Load forecasting of supermarket refrigeration

Lisa Buth Rasmussen, Peder Bacher, Henrik Madsen, Henrik Aalborg Nielsen, Christian Heerup, Torben Green

Research output: Contribution to journalJournal articleResearchpeer-review

186 Downloads (Pure)

Abstract

This paper presents a novel study of models for forecasting the electrical load for supermarket refrigeration. The data used for building the models consists of load measurements, local climate measurements and weather forecasts. The load measurements are from a supermarket located in a village in Denmark. Every hour the hourly electrical load for refrigeration is forecasted for the following 42 h. The forecast models are adaptive linear time series models. The model has two regimes; one for opening hours and one for closing hours, this is modeled by a regime switching model and two different methods for predicting the regimes are tested. The dynamic relation between the weather and the load is modeled by simple transfer functions and the non-linearities are described using spline functions. The results are thoroughly evaluated and it is shown that the spline functions are suitable for handling the non-linear relations and that after applying an auto-regressive noise model the one-step ahead residuals do not contain further significant information.
Original languageEnglish
JournalApplied Energy
Volume163
Issue numberFebruar 2016
Pages (from-to)32-40
ISSN0306-2619
DOIs
Publication statusPublished - 2016

Keywords

  • Refrigeration
  • Load forecasting
  • Numerical weather predictions
  • Adaptive models
  • Base splines
  • Time series analysis

Cite this

Rasmussen, L. B., Bacher, P., Madsen, H., Nielsen, H. A., Heerup, C., & Green, T. (2016). Load forecasting of supermarket refrigeration. Applied Energy, 163(Februar 2016), 32-40. https://doi.org/10.1016/j.apenergy.2015.10.046
Rasmussen, Lisa Buth ; Bacher, Peder ; Madsen, Henrik ; Nielsen, Henrik Aalborg ; Heerup, Christian ; Green, Torben. / Load forecasting of supermarket refrigeration. In: Applied Energy. 2016 ; Vol. 163, No. Februar 2016. pp. 32-40.
@article{490668c26eb348098d1d8d9b9df1d869,
title = "Load forecasting of supermarket refrigