Neural NILM: Deep Neural Networks Applied to Energy Disaggregation

TL;DR

This paper explores the application of deep neural networks, including LSTM, autoencoders, and regression models, to improve energy disaggregation accuracy from single-meter household electricity data, outperforming traditional methods.

Contribution

It adapts and evaluates three deep neural network architectures for energy disaggregation, demonstrating superior performance and generalization to unseen houses.

Findings

Neural networks achieve higher F1 scores than traditional models.

All three neural architectures generalize well to unseen houses.

Deep learning methods outperform existing energy disaggregation techniques.

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.