https://github.com/kbodurri/NILM

Code for our MPS 2019 paper entitled "A Machine Learning Approach for NILM based on Odd Harmonic Current Vectors"
https://github.com/kbodurri/NILM

energy energy-disaggregation machine-learning nilm scientific-publications sklearn supervised-learning

Last synced: 3 months ago
JSON representation

Code for our MPS 2019 paper entitled "A Machine Learning Approach for NILM based on Odd Harmonic Current Vectors"

• Host: GitHub
• URL: https://github.com/kbodurri/NILM
• Owner: kbodurri
• Created: 2018-11-11T16:12:30.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-09-03T15:41:45.000Z (almost 5 years ago)
• Last Synced: 2024-01-29T16:55:25.658Z (5 months ago)
• Topics: energy, energy-disaggregation, machine-learning, nilm, scientific-publications, sklearn, supervised-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 3.03 MB
• Stars: 8
• Watchers: 3
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Lists

• awesome-stars - kbodurri/NILM - Code for our MPS 2019 paper entitled "A Machine Learning Approach for NILM based on Odd Harmonic Current Vectors" (Jupyter Notebook)

README

        
# NILM

## Info

In this repo, we provide the **code and** the **datasets used in the following publication**, in order to promote reproduction and further research.

## A Machine Learning Approach for NILM based on Odd Harmonic Current Vectors

#### Published in: 2019 8th International Conference on Modern Power Systems (MPS)

#### Authors: EP. Loukas, K. Bodurri, P. Evangelopoulos, AS. Bouhouras, N. Poulakis, GC. Christoforidis, I. Panapakidis, KCH. Chatzisavvas

### Abstract

This paper examines the application of machine learning techniques in NILM methodologies based on the first three odd harmonic order current vectors as the only attributes of the appliances. Proper formulation of the measured current waveform of appliances' combinations is also presented. We apply our methodology on performed measurements of typical Low Voltage residential installations considering harmonic order currents as the input features for both the training and disaggregation scheme. Our results support the hypothesis that the identification performance is enhanced when higher harmonic currents are included in the NILM methodology.

### The full paper can be found [here](https://ieeexplore.ieee.org/abstract/document/8759666).

#### DOI: `10.1109/MPS.2019.8759666`

---

### BibTeX

In case our work inspires you in any way:

```

@inproceedings{Loukas2019,

  doi = {10.1109/mps.2019.8759666},

  url = {https://doi.org/10.1109/mps.2019.8759666},

  year = {2019},

  month = may,

  publisher = {{IEEE}},

  author = {Eleftherios P. Loukas and Klajdi Bodurri and Panagiotis Evangelopoulos and Aggelos S. Bouhouras and Nikolay Poulakis and Giorgos C. Christoforidis and Ioannis Panapakidis and Konstantinos Ch. Chatzisavvas},

  title = {A Machine Learning Approach for {NILM} based on Odd Harmonic Current Vectors},

  booktitle = {2019 8th International Conference on Modern Power Systems ({MPS})}

}

```