Interactive visualization for NILM in large buildings using non-negative matrix factorization
Palabra(s) clave:
Energy efficiency
Visual analytics
Building energy consumption
NMF
Fecha de publicación:
Editorial:
Elsevier
Versión del editor:
Citación:
Descripción física:
Resumen:
Non-intrusive load monitoring (NILM) techniques have recently attracted much interest, since they allow to obtain latent patterns from power demand data in buildings, revealing useful information to the expert user. Unsupervised methods are specially attractive, since they do not require labeled datasets. Particularly, non-negative matrix factorization (NMF) methods decompose a single power demand measurement over a certain time period into a set of components or “parts” that are sparse, non-negative and sum up the original measured quantity. Such components reveal hidden temporal patterns which may be difficult to interpret in complex systems such as large buildings. We suggest to integrate the knowledge of the user into the analysis in order to recognize the real events inside the electric network behind the learnt patterns. In this paper, we integrate the available domain knowledge of the user by means of a visual analytics web application in which an expert user can interact in a fluid way with the NMF outcome through visual approaches such as barcharts, heatmaps or calendars. Our approach is tested with real electric power demand data from a hospital complex, showing how the interpretation of the decomposition is improved by means of interactive data cube visualizations, in which the user can insightfully relate the NMF components to characteristic demand patterns of the hospital such as those derived from human activity, as well as to inefficient behaviors of the largest systems in the hospital
Non-intrusive load monitoring (NILM) techniques have recently attracted much interest, since they allow to obtain latent patterns from power demand data in buildings, revealing useful information to the expert user. Unsupervised methods are specially attractive, since they do not require labeled datasets. Particularly, non-negative matrix factorization (NMF) methods decompose a single power demand measurement over a certain time period into a set of components or “parts” that are sparse, non-negative and sum up the original measured quantity. Such components reveal hidden temporal patterns which may be difficult to interpret in complex systems such as large buildings. We suggest to integrate the knowledge of the user into the analysis in order to recognize the real events inside the electric network behind the learnt patterns. In this paper, we integrate the available domain knowledge of the user by means of a visual analytics web application in which an expert user can interact in a fluid way with the NMF outcome through visual approaches such as barcharts, heatmaps or calendars. Our approach is tested with real electric power demand data from a hospital complex, showing how the interpretation of the decomposition is improved by means of interactive data cube visualizations, in which the user can insightfully relate the NMF components to characteristic demand patterns of the hospital such as those derived from human activity, as well as to inefficient behaviors of the largest systems in the hospital
Descripción:
Artículo publicado en abierto mediante APC Elsevier Open Access
ISSN:
Patrocinado por:
Plan Nacional I+D+i (DPI2015-69891-C2-2-R)
Colecciones
Ficheros en el ítem
![Thumbnail](/dspace/bitstream/handle/10651/49010/1-s2.0-S0378778818304146-main.pdf.jpg?sequence=6&isAllowed=y)