Multi-State Household Appliance Identification Based on Convolutional Neural Networks and Clustering

Non-intrusive load monitoring, a convenient way to discern the energy consumption of a house, has been studied extensively. However, most research works have been carried out based on a hypothetical condition that each electric appliance has only one running state. This leads to low identification accuracy for multi-state electric appliances. To deal with this problem, a method for identifying the type and state of electric appliances based on a power time series is proposed in this paper. First, to identify the type of appliance, a convolutional neural network model was constructed that incorporated residual modules. Then, a k-means clustering algorithm was applied to calculate the number of states of the appliance. Finally, in order to identify the states of the appliances, different k-means clustering models were established for different multi-state electric appliances. Experimental results show effectiveness of the proposed method in identifying both the type and the running state of electric appliances.

[1]  Chuan Choong Yang,et al.  A systematic approach to ON-OFF event detection and clustering analysis of non-intrusive appliance load monitoring , 2015, Frontiers in Energy.

[2]  Maide Bucolo,et al.  A Real Time Feed Forward Control of Slug Flow in Microchannels † , 2019, Energies.

[3]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[4]  Youda Liu,et al.  Admittance-based load signature construction for non-intrusive appliance load monitoring , 2018 .

[5]  Haimonti Dutta,et al.  NILMTK: an open source toolkit for non-intrusive load monitoring , 2014, e-Energy.

[6]  Yoash Levron,et al.  MO-NILM: A multi-objective evolutionary algorithm for NILM classification , 2019, Energy and Buildings.

[7]  Arunava Chatterjee,et al.  Improved non-intrusive identification technique of electrical appliances for a smart residential system , 2019 .

[8]  Hui Liu,et al.  A hybrid model for appliance classification based on time series features , 2019, Energy and Buildings.

[9]  De Baets Leen,et al.  VI-Based Appliance Classification Using Aggregated Power Consumption Data , 2018, 2018 IEEE International Conference on Smart Computing (SMARTCOMP).

[10]  Chris Develder,et al.  Appliance classification using VI trajectories and convolutional neural networks , 2018 .

[11]  Hassani Messaoud,et al.  A new approach of electrical appliance identification in residential buildings , 2020 .

[12]  Fred Popowich,et al.  Nonintrusive load monitoring (NILM) performance evaluation , 2014, Energy Efficiency.

[13]  Jue Wang,et al.  Self-configuring event detection in electricity monitoring for human-building interaction , 2019, Energy and Buildings.

[14]  Sachin K. Jain,et al.  Pattern matrix and decision tree based technique for non-intrusive monitoring of home appliances , 2017, 2017 7th International Conference on Power Systems (ICPS).

[15]  Stefano Squartini,et al.  A Non-Intrusive Load Monitoring Algorithm Based on Non-Uniform Sampling of Power Data and Deep Neural Networks , 2019, Energies.

[16]  Shirantha Welikala,et al.  Non-intrusive load monitoring under residential solar power influx , 2017 .

[17]  Pascal A. Schirmer,et al.  Statistical and Electrical Features Evaluation for Electrical Appliances Energy Disaggregation , 2019, Sustainability.

[18]  Seung-Yeon Kim,et al.  Multiple power-based building energy management system for efficient management of building energy , 2018, Sustainable Cities and Society.

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

[20]  Bin Yang,et al.  A new approach for supervised power disaggregation by using a deep recurrent LSTM network , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).