Power Demand Data Analysis and Recovery for Management of Power Distribution Systems

被引：0

作者：

Hong, Haisheng ^{[1
]}

Xu, Chende ^{[1
]}

Liu, Zhe ^{[1
]}

Qin, Yang ^{[1
]}

Chen, Yuanyi ^{[2
]}

Wang, Yubin ^{[2
]}

机构：

[1] Guangdong Power Grid Co Ltd, Guangzhou Power Supply Bur, Guangzhou, Peoples R China

[2] Zhejiang Univ, Coll Elect Engn, Hangzhou, Peoples R China

来源：

MACHINE LEARNING, IMAGE PROCESSING, NETWORK SECURITY AND DATA SCIENCES, MIND 2022, PT I | 2022年 / 1762卷

关键词：

Data analytics; Missing data recovery; Convolutional network; Data processing; Power distribution systems;

D O I：

10.1007/978-3-031-24352-3_24

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Efficient anomaly detection and repair method is an important means to solve the problem of time series data quality. Current pair research on the quality of time series data mainly focuses on the lack of attribute value, data anomaly and data disorder, but the phenomenon of data loss is very common in the industry. This work presented a solution for power demand measurement analysis and recovery for the management of power distribution systems. The developed method and the algorithm are extensively evaluated and validated based on the simulation experiments for different test cases and the numerical results demonstrated that the proposed missing data recovery method can perform efficiently to recover the missing data for the improvement of data quality to enhance the operation of power distribution system operations. The solution can be further extended to different application domains to improve the data quality of advanced intelligent functionalities.

引用

页码：290 / 298

页数：9

共 10 条

[1] Using Residual Networks and Cosine Distance-Based K-NN Algorithm to Recognize On-Line Signatures [J].

Abosamra, Gibrael ;

Oqaibi, Hadi .

IEEE ACCESS, 2021, 9 :54962-54977

[2] Railway Track Circuit Fault Diagnosis Using Recurrent Neural Networks [J].

de Bruin, Tim ;

Verbert, Kim ;

Babuska, Robert .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 28 (03) :523-533

[3] Nonconvex Online Support Vector Machines [J].

Ertekin, Seyda ;

Bottou, Leon ;

Giles, C. Lee .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (02) :368-381

[4] Rolling element bearing fault diagnosis using convolutional neural network and vibration image [J].

Hoang, Duy-Tang ;

Kang, Hee-Jun .

COGNITIVE SYSTEMS RESEARCH, 2019, 53 :42-50

[5] A Breast Cancer Diagnosis Method Based on VIM Feature Selection and Hierarchical Clustering Random Forest Algorithm [J].

Huang, Zexian ;

Chen, Daqi .

IEEE ACCESS, 2022, 10 :3284-3293

[6] Dynamic Independent Component/Vector Analysis: Time-Variant Linear Mixtures Separable by Time-Invariant Beamformers [J].

Koldovsky, Zbynek ;

Kautsky, Vaclav ;

Tichavsky, Petr ;

Cmejla, Jaroslav ;

Malek, Jiri .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 :2158-2173

[7] An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data [J].

Lei, Yaguo ;

Jia, Feng ;

Lin, Jing ;

Xing, Saibo ;

Ding, Steven X. .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2016, 63 (05) :3137-3147

[8] Rolling bearing fault diagnosis using an optimization deep belief network [J].

Shao, Haidong ;

Jiang, Hongkai ;

Zhang, Xun ;

Niu, Maogui .

MEASUREMENT SCIENCE AND TECHNOLOGY, 2015, 26 (11)

[9] A sparse auto-encoder-based deep neural network approach for induction motor faults classification [J].

Sun, Wenjun ;

Shao, Siyu ;

Zhao, Rui ;

Yan, Ruqiang ;

Zhang, Xingwu ;

Chen, Xuefeng .

MEASUREMENT, 2016, 89 :171-178

[10] A roller bearing fault diagnosis method based on EMD energy entropy and ANN [J].

Yu, Yang ;

YuDejie ;

Cheng Junsheng .

JOURNAL OF SOUND AND VIBRATION, 2006, 294 (1-2) :269-277

← 1 →