Classification performance using gated recurrent unit recurrent neural network on energy disaggregation

Energy disaggregation or NILM is the best solution to reduce our consumption of electricity. Many algorithms in machine learning are applied to this field. However, the classification results from those algorithms are not as well as expected. In this paper, we propose a new approach to construct a classifier for energy disaggregation with deep learning field. We apply Gated Recurrent Unit (GRU) based on Recurrent Neural Network (RNN) to train our model using UK DALE dataset on this field. Besides, we compare our approach to original RNN on energy disaggregation. By applying GRU RRN, we achieve accuracy and F-measure for energy disaggregation with the ranges [89%–98%] and [81%–98%] respectively. Through these results of the experiment, we confirm that the deep learning approach is really effective for NILM.

[1]  Manish Marwah,et al.  Unsupervised Disaggregation of Low Frequency Power Measurements , 2011, SDM.

[2]  Jack Kelly,et al.  The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes , 2014, Scientific Data.

[3]  Hsueh-Hsien Chang,et al.  Load identification in nonintrusive load monitoring using steady-state and turn-on transient energy algorithms , 2010, The 2010 14th International Conference on Computer Supported Cooperative Work in Design.

[4]  J. Zico Kolter,et al.  REDD : A Public Data Set for Energy Disaggregation Research , 2011 .

[5]  Lucio Soibelman,et al.  Enhancing Electricity Audits in Residential Buildings with Nonintrusive Load Monitoring , 2010 .

[6]  Tatsuya Yamazaki,et al.  Appliance Recognition from Electric Current Signals for Information-Energy Integrated Network in Home Environments , 2009, ICOST.

[7]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[8]  Shwetak N. Patel,et al.  ElectriSense: single-point sensing using EMI for electrical event detection and classification in the home , 2010, UbiComp.

[9]  G. W. Hart,et al.  Nonintrusive appliance load monitoring , 1992, Proc. IEEE.

[10]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[11]  Andrew Y. Ng,et al.  Energy Disaggregation via Discriminative Sparse Coding , 2010, NIPS.

[12]  H. M. Kitching,et al.  Requirements for an advanced utility load monitoring system , 1989 .

[13]  Tommi S. Jaakkola,et al.  Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation , 2012, AISTATS.

[14]  P J Webros.  BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT , 1990 .

[15]  Bernardete Ribeiro,et al.  An Experimental Study on Electrical Signature Identification of Non-Intrusive Load Monitoring (NILM) Systems , 2011, ICANNGA.

[16]  Muhammad Ali Imran,et al.  Low-power appliance monitoring using Factorial Hidden Markov Models , 2013, 2013 IEEE Eighth International Conference on Intelligent Sensors, Sensor Networks and Information Processing.

[17]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[18]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.