CJEE

Chinese Journal of Electrical Engineering ›› 2019, Vol. 5 ›› Issue (4): 33-39.doi: 10.23919/CJEE.2019.000025

Previous Articles     Next Articles

扫码分享

A Missing Power Data Filling Method Based on Improved Random Forest Algorithm*

Wei Deng1, Yixiu Guo2, Jie Liu2, Yong Li2,*, Dingguo Liu3, Liang Zhu3   

  1. 1. State Grid Hunan Power Company Limited Research Institute, Changsha 410007, China;
    2. College of Electrical and Information Engineering, Hunan University, Changsha 410082, China;
    3. State Grid Hunan Electric Power Company Limited, Changsha 410004, China
  • Online:2019-12-25 Published:2020-03-12
  • Contact: * Email: yongli@hnu.edu.cn
  • About author:Wei Deng was born in Hunan, China, in 1983. He received the Ph.D. degree in 2012, from the College of Electrical and Information Engineering, Hunan University, Changsha, China. Since 2012, he has worked in the State Grid Hunan Electric Power Co., Ltd. He has been engaged in the research of voltage and reactive power control, distribution network loss, and distribution network electric power research institute. His current research interests include optimal operation of smart distribution networks, application of big data and artificial intelligence in power grids, and distribution IOT technology.
    Yixiu Guo was born in Fujian, China, in 1995. She received the B.Sc. degree in 2002, from the College of Electrical and Information Engineering, Hunan University, Changsha, China. She is currently a master student in College of Electrical and Information Engineering, Hunan University, Changsha, China. Her research interests include machine learning, smart grid and power system stability.
    Jie Liu was born in Hunan, China, in 1979. She received the B.Sc. degree in 2002, from the School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China. She received the M.S. degree in 2006, from the School of Computer Science and Technology, Huazhong University of Science & Technology, Wuhan, China. She is currently a Ph.D. student in College of Electrical and Information Engineering, Hunan University, Changsha, China. Her research interests include machine learning, modeling analysis and control of cyber physical power system, analysis and control of power quality.
    Yong Li (S’09-M’12-SM’14) was born in Henan, China, in 1982. He received the B.Sc. and Ph.D. degrees in 2004 and 2011, respectively, from the College of Electrical and Information Engineering, Hunan University, Changsha, China. Since 2009, he worked as a Research Associate at the Institute of Energy Systems, Energy Efficiency, and Energy Economics (ie3), TU Dortmund University, Dortmund, Germany, where he received the second Ph.D. degree in June 2012. After then, he was a Research Fellow with The University of Queensland, Brisbane, Australia. Since 2014, he is a Full Professor of electrical engineering with Hunan University. His current research interests include power system stability analysis and control, ac/dc energy conversion systems and equipment, analysis and control of power quality, and HVDC and FACTS technologies.
    Dingguo Liu was born in Hunan, China, on June 6,1979. He received the B.S. and M.S. degrees from the College of Electrical and Information Engineering, Hunan University, Changsha, China, in 2005 and 2008, respectively, where he has been working toward the doctoral degree in the College of Electrical and Information Engineering. His research interests include harmonics suppression, reactive power compensation, and smart grid.
    Liang Zhu was born in Hunan, China, on August, 1974. He received the B.S. and M.S. degrees from the College of Electrical and Information engineering, Hunan University, Changsha, China. His research interests include power production management, distribution automation and power supply technology.
  • Supported by:
    * Supported by the State Grid Power Company of Hunan Province Science and Technology Project (No.5216A517000U).

PDF

243

Abstract: Missing data filling is a key step in power big data preprocessing, which helps to improve the quality and the utilization of electric power data. Due to the limitations of the traditional methods of filling missing data, an improved random forest filling algorithm is proposed. As a result of the horizontal and vertical directions of the electric power data are based on the characteristics of time series. Therefore, the method of improved random forest filling missing data combines the methods of linear interpolation, matrix combination and matrix transposition to solve the problem of filling large amount of electric power missing data. The filling results show that the improved random forest filling algorithm is applicable to filling electric power data in various missing forms. What’s more, the accuracy of the filling results is high and the stability of the model is strong, which is beneficial in improving the quality of electric power data.

Key words: Big data cleaning, missing data filling, data preprocessing, random forest, data quality