钟小强;陈杰;蒋敏敏;郑晓晖;

• 1:国网福建省电力有限公司
• 2:国网信通亿力科技有限责任公司

摘要(Abstract)：

该文提出了一种基于深度学习技术的台区线损分析方法。首先,构建了基于门控循环单元的多层网络结构。然后,结合多个维度的台区电气特征参数作为输入进行训练,获得了相应的深度学习线损率计算模型。最后,基于若干小区的实测数据,验证了所提方法的有效性。实验结果表明,与已有文献中采用反向传播(back propagation,BP)神经网络预测方法相比,所提方法具有更优的线损预测精度和计算效率,可以分别获得10.7%和25.5%的性能提升。

关键词(KeyWords)： 深度学习网络;门控循环单元;预测模型;台区线损计算

Abstract:

Keywords:

基金项目(Foundation): 国家电网有限公司科技项目(SGITG-201719SQFJ-FF05)~~

作者(Author): 钟小强;陈杰;蒋敏敏;郑晓晖;

Email:

DOI: 10.13335/j.1000-3673.pst.2018.2930

参考文献(References)：

• [1] Jiang L M,Meng J X,Yin Z D,et al.Research on additional loss of line and transformer in low voltage distribution network under the disturbance of power quality[C]//International Conference on Advanced Mechatronic Systems(ICAMechS),Beijing,China:IEEE,2018:364-369.
• [2]张勤，马玮，付锦，等．中压配电网规划态线损计算方法[J]．电气技术，2018,19(2):42-45.Zhang Qin,Ma Wei,Fu Jin,et al.Line loss calculation for middle voltage distribution network planning[J].Electrical Engineering,2018,19(2):42-45(in Chinese).
• [3]陈得治，郭志忠．基于负荷获取和匹配潮流方法的配电网理论线损计算[J]．电网技术，2005,29(1):83-87.Chen Dezhi,Guo Zhizhong.Distribution system theoretical line loss calculation based on load obtaining and matching power flow[J].Power System Technology,2005,29(1):83-87(in Chinese).
• [4]黄训诚，何方国，齐欢．基于支持向量回归的配电网线损计算模型[J]．电力系统保护与控制，2008,36(18):51-54.Huang Xuncheng,He Fangguo,Qi Huan.Calculation of energy losses in distribution system based on a support vector regression model[J].Power System Protection and Control,2008,36(18):51-54(in Chinese).
• [5]彭宇文，刘克文．基于改进核心向量机的配电网理论线损计算方法[J]．中国电机工程学报，2011,31(34):120-126.Peng Yuwen,Liu Kewen.A distribution network theoretical line loss calculation method based on improved core vector machine[J].Proceedings of the CSEE,2011,31(34):120-126(in Chinese).
• [6]唐晓勇，江亚群，黄纯，等．改进ASMDE算法和RBFNN的配电网线损计算[J]．计算机工程与应用，2015,51(13):245-250.Tang Xiaoyong,Jiang Yaqun,Huang Chun,et al.Calculation of power loss in distribution systems based on improved ASMDE algorithm and RBFNN[J].Computer Engineering and Applications,2015,51(13):245-250(in Chinese).
• [7]邹云峰，梅飞，李悦，等．基于数据挖掘技术的台区合理线损预测模型研究[J]．电力需求侧管理，2015,17(4):25-29.Zou Yunfeng,Mei Fei,Li Yue,et al.Prediction model research of reasonable line loss for transformer district based on data mining technology[J].Power Demand Side Management,2015,17(4):25-29(in Chinese).
• [8]李亚，刘丽平，李柏青，等．基于改进K-Means聚类和BP神经网络的台区线损率计算方法[J]．中国电机工程学报，2016,36(17):4543-4551.Li Ya,Liu Liping,Li Boqing,et al.Calculation of line loss rate in transformer district based on improved K-Means clustering algorithm and BP neural network[J].Proceedings of the CSEE,2016,36(17):4543-4551(in Chinese).
• [9]史佳琪，张建华．基于深度学习的超短期光伏精细化预测模型研究[J]．电力建设，2017,38(6):28-35.Shi Jiaqi, Zhang Jianhua. Ultra short-term photovoltaic refined forecasting model based on deep learning[J]. Electric Power Construction,2017,38(6):28-35(in Chinese).
• [10] Zhang Q,Yang L T,Chen Z,et al.A survey on deep learning for big data[J].Information Fusion,2018,42(2018):146-157.
• [11] Deng L, Yu D. Deep learning:methods and applications[J].Foundations and Trends?in Signal Processing,2014,7(3):197-387.
• [12] Shi H,Xu M,Li R.Deep learning for household load forecasting-A novel pooling deep RNN[J].IEEE Transactions on Smart Grid,2018,9(5):5271-5280.
• [13] Graves A,Schmidhuber J.Frame wise phoneme classification with bidirectional LSTM and other neural network architectures[J].Neural Networks,2005,18(6):602-610.
• [14] Shen G,Tan Q,Zhang H,et al.Deep learning with gated recurrent unit networks for financial sequence predictions[J].Procedia computer science,2018,131(2018):895-903.