基于深度置信网络的电力负荷识别

doi:10.19595/j.cnki.1000-6753.tces.181385

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1542 KB)
输出: BibTeX | EndNote (RIS)

摘要针对目前电力负荷自动识别中存在的人工选择特征困难的问题并且为了进一步提高识别精度,提出一种基于深度置信网络（DBN）的电力负荷识别方法。DBN是一种深度神经网络架构,在图像识别、语音识别以及电能质量扰动识别等领域有着成功的应用。DBN由多个受限玻耳兹曼机（RBMs）和一层后向传播神经网络组成。使用对比散度算法,首先对第一个RBM进行充分训练,获取初始特征;然后将这些初始特征值作为训练数据训练下一个RBM以获取高级特征,以此类推;最后,通过反向传播算法采用监督方式微调整个DBN。实验结果表明所提方法在8种电力负荷类型的识别上有很好的效果,平均识别率超过98%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	徐春华
	陈克绪
	马建
	刘佳翰
	吴建华

关键词 ：电力负荷, 深度学习, 受限玻耳兹曼机, 深度置信网络, 识别, 对比散度

Abstract：Aiming at the difficulty of manual feature selection in current automatic recognition of power loads (PLs) and to further heighten the identification accuracy, a deep belief network (DBN) based recognition method is proposed in this paper. DBN is a framework of deep neural network and has found a wide use in image recognition, speech recognition, power quality disturbances recognition, etc. A DBN consists of several restricted Boltzmann machines (RBMs) and one layer of back-propagation neural network. By using the contrastive divergence algorithm, the first RBM is fully trained with the training data to obtain initial features, then the next RBM is trained with the initial features as training data, etc. Finally, the whole DBN is fine-tuned in a manner of supervised training by back-propagation. Experimental results demonstrate that the proposed approach has a good performance on the recognition of eight types of PLs with an average accuracy over 98%.

Key words： Power loads deep learning restricted Boltzmann machines deep belief network recognition contrastive divergence

收稿日期: 2018-08-17 出版日期: 2019-10-12

PACS:

TM711

基金资助:国家自然科学基金项目（61662047）和国网江西省电力有限公司科技项目(521820180014)资助

通讯作者: 吴建华男,1956年生,教授,博士生导师,研究方向为数字图像处理、电能质量分析、模式识别。E-mail：jhwu@ncu.edu.cn

作者简介: 徐春华男,1989年生,硕士研究生,研究方向为电力负荷类型识别、深度学习。E-mail：chunhua_ly@163.com

引用本文:

徐春华, 陈克绪, 马建, 刘佳翰, 吴建华. 基于深度置信网络的电力负荷识别[J]. 电工技术学报, 2019, 34(19): 4135-4142. Xu Chunhua, Chen Kexu, Ma Jian, Liu Jiahan, Wu Jianhua. Recognition of Power Loads Based on Deep Belief Network. Transactions of China Electrotechnical Society, 2019, 34(19): 4135-4142.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.181385 https://dgjsxb.ces-transaction.com/CN/Y2019/V34/I19/4135

