Non-Intrusive Load Monitoring by Voltage–Current Trajectory Enabled Transfer Learning

Non-intrusive load monitoring (NILM) is a technique for analyzing changes in the voltage and current flowing through the main feeder and determining the appliances in operation as well as their energy consumption. With the increase in amount and type of electric loads nowadays, it is of increasing significance to extract unique load signatures and build robust classification models for NILM. However, the electric loads of different households differ materially from one another, which makes it difficult to collect enough label data and train classification models with strong representation and generalization ability. In this paper, a voltage–current (<inline-formula> <tex-math notation="LaTeX">${V}$ </tex-math></inline-formula>–<inline-formula> <tex-math notation="LaTeX">${I}$ </tex-math></inline-formula>) trajectory enabled transfer learning method has been proposed for NILM. Different from the existing methods, a deep learning model pretrained on a visual recognition dataset is transferred to train the classifier for NILM, linking the knowledge between different domains. Moreover, the <inline-formula> <tex-math notation="LaTeX">${V}$ </tex-math></inline-formula>–<inline-formula> <tex-math notation="LaTeX">${I}$ </tex-math></inline-formula> trajectory is also transferred to visual representation by color encoding, which not only enhances the load signature’s uniqueness but also enables the NILM implementation of transfer learning. The experimental results on NILM datasets show that the proposed method significantly improves the accuracy and can be efficiently generalized compared with state-of-the-art methods.

[1]  Jing Liao,et al.  Non-Intrusive Load Disaggregation Using Graph Signal Processing , 2018, IEEE Transactions on Smart Grid.

[2]  Tom Dhaene,et al.  On the Bayesian optimization and robustness of event detection methods in NILM , 2017 .

[3]  A. Longjun Wang,et al.  Non-intrusive load monitoring algorithm based on features of V–I trajectory , 2018 .

[4]  Muhammad Ali Imran,et al.  Non-Intrusive Load Monitoring Approaches for Disaggregated Energy Sensing: A Survey , 2012, Sensors.

[5]  Francesco Piazza,et al.  Denoising autoencoders for Non-Intrusive Load Monitoring: Improvements and comparative evaluation , 2018 .

[6]  Álvaro Hernández,et al.  Event-Based Energy Disaggregation Algorithm for Activity Monitoring From a Single-Point Sensor , 2017, IEEE Transactions on Instrumentation and Measurement.

[7]  Jingkun Gao,et al.  A feasibility study of automated plug-load identification from high-frequency measurements , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[8]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[9]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[10]  Dawit Fekadu Teshome,et al.  Distinctive Load Feature Extraction Based on Fryze’s Time-Domain Power Theory , 2016, IEEE Power and Energy Technology Systems Journal.

[11]  Stefano Ermon,et al.  Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping , 2015, AAAI.

[12]  H. Y. Lam,et al.  A Novel Method to Construct Taxonomy Electrical Appliances Based on Load Signaturesof , 2007, IEEE Transactions on Consumer Electronics.

[13]  Sousso Kelouwani,et al.  Non-intrusive load monitoring through home energy management systems: A comprehensive review , 2017 .

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

[15]  Thomas G. Habetler,et al.  Electric Load Classification by Binary Voltage–Current Trajectory Mapping , 2016, IEEE Transactions on Smart Grid.

[16]  Fred Popowich,et al.  Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring , 2016, IEEE Transactions on Smart Grid.

[17]  Chi Zhou,et al.  SARAA: Semi-Supervised Learning for Automated Residential Appliance Annotation , 2017, IEEE Transactions on Smart Grid.

[18]  Bernardete Ribeiro,et al.  Home electrical signal disaggregation for non-intrusive load monitoring (NILM) systems , 2012, Neurocomputing.

[19]  Walid G. Morsi,et al.  Designing New Orthogonal High-Order Wavelets for Nonintrusive Load Monitoring , 2018, IEEE Transactions on Industrial Electronics.

[20]  H. Jacobsen,et al.  WHITED-A Worldwide Household and Industry Transient Energy Data Set , 2016 .

[21]  Hussain Shareef,et al.  Application of load monitoring in appliances’ energy management – A review , 2017 .

[22]  Dongdong Li,et al.  A nonintrusive load identification method for residential applications based on quadratic programming , 2016 .

[23]  Ji-Hyun Kim,et al.  Estimating classification error rate: Repeated cross-validation, repeated hold-out and bootstrap , 2009, Comput. Stat. Data Anal..

[24]  Qiang Yang,et al.  Transitive Transfer Learning , 2015, KDD.

[25]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[27]  Andrea Acquaviva,et al.  A Cloud-Based On-Line Disaggregation Algorithm for Home Appliance Loads , 2019, IEEE Transactions on Smart Grid.

[28]  Yu-Hsiu Lin,et al.  An Advanced Home Energy Management System Facilitated by Nonintrusive Load Monitoring With Automated Multiobjective Power Scheduling , 2015, IEEE Transactions on Smart Grid.

[29]  Angshul Majumdar,et al.  Deep Sparse Coding for Non–Intrusive Load Monitoring , 2018, IEEE Transactions on Smart Grid.

[30]  Fred Popowich,et al.  Nonintrusive load monitoring (NILM) performance evaluation , 2015 .

[31]  Jingkun Gao,et al.  PLAID: a public dataset of high-resoultion electrical appliance measurements for load identification research: demo abstract , 2014, BuildSys@SenSys.

[32]  Fahad Javed,et al.  An Empirical Investigation of V-I Trajectory Based Load Signatures for Non-Intrusive Load Monitoring , 2013, IEEE Transactions on Smart Grid.

[33]  Michael I. Jordan,et al.  Deep Transfer Learning with Joint Adaptation Networks , 2016, ICML.

[34]  Walid G. Morsi,et al.  Non-Intrusive Load Monitoring Using Semi-Supervised Machine Learning and Wavelet Design , 2017, IEEE Transactions on Smart Grid.

[35]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[36]  Chin-Feng Lai,et al.  Multi-appliance recognition system with hybrid SVM/GMM classifier in ubiquitous smart home , 2013, Inf. Sci..

[37]  Jyoti Maggu,et al.  Simultaneous Detection of Multiple Appliances From Smart-Meter Measurements via Multi-Label Consistent Deep Dictionary Learning and Deep Transform Learning , 2019, IEEE Transactions on Smart Grid.

[38]  Walid G. Morsi,et al.  Nonintrusive Load Monitoring Using Wavelet Design and Machine Learning , 2016, IEEE Transactions on Smart Grid.

[39]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[40]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Jian Liang,et al.  Load Signature Study—Part I: Basic Concept, Structure, and Methodology , 2010, IEEE Transactions on Power Delivery.

[42]  Chris Develder,et al.  Comprehensive feature selection for appliance classification in NILM , 2017 .

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

[44]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[45]  Qiang Yang,et al.  Distant Domain Transfer Learning , 2017, AAAI.