Neural NILM: deep neural networks applied to energy disaggregation
File(s)
Accepted version
Author(s)
Kelly, Jack
Knottenbelt, William J
Type
Conference Paper
Abstract
Energy disaggregation estimates appliance-by-appliance electricity consumption from a single meter that measures the whole home's electricity demand. Recently, deep neural networks have driven remarkable improvements in classification performance in neighbouring machine learning fields such as image classification and automatic speech recognition. In this paper, we adapt three deep neural network architectures to energy disaggregation: 1) a form of recurrent neural network called `long short-term memory' (LSTM); 2) denoising autoencoders; and 3) a network which regresses the start time, end time and average power demand of each appliance activation. We use seven metrics to test the performance of these algorithms on real aggregate power data from five appliances. Tests are performed against a house not seen during training and against houses seen during training. We find that all three neural nets achieve better F1 scores (averaged over all five appliances) than either combinatorial optimisation or factorial hidden Markov models and that our neural net algorithms generalise well to an unseen house.
Editor(s)
Culler, David
Agarwal, Yuvraj
Mangharam, Rahul
Date Issued
2015-11-01
Date Acceptance
2015-11-01
Citation
BuildSys '15: Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, 2015, pp.55-64
ISBN
978-1-4503-3981-0
Publisher
ACM
Start Page
55
End Page
64
Journal / Book Title
BuildSys '15: Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments
Copyright Statement
© 2015 ACM. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in BuildSys '15: Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, http://dx.doi.org/10.1145/10.1145/2821650.2821672
Identifier
https://doi.org/10.1145/2821650
Source
BuildSys 2015
Publication Status
Published
Start Date
2015-11-04
Finish Date
2015-11-05
Coverage Spatial
Seoul, South Korea