Jun,Pan Xueli,et al.Representational learning approach for power system transient stability assessment based on convolutional neural network[C]//The 6th International Conference on Renewable Power Generation(RPG).Wuhan:IET,2017:1847-1850.
[19]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[20]Krizhevsky A,Sutskever I,Hinton G E.Image net classification with deep convolutional neural networks[C]//The 25th International Conference on Neural Information Prosessing systems.Lake Tahoe:Curran Assocites Inc.,2012:1097-1105.
[21]Parkhi O M,Vedaldi A,Zisserman A.Deep face recognition[C]//British Machine Vision Conference.Swansea:British Machine Vision Association,2015:41-42.
[22]Szegedy C,Liu W,Jia Y Q,et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015:1-9.
[23]李彦冬,郝宗波,雷航.卷积神经网络研究综述[J].计算机应用,2016,36(9):2508-2515,2565.Li Yandong,Hao Zongbo,Lei Hang.Survey of convolutional neural network[J].Journal of Computer Applications,2016,36(9):2508-2515,2565(in Chinese).
[24]Chang C C,Lin C J.LIBSVM:A library for support vector machines[J].ACM Transactions on Intelligent System Technology,2011,2(3):389-396.