A Deep Migration Learning Based Power Loss Rate Calculation Method for Distributed Power System With Wind and Solar Generation

被引：0

作者：

Lu Z. ^{[1
]}

Yang Y. ^{[1
]}

Li X. ^{[1
]}

Chen J. ^{[2
]}

Liu J. ^{[1
]}

机构：

[1] Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, Yanshan University, Qinhuangdao, 066004, Hebei Province

[2] State Grid Jibei Power Co., Ltd., Xicheng District, Beijing

来源：

Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2020年 / 40卷 / 13期

基金：

中国国家自然科学基金;

关键词：

Deep learning; Maximum mean difference; Migration learning; Network loss rate calculation;

D O I：

10.13334/j.0258-8013.pcsee.190602

中图分类号：

学科分类号：

摘要：

Aiming at the problem of network loss calculation of wind power photovoltaic power system, a calculation model of network loss rate based on transfer-deep boltzmann network-deep neural network (TDBN-DNN) was proposed. Firstly, the trained deep learning model was used as the source model, and the deep boltzmann network (DBN) feature extraction layer was frozen. Then, contribution coefficient of maximum mean discrepancy was defined and the sample data that has closer distribution with the data to be calculated is selected. The sample data was used to fine-tune the deep neural network (DNN), and the network loss calculation model based on TDBN-DNN was obtained. The TDBN-DNN based deep migration learning model was used to calculate the network loss rate. Finally, the actual power grid in a certain area of northern China was taken as an example. The simulation results show that the DBN-DNN deep learning calculation method has better nonlinear fitting ability than the traditional shallow back propagation (BP) neural network calculation method. In addition, after migration learning, the TDBN-DNN deep migration learning model has higher calculation accuracy and better timeliness than the DBN-DNN model and also has certain data fault tolerance. © 2020 Chin. Soc. for Elec. Eng.

引用

页码：4102 / 4110

页数：8

共 20 条

[1]

Zhang Yongjun, Shi Hui, Zhai Weifang, Et al., Line loss rate prediction based on combinatorial modeling by analytic hierarchy process-gray comprehensive relationship and multi grey models, Power System Technology, 35, 6, pp. 71-76, (2011)

[2]

Li Yalong, Liu Wenying, Tian Hao, Et al., Calculation method of combined loss reduction baseline based on matching vertical and horizontal errors, Proceedings of the CSEE, 36, 21, pp. 5831-6026, (2016)

[3]

Li Ziruo, Forecasting of theory line loss rate for municipality A network based on artificiall neural network, (2006)

[4]

Li Ya, Liu Liping, Li Baiqing, Et al., Calculation of line loss rate in transformer district based on improved K-Means clustering algorithm and BP neural network, Proceedings of the CSEE, 36, 17, pp. 4543-4551, (2016)

[5]

Schmidhuber J., Deep learning in neural networks:An overview[J], Neural Networks, 61, pp. 85-117, (2015)

[6]

Hori T, Hori C, Minami Y, Et al., Efficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition [J], IEEE Transactions on Audio,Speech,and Language Processing, 15, 4, pp. 1352-1365, (2007)

[7]

Gupta V, Gavrilovska A, Schwan K, Et al., GViM:GPU-accelerated virtual machines, Proceedings of the 3rd ACM Workshop on System-Level Virtualization for High Performance Computing, (2009)

[8]

Shi Jiaqi, Zhang Jianhua, Ultra short-term photovoltaic refined forecasting model based ondeep learning[J], Electric Power Construction, 38, 6, pp. 28-35, (2017)

[9]

Liang Zhi, Sun Guoqiang, Li Hucheng, Et al., Short-term load forecasting based on VMD and PSO optimized deep belief network, Power System Technology, 42, 2, pp. 598-606, (2018)

[10]

Zhu Qiaomu, Dang Jie, Chen Jinfu, Et al., A method for power system transient stability assessment based on deep belief networks, Proceedings of the CSEE, 38, 3, pp. 735-743, (2018)

← 1 2 →