Site logo
Sticky header logo
Site logo
  • About us
  • Research Lines
    • Big data analytics for energy efficiency in buildings
    • Energy Communities & Energy Positive Municipalities
    • Demand Response
    • Energy empowerment & user behaviour
    • Biodigesters
    • Energy positive buildings
  • Tech transfer
  • Team
  • Contact
  • Resource
    • Publications
    • Research projects
    • BEE News archive
  • |
  • EN
    • English
    • Spanish
PrevOperation and energy flexibility evaluation of direct load controlled buildings equipped with heat pumps23 September 2021NextePLANET – Accelerate the energy transition in your region22 April 2022
  • Scientific publication
22/04/2022
Image module

User behaviour models to forecast electricity consumption of residential customers based on smart metering data

 

ELSEVIER, Energy Reports,  vol. 8, pag. 3680-3691, November 2022

Authors: F.Lazzaria ; Jordi Ciprianoa ; Gerard Mora ;  E. Gabaldona ;  B. Grilloneb ;  D. Chemisanac ;  F. Solsonad

a International Center for Numerical Methods in Engineering, Building Energy and Environment Group, CIMNE-Lleida, Pere de Cabrera 16, Office 2G, 25001 Lleida, Spain
b CIMNE-UPC, Terrassa, Spain
c Applied Physics Section of the Environmental Science Department, University of Lleida, Jaume II 69, 25001 Lleida, Spain
c Department of Computer Science, University of Lleida, Jaume II 69, 25001 Lleida, Spain

VIEW PUBLICATION
Abstract:

This paper presents a novel approach to forecast day-ahead electricity consumption for residential households where highly irregular human behaviour plays a significant role. The methodology requires data from fiscal smart meters, which makes it applicable to real scenarios where personal data gathering is not feasible. These data are rarely complete; therefore, a robust combination of machine-learning techniques is used to handle missing data and outliers.

The novelty of this method relies on identifying and predicting user electricity consumption behaviour as a procedure to improve the forecasting of the overall electricity consumption of each individual customer. The methodology uses Gaussian mixture clustering to identify behaviour clusters and an eXtreme Gradient Boosting classification (XGBoost) model to predict the day-ahead behaviour pattern. This predicted user behaviour cluster is fed into an Artificial Neural Network (ANN) to enable an improved capturing of the highly unpredictable user conduct for the forecast of electricity consumption. A novel metric, namely the Euclidean Distance-based Accuracy (EDA), is finally proposed to enable a more thorough evaluation of time series classification algorithms. The whole development is tested over 500 residential users placed in a southeastern region of Spain.

The results showed that, when the novel approach was used, the MAPEd and NRMSEd were reduced by 7% and 9% respectively, increasing to a 20% and 17% respective reduction for the best cases according to EDA. This methodology sets the basis for massive user-centred analyses, very profitable to any electricity company.

  • Benedetto Grillone
  • Eloi Gabaldón
  • Florencia Lazzari
  • Gerard Mor
  • Jordi Cipriano
0 Likes

Related posts

Scientific publication Dynamic horizon selection methodology for model predictive control in buildings
03/10/2022in Scientific publication 0 Comments 0 Likes

Dynamic horizon selection methodology for model predictive control in buildings

Scientific publication Operation and energy flexibility evaluation of direct load controlled buildings equipped with heat pumps
23/09/2021in Scientific publication 0 Comments 0 Likes

Operation and energy flexibility evaluation of direct load controlled buildings equipped with heat pumps

Scientific publication Baseline Energy Use Modeling and Characterization in Tertiary Buildings Using an Interpretable Bayesian Linear Regression Methodology
06/09/2021in Scientific publication 0 Comments 0 Likes

Baseline Energy Use Modeling and Characterization in Tertiary Buildings Using an Interpretable Bayesian Linear Regression Methodology

Scientific publication A data-driven methodology for enhanced measurement and verification of energy efficiency savings in commercial buildings
02/09/2021in Scientific publication 0 Comments 0 Likes

A data-driven methodology for enhanced measurement and verification of energy efficiency savings in commercial buildings

Scientific publication Data-Driven Virtual Replication of Thermostatically Controlled Domestic Heating Systems
01/09/2021in Scientific publication 0 Comments 0 Likes

Data-Driven Virtual Replication of Thermostatically Controlled Domestic Heating Systems

Scientific publication Data-driven method for unsupervised electricity consumption characterisation at district level and beyond
03/08/2021in Scientific publication 0 Comments 0 Likes

Data-driven method for unsupervised electricity consumption characterisation at district level and beyond

Energy that matters BIGG Project Greek pilot: Business and use cases
01/07/2021in Energy that matters 0 Comments 0 Likes

BIGG Project Greek pilot: Business and use cases

Energy that matters Meet the expert: Jordi Cipriano
16/06/2021in Energy that matters 0 Comments 0 Likes

Meet the expert: Jordi Cipriano

Energy that matters BIGG Project Catalan pilot: Business and use cases
16/04/2021in Energy that matters 0 Comments 0 Likes

BIGG Project Catalan pilot: Business and use cases

Scientific publication A review of deterministic and data-driven methods to quantify energy efficiency savings and to predict retrofitting scenarios in buildings
13/07/2020in Scientific publication 0 Comments 0 Likes

