Redirigiendo al acceso original de articulo en 20 segundos...
Inicio  /  Energies  /  Vol: 12 Núm: 8 Par: April-2 (2019)  /  Artículo
ARTÍCULO
TITULO

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

Resumen

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.

 Artículos similares

       
 
Chao Liu, Chunhai Sun, Guangyuan Li, Wenjia Yang and Fang Wang    
The present study provides comprehensive analyses of a newly constructed passive energy-efficient building located in Harbin, China, which is a prime example of how to design a passive building that withstands the severe cold climate in northeast Asia. C... ver más
Revista: Buildings

 
Maoqing Duan, Qi Liu, Yu Zhang, Feiyan Yuan, Xianzhi Meng, Shilu Zhang and Jun Zhang    
The background values of pollutants are becoming increasingly prominent in evaluating water quality and management, and their load and output characteristics are of great significance to the study of changes in the background values. Thus, this paper stu... ver más
Revista: Water

 
Jing-Kun Dong and Mao Ye    
Overall, this paper provides a comprehensive approach for designing structures subject to rhythmic crowd loading. By considering the randomness of the load model and structural response, the design method provides a more realistic evaluation of the struc... ver más
Revista: Buildings

 
Alina Dereszewska and Stanislaw Cytawa    
Technologies used in municipal wastewater treatment plants (WWTPs) allow the recovery of energy and valuable elements (phosphorus, nitrogen, and organic carbon) for the soil. This article presents, in schematic form, the carbon, nitrogen, and phosphorus ... ver más
Revista: Water

 
Felipe Orellana, Peppe J. V. D?Aranno, Silvia Scifoni and Maria Marsella    
Monitoring structural stability in urban areas and infrastructure networks is emerging as one of the dominant socio-economic issues for population security. The problem is accentuated by the age of the infrastructure because of increasing risks due to ma... ver más
Revista: Infrastructures