[1] 程祥, 李林芝, 吴浩, 等. 非侵入式负荷监测与分解研究综述[J]. 电网技术, 2016, 40(10): 3108-3117.
Cheng Xiang, Li Linzhi, Wu Hao, et al.A survey of the research on non-intrusive load monitoring and disaggregation[J]. Power System Technology, 2016, 40(10): 3108-3117.
[2] 董瑞, 黄民翔. 基于减法聚类的FCM算法在电力负荷分类中的应用[J]. 华东电力, 2014, 42(5): 917-921.
Dong Rui, Huang Minxiang.An improved FCM algorithm based on subtractive clustering for power load classification[J]. East China Electric Power, 2014, 42(5): 917-921.
[3] 黄麒元, 王致杰, 朱俊, 等. 基于模糊聚类的电力系统负荷分类分析[J]. 电力学报, 2015, 30(3): 200-205.
Huang Qiyuan, Wang Zhijie, Zhu Jun, et al.Analysis for the classification of power system load based on the fuzzy clustering[J]. Journal of Electric Power, 2015, 30(3): 200-205.
[4] 赵国生, 牛贞贞, 刘永光, 等. 基于自适应模糊C均值聚类算法的电力负荷特性分类[J]. 郑州大学学报: 工学版, 2015, 36(6): 56-60.
Zhao Guosheng, Niu Zhenzhen, Liu Yongguang, et al.Power load characteristic classification technology research based on an optimal fuzzy C-means clustering algorithm[J]. Journal of Zhengzhou University: Engineering Science Edition, 2015, 36(6): 56-60.
[5] 李龙, 魏靖, 黎灿兵, 等. 基于人工神经网络的负荷模型预测[J]. 电工技术学报, 2015, 30(8): 225-230.
Li Long, Wei Jing, Li Canbing, et al.Prediction of load model based on artificial neural network[J]. Transactions of China Electrotechnical Society, 2015, 30(8): 225-230.
[6] 陈亚, 李萍. 基于神经网络的短期电力负荷预测仿真研究[J]. 电气技术, 2017, 18(1): 26-29.
Chen Ya, Li Ping.Research on simulation of short-term power load forecasting based on neural network[J]. Electrical Engineering, 2017, 18(1): 26-29.
[7] 朱桂川, 周磊. 基于BP神经网络的用电器分类识别技术的研究[J]. 杭州电子科技大学学报: 自然科学版, 2016, 36(6): 5-9.
Zhu Guichuan, Zhou Lei.Research on classification and recognition technology for electrical appliance based on BP neural network[J]. Journal of Hangzhou Dianzi University: Natural Sciences, 2016, 36(6): 5-9.
[8] Du Liang, He Dawei, Yang Yi, et al.Self-organizing classification and identification of miscellaneous electric loads[C]//2012 IEEE Power and Energy Society General Meeting, San Diego, CA, USA, 2012: 1-6.
[9] Chang H H, Lin L S, Chen Nanming, et al.Particle-swarm-optimization-based nonintrusive demand monitoring and load identification in smart meters[J]. IEEE Transactions on Industry Applications, 2013, 49(5): 2229-2236.
[10] Guedes J D S, Ferreira D D, Barbosa B H G, et al. Non-intrusive appliance load identification based on higher-order statistics[J]. IEEE Latin America Transactions, 2016, 13(10): 3343-3349.
[11] Cox R, Leeb S B, Shaw S R, et al.Transient event detection for nonintrusive load monitoring and demand side management using voltage distortion[C]// Twenty-First Annual IEEE Applied Power Electronics Conference and Exposition, Dallas, TX, USA, 2006: 1751-1757.
[12] 高云, 杨洪耕. 基于暂态特征贴近度匹配的家用负荷识别[J]. 电力系统自动化, 2013, 37(9): 54-59.
Gao Yun, Yang Honggeng.Household load identification based on closeness matching of transient characteristics[J]. Automation of Electric Power Systems, 2013, 37(9): 54-59.
[13] 曲朝阳, 于华涛, 郭晓利. 基于开启瞬时负荷特征的家电负荷识别[J]. 电工技术学报, 2015, 30(增刊1): 358-364.
Qu Zhaoyang, Yu Huatao, Guo Xiaoli.The recognition of appliances instantaneous load[J]. Transactions of China Electrotechnical Society, 2015, 30(S1): 358-364.