A review of deterministic and data-driven methods to quantify energy efficiency savings and to predict retrofitting scenarios in buildings

Scientific publication Model Predictive Control applied to thermostatic controlled systems - CIMNE Building Energy and Environment Group
10/06/2020in Scientific publication 0 Comments 1 Likes

Model Predictive Control applied to thermostatic controlled systems

Scientific publication SBE19 SCILLA - Use of generalised additive models to assess energy efficiency savings in buildings using smart metering data
07/12/2019in Scientific publication 0 Comments 0 Likes

Use of generalised additive models to assess energy efficiency savings in buildings using smart metering data

Scientific publication EMPOWERING, a smart big data framework for sustainable electricity suppliers
15/11/2018in Scientific publication 0 Comments 0 Likes

EMPOWERING, a smart big data framework for sustainable electricity suppliers

Scientific publication Assessing the nearly zero-energy building gap in university campuses with a feature extraction methodology applied to a case study in Spain
08/02/2018in Scientific publication 0 Comments 1 Likes

Assessing the nearly zero-energy building gap in university campuses with a feature extraction methodology applied to a case study in Spain

Scientific publication Developing indicators to improve energy action plans in municipalities: An accounting framework based on the fund-flow model
30/07/2017in Scientific publication 0 Comments 0 Likes

Developing indicators to improve energy action plans in municipalities: An accounting framework based on the fund-flow model

Scientific publication Using matrix factorisation for the prediction of electrical quantities
30/06/2017in Scientific publication 0 Comments 0 Likes

Using matrix factorisation for the prediction of electrical quantities

Scientific publication Comparing time-series clustering approaches for individual electrical load patterns
15/06/2017in Scientific publication 0 Comments 0 Likes

Comparing time-series clustering approaches for individual electrical load patterns

Scientific publication Hidden Markov Models for indirect classification of occupant behaviour
14/07/2016in Scientific publication 0 Comments 0 Likes

Hidden Markov Models for indirect classification of occupant behaviour

Scientific publication Influencing factors in energy use of housing blocks: a new methodology, based on clustering and energy simulations, for decision making in energy refurbishment projects
04/07/2016in Scientific publication 0 Comments 0 Likes

Influencing factors in energy use of housing blocks: a new methodology, based on clustering and energy simulations, for decision making in energy refurbishment projects

Scientific publication Development of a dynamic model for natural ventilated photovoltaic components and of a data driven approach to validate and identify the model parameters
05/03/2016in Scientific publication 0 Comments 0 Likes

Development of a dynamic model for natural ventilated photovoltaic components and of a data driven approach to validate and identify the model parameters

Scientific publication Evaluation of a multi-stage guided search approach for the calibration of building energy simulation models
11/11/2014in Scientific publication 0 Comments 0 Likes

Evaluation of a multi-stage guided search approach for the calibration of building energy simulation models

Scientific publication Numerical analysis of the most appropriate heat transfer correlations for free ventilated double skin photovoltaic façades
10/04/2013in Scientific publication 0 Comments 0 Likes

Numerical analysis of the most appropriate heat transfer correlations for free ventilated double skin photovoltaic façades

Scientific publication Approaches to evaluate building energy performance from daily consumption data considering dynamic and solar gain effects
15/11/2012in Scientific publication 0 Comments 0 Likes

Approaches to evaluate building energy performance from daily consumption data considering dynamic and solar gain effects

Scientific publication Modelling the heat dynamics of a monitored Test Reference Environment for Building Integrated Photovoltaic systems using stochastic differential equations
01/04/2012in Scientific publication 0 Comments 0 Likes

Modelling the heat dynamics of a monitored Test Reference Environment for Building Integrated Photovoltaic systems using stochastic differential equations

Scientific publication An outdoor Test Reference Environment for double skin applications of Building Integrated PhotoVoltaic Systems
17/03/2012in Scientific publication 0 Comments 0 Likes

An outdoor Test Reference Environment for double skin applications of Building Integrated PhotoVoltaic Systems

Scientific publication Monitoring and modelling energy efficiency of municipal public buildings: case study in Catalonia region
04/12/2010in Scientific publication 0 Comments 0 Likes

Monitoring and modelling energy efficiency of municipal public buildings: case study in Catalonia region

Publications

Book (10) Energy that matters (9) Manual (4) Scientific publication (33) Uncategorised (1) White paper (3)

Research Lines

Biodigesters (1) Data analytics (12) Demand response (3) Energy empowerment (6) Positive living (7) Renewable energy (2) Spin offs (2)

Researchers

Benedetto Grillone (8) Biodigesters (17) Daniel Pérez (3) Eloi Gabaldón (6) Fabio Renda (1) Florencia Lazzari (4) Gerard Laguna (1) Gerard Mor (19) Gonzalo Gamboa (2) Jaime Martí-Herrero (25) Jordi Carbonell (6) Jordi Cipriano (25) Jose Santos Lopez (1) Stoyan Danov (14) Xavier Cipriano (4)

BEE Group is a  research department of CIMNE



or email us at
info.beegroup@cimne.upc.edu

© CIMNE BEE Group 2019
Terms of Use     Policy privacy