Neural Computing and Applications

, Volume 31, Issue 12, pp 8351–8358 | Cite as

A non-intrusive load decomposition algorithm for residents

  • Yuan-Jia Ma
  • Ming-Yue ZhaiEmail author
Machine Learning - Applications & Techniques in Cyber Intelligence


In view of the large amount of data involved in the existing decomposition algorithm, which leads to low decomposition efficiency and high hardware requirements, a non-intrusive load decomposition method based on hidden Markov model (HMM) and improved Viterbi algorithm is proposed. First, the steady-state current data of the load is monitored and collected, and then the monitoring value is quantified and the probability distribution of the quantized monitoring value is created. Finally, the state of the load is identified from the probability distribution. According to the correlation of a composite state transition composed of states of multiple loads, the corresponding HMM model is created. Based on the matrix sparsity, the compression algorithm is used to reduce the amount of data stored. By using the query algorithm and the improved Viterbi algorithm, the calculation of zero probability items can be avoided, and the decomposition efficiency can be greatly improved. Results from simulation and real data have been used to verify the performance of the proposed algorithm.


Hidden Markov model Matrix sparsity Non-intrusive load decomposition Viterbi algorithm 


Compliance with ethical standards

Conflict of interest

There are no conflicts of interest.


  1. 1.
    Yu Y, Luan W (2009) Smart grid and its implementations. Proc CSEE 29(34):1–8Google Scholar
  2. 2.
    Hongyu L, Shiming T (2011) Research on key technologies for smart residential community. Power Syst Technol 35(12):1–7Google Scholar
  3. 3.
    Beibei W, Yang L (2010) Demand side management planning and implementation mechanism for smart grid. Electric Power Autom Equip 30(20):1–24Google Scholar
  4. 4.
    Shiming T, Beibei W, Jing Z (2014) Key technologies for demand respond in smart grid. Proc CSEE 34(22):3576–3589Google Scholar
  5. 5.
    Hongchuan C, Bo L, Wenpeng L, Qiushuo L (2017) Modified Viterbi algorithm for nonintrusive load monitoring. Proc CSU-EPSA 29(2):84–88Google Scholar
  6. 6.
    Hart GW (1992) Nonintrusive appliance load monitoring. Proc IEEE 80(12):1870–1891CrossRefGoogle Scholar
  7. 7.
    Li R, Wang X (2016) Application of RPROP neural network in noninvasive load decomposition. Power Syst Protect Control 44(7):55–61Google Scholar
  8. 8.
    Yixin Y, Bo L, Wenpeng L (2013) Nonintrusive residential load monitoring and decomposition technology. South Power Syst Technol 7(4):1–5Google Scholar
  9. 9.
    Xiaodan Y, Yang L (2014) Research on household electricity response mode. Power Syst Protect Control 42(12):51–56Google Scholar
  10. 10.
    Peng L, Yinxin Y (2008) Non-intrusive method for on-line power load decomposition. In: China international conference on electricity distribution, CICED, Guangzhou, ChinaGoogle Scholar
  11. 11.
    Jianlou L, Huatao Y, Chaoyang Q (2015) Household user oriented method of power load decomposition. J Jilin Univ: Sci Ed 53(4):744–753Google Scholar
  12. 12.
    Christopher L, Kwangduk L, Robert C, Steven S, Steven L, Les N, Armstrong P (2003) Power signature analysis. IEEE Power Energy Mag 1(2):56–63CrossRefGoogle Scholar
  13. 13.
    Alan M, Douglas H, Qi H, Lieko E (2011) Circuit-level load monitoring for household energy management. IEEE Pervasive Comput 10(1):40–48CrossRefGoogle Scholar
  14. 14.
    Srinivasan D, Ng WS, Liew AC (2006) Neural-network based Signature Recognition for harmonic source identification. IEEE Trans Power Deliv 21(1):398–405CrossRefGoogle Scholar
  15. 15.
    Leeb SB, Shaw SR, Kirtley JL (1995) Transient event detection in spectral envelope estimates for nonintrusive load monitoring. IEEE Trans Power Deliv 10(3):1200–1210CrossRefGoogle Scholar
  16. 16.
    Cox R, Leeb SB, Shaw SR, Norford LK (2006) Transient event detection for nonintrusive load monitoring and demand side management using voltage distortion. In: Applied power electronics conference and exposition, Dallas, USAGoogle Scholar
  17. 17.
    Zeifman M (2012) Disaggregation of home energy display data using probabilistic approach. IEEE Trans Consum Electron 58(1):23–31MathSciNetCrossRefGoogle Scholar
  18. 18.
    Zia T, Bruckner D, Zaidi A (2011) A hidden Markov model based procedure for identifying household electric loads. In: IECON 2011-37th annual conference on the IEEE Industrial Electronics Society, Melbourne, AustraliaGoogle Scholar
  19. 19.
    Zeifman M, Roth K (2011) Viterbi algorithm with sparse transitions (VAST) for nonintrusive load monitoring. In: Computational intelligence applications in smart grid (CIASG) of 2011 IEEE symposium, Paris, FranceGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Computer and Information EngineeringGuangdong University of Petrochemical TechnologyMaomingChina

Personalised recommendations