Int J Performability Eng ›› 2021, Vol. 17 ›› Issue (1): 74-84.doi: 10.23940/ijpe.21.01.p7.7484

• Orginal Article • Previous Articles     Next Articles

Decomposition and Identification of Non-Intrusive Load Equipment Group

Jiali Yanga, Jiarui Chena, and Sheng Lia,b*   

  1. aSchool of Mathematics and Computer, Guangdong Ocean University, Zhanjiang, 524088, China
    bSouthern Marine Science and Engineering Guangdong Laboratory (Zhanjiang), Zhanjiang, 524088, China
  • Submitted on ; Revised on ; Accepted on
  • Contact: * Corresponding author. E-mail address: lish_ls@sina.com
  • Supported by:
    the Fund of Southern Marine Science and Engineering Guangdong Laboratory (Zhanjiang) (ZJW-2019-04) and the Natural Science Foundation of Guangdong Province (2018A030307062)

Abstract:

Non-Intrusive Load Monitoring technology is the most common method for power system decomposition recently. In order to solve the problem of low precision of current non-intrusive load decomposition, an improved sliding window bilateral accumulation and event detection algorithm is proposed in this paper. The random forest and deep neural network and support vector machine algorithm are used to decompose and identify the non-intrusive load equipment group. The results of the case analysis show that this algorithm is significantly better than the traditional non-intrusive load decomposition algorithm for non-intrusive load equipment group decomposition.

Key words: non-intrusive load decomposition, event detection, random forest, deep neural network, support vector machine