[14] Du Liang, He Dawei, Harley R G, et al.Electric load classification by binary voltage-current trajectory mapping[J]. IEEE Transactions on Smart Grid, 2016, 7(1): 358-365.
[15] 马建, 陈克绪, 肖露欣, 等. 基于受限玻尔兹曼机的电能质量复合扰动识别[J]. 南昌大学学报: 理科版, 2016, 40(1): 30-34.
Ma Jian, Chen Kexu, Xiao Luxin, et al.Classification on mixed disturbances of power quality based on restricted Boltzmann machine[J]. Journal of Nanchang University: Natural Science, 2016, 40(1): 30-34.
[16] Wang Yanbin, You Zhuhong, Li Xiao, et al.Predicting protein-protein interactions from protein sequences by a stacked sparse autoencoder deep neural network[J]. Molecular Biosystems, 2017, 13(7): 1336-1344.
[17] Zhao Zhiqiang, Jiao Licheng, Zhao Jiaqi, et al.Discriminant deep belief network for high-resolution SAR image classification[J]. Pattern Recognition, 2017, 61: 686-701.
[18] 林颖, 郭志红, 陈玉峰. 基于卷积递归网络的电流互感器红外故障图像诊断[J]. 电力系统保护与控制, 2015, 43(16): 87-94.
Lin Ying, Guo Zhihong, Chen Yufeng.Convolutional-recursive network based current transformer infrared fault image diagnosis[J]. Power System Protection and Control, 2015, 43(16): 87-94.
[19] Siniscalchi S M, Yu Dong, Deng Li, et al.Exploiting deep neural networks for detection-based speech recognition[J]. Neurocomputing, 2013, 106(6): 148-157.
[20] 金亮, 王飞, 杨庆新, 等. 永磁同步电机性能分析的典型深度学习模型与训练方法[J]. 电工技术学报, 2018, 33(增刊1): 41-48.
Jin Liang, Wang Fei, Yang Qingxin, et al.Typical deep learning model and training method for performance analysis of permanent magnet synchronous motor[J]. Transactions of China Electrotechnical Society, 2018, 33(S1): 41-48.
[21] 石鑫, 朱永利, 萨初日拉, 等. 基于深度信念网络的电力变压器故障分类建模[J].电力系统保护与控制, 2016, 44(1): 71-76.
Shi Xin, Zhu Yongli, Sa Churila, et al.Power transformer fault classifying model based on deep belief network[J]. Power System Protection and Control, 2016, 44(1): 71-76.
[22] 王晓辉, 朱永利, 王艳, 等. 基于深度学习的电容器介损角在线辨识[J]. 电工技术学报, 2017, 32(15): 145-152.
Wang Xiaohui, Zhu Yongli, Wang Yan, et al.Online identification method of power capacitor dielectric loss angle based on deep learning[J]. Transactions of China Electrotechnical Society, 2017, 32(15): 145-152.
[23] Ma Jian, Zhang Jun, Xiao Luxin, et al.Classification of power quality disturbances via deep learning[J]. IETE Technical Review, 2017, 34(4): 408-415.
[24] 赵希梅, 金鸿雁. 基于Elman神经网络的永磁直线同步电机互补滑模控制[J]. 电工技术学报, 2018, 33(5): 973-979.
Zhao Ximei, Jin Hongyan.Complementary sliding mode control for permanent magnet linear synchronous motor based on Elman neural network[J]. Transactions of China Electrotechnical Society, 2018, 33(5): 973-979.
[25] 陈伟, 何家欢, 裴喜平. 基于相空间重构和卷积神经网络的电能质量扰动分类[J]. 电力系统保护与控制, 2018, 46(14): 87-93.
Chen Wei, He Jiahuan, Pei Xiping.Classification for power quality disturbance based on phase-space reconstruction and convolution neural network[J]. Power System Protection and Control, 2018, 46(14): 87-93.
[26] 刘辉海, 赵星宇, 赵洪山, 等. 基于深度自编码网络模型的风电机组齿轮箱故障检测[J]. 电工技术学报, 2017, 32(17): 156-163.
Liu Huihai, Zhao Xingyu, Zhao Hongshan, et al.Fault detection of wind turbine gearbox based on deep autoencoder network[J]. Transactions of China Electrotechnical Society, 2017, 32(17): 156-163.
[27] 贺辉. 电力负荷预测和负荷管理[M]. 北京: 中国电力出版社, 2013.
[28] Hinton G E.Training products of experts by minimizing contrastive divergence[J]. Neural Computation, 2002, 14(8): 1771-1800.