Concatenate Convolutional Neural Networks for Non-Intrusive Load Monitoring across Complex Background

• Published in: Energies (Basel) Vol. 12; no. 8; p. 1572
• Main Authors: Wu, Qian, Wang, Fei
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 25.04.2019
• Subjects: Appliances; Artificial intelligence; Classification; Deep learning; Demand side management; Electricity; Energy consumption; energy disaggregation; Energy management; Fourier transforms; Households; Information processing; Load; Loads (forces); Neural networks; Noise; non-intrusive load monitoring; Power; Real time; Residential energy; Signal processing; source separation; Sparsity; Spectrograms; Spectrum analysis; Speech recognition; Voice recognition; Wireless communications; United Kingdom > UK; United States > US
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en12081572

Non-Intrusive Load Monitoring (NILM) provides a way to acquire detailed energy consumption and appliance operation status through a single sensor, which has been proven to save energy. Further, besides load disaggregation, advanced applications (e.g., demand response) need to recognize on/off events of appliances instantly. In order to shorten the time delay for users to acquire the event information, it is necessary to analyze extremely short period electrical signals. However, the features of those signals are easily submerged in complex background loads, especially in cross-user scenarios. Through experiments and observations, it can be found that the feature of background loads is almost stationary in a short time. On the basis of this result, this paper provides a novel model called the concatenate convolutional neural network to separate the feature of the target load from the load mixed with the background. For the cross-user test on the UK Domestic Appliance-Level Electricity dataset (UK-DALE), it turns out that the proposed model remarkably improves accuracy, robustness, and generalization of load recognition. In addition, it also provides significant improvements in energy disaggregation compared with the state-of-the-art.