Skip to content

The super-state hidden Markov model disaggregator that uses a sparse Viterbi algorithm for decoding.

License

Notifications You must be signed in to change notification settings

sdanielzafar/SparseNILM

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

60 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Sparse NILM

Copyright (c) 2015 by Stephen Makonin Additions by S Daniel Zafar

The super-state hidden Markov model disaggregator that uses a sparse Viterbi algorithm for decoding. This project contains the source code that was used for the IEEE Transactions on Smart Grid journal paper.

If you usethe code in your research please cite this paper. Current citation details are:

  • Title: Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring (NILM)
  • Authors: Stephen Makonin, Fred Popowich, Ivan V. Bajic, Bob Gill, Lyn Bartram
  • Journal: IEEE Transactions on Smart Grid
  • Vol/No/Pages: vol. PP, no. 99, pp. 1-11
  • Accepted: October 2015
  • DOI: 10.1109/TSG.2015.2494592

NOTE: This code is a rewritten and modified version of the code used Makonin's my PhD thesis.

Updates by S Daniel Zafar (10/11/16):

Additional scripts for

  • disagg.NAV: Disaggregating new whole-house data and ouputing disaggregated results
  • disagg_viz.R & app_viz.R: Visualization (in R) of all disaggregated data as well as obs and est for each appliance (disagg_viz.R & app_viz.R)
  • ~.bat: batch files for Windows machines

Added a function to class Accuracy which outputs the Verification metrics to a specified .txt file in "\reports" folder ( accuracy.write() )

About

The super-state hidden Markov model disaggregator that uses a sparse Viterbi algorithm for decoding.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 78.7%
  • R 12.2%
  • Shell 5.3%
  • Batchfile 3.8%