Cluster analysis of residential heat load profiles and the role of technical and household characteristics

Carmo, Carolina; Christensen, Toke Haunstrup

doi:10.1016/j.enbuild.2016.04.079

Cited by 84 publications

(40 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The low utilization of this factor in the determination of archetypes can be associated with its recent origin, according to the international literature. However, the household income is a factor that delivers important information, it brings a socio -economic component, it has to do with the users behavior house, which provides a more accurate characterization regarding the different types of users (Madeira & Haunstrup, 2016).…”

Section: Resultsmentioning

confidence: 99%

Residential archetypes in urban energy simulation models in Chile: Determining factors of residential energy consumption

Aguilera

Ossio

2017

rdlc

View full text Add to dashboard Cite

The national and international overview has shown that residential energy consumption is increasing. As a result, efforts have focused on reducing the initial demand for housing and its associated consumption. One of the most used tools for this purpose is bottom-up energy modelling, specifically on the archetypes branch. This method proposes that energy demand of a dwelling can estimated from the interaction of several parameters and factors. However, the method's main limitation, is the complexity of defining the variables and factors to be used. This article presents a review of specialized literature, concerned with, determining and characterizing residential archetypes. From this literature, It was possible to determine the most influential factors in energy consumption. The results showed 19 factors that were categorized into five groups; general, geometric, thermal, operational, and systems and equipment characteristics. The applicability of these factors to Chile was verified. This article, is intended a guide to generating representative archetypes and characterizing dwellings in an efficiente manner.Key words: energy efficiency, bottom-up modelling, archetypes, residential energy consumption, urban energy simulation. ResumenEl panorama nacional e internacional han demostrado que el consumo energético residencial está en alza. Por lo cual, los esfuerzos se han centrado en disminuir la demanda inicial de las viviendas y su consumo asociado. Para esto, una de las herramientas más utilizadas corresponde metodología bottom-up, específicamente del tipo arquetipos. Esta propone, que, a través de la interacción de diversos parámetros y factores, se puede obtener demanda energética de una vivienda, generando así arquetipos representativos del stock de viviendas simuladas, el cual se puede extrapolar a distintos niveles. Sin embargo, la principal limitante, corresponde a la complejidad de definir las variables y factores a utilizar. Este artículo presenta una revisión de literatura especializada, donde se compilaron las variables, más utilizadas en el consumo energético, para determinar y caracterizar arquetipos residenciales. Se obtuvieron 19 variables las que se categorizaron en cinco niveles; características generales, geométricas, térmicas y operacionales, y de equipamiento y sistemaas, a las que, se les verificó su aplicabilidad en Chile. A través de este artículo se pretende generar una guía que permita realizar una caracterización eficiente de las viviendas y su contextualización, de manera que los arquetipos que se puedan generar sean lo más representativos posibles.Palabras Claves: eficiencia energética, modelación bottom-up, arquetipos, consumo energético residencial, simulación energética urbana.

show abstract

Section: Resultsmentioning

confidence: 99%

Residential archetypes in urban energy simulation models in Chile: Determining factors of residential energy consumption

Aguilera

Ossio

2017

rdlc

View full text Add to dashboard Cite

show abstract

“…The research community has already recognized a strong relationship between the household characteristics and household energy consumption [12][13][14]. To make inferences from the smart meter data, many researchers utilized the univariate time-series data to train machine learning models and compute household characteristics.…”

Section: Related Workmentioning

confidence: 99%

“…Carolina et al [12] focused on the heating of Danish dwellings by analyzing the daily load profiles of energy consumption using k-means method. The obtained clusters have influenced the socio-economic characteristics.…”

Section: Related Workmentioning

confidence: 99%

Analyzing Load Profiles of Energy Consumption to Infer Household Characteristics Using Smart Meters

Fahim

Sillitti

2019

Energies

View full text Add to dashboard Cite

The increasing penetration of smart meters provides an excellent opportunity to monitor and analyze energy consumption in residential buildings. In this paper, we propose a framework to process the observed profiles of energy consumption to infer the household characteristics in residential buildings. Such characteristics can be used for improving resource allocation and for an efficient energy management that will ultimately contribute to reducing carbon dioxide (CO 2 ) emission. Our approach is based on automated extraction of features from univariate time-series data and development of a model through a variant of the decision trees technique (i.e., ensemble learning mechanism) random forest. We process and analyzed energy consumption data to answer four primitive questions. To evaluate the approach, we performed experiments on publicly available datasets. Our experiments show a precision of 82% and a recall of 81% in inferring household characteristics.

show abstract

“…Identification of typical building load profiles based on the collected massive energy usage data has been proved to be an effective way to understand building energy usage characteristics and help to develop cost effective load shifting and peak demand control strategies [4,5]. Cluster analysis, as a data mining technique to discover the natural grouping(s) of a set of patterns, points, or objects [6], has been used in a number of studies to identify typical building load profiles [4,5,7,8]. Jota et al [4], for instance, used an agglomerative hierarchical clustering algorithm with Euclidean distance (ED) to identify the typical building load profiles, which were further used to predict the accumulated energy usage at the end of the day and the daily peak demand.…”

Section: Introductionmentioning

confidence: 99%

A variation focused cluster analysis strategy to identify typical daily heating load profiles of higher education buildings

Yan

Nord

2017

Energy

View full text Add to dashboard Cite

show abstract

Cluster analysis of residential heat load profiles and the role of technical and household characteristics

Cited by 84 publications

References 20 publications

Residential archetypes in urban energy simulation models in Chile: Determining factors of residential energy consumption

Residential archetypes in urban energy simulation models in Chile: Determining factors of residential energy consumption

Analyzing Load Profiles of Energy Consumption to Infer Household Characteristics Using Smart Meters

A variation focused cluster analysis strategy to identify typical daily heating load profiles of higher education buildings

Contact Info

Product

Resources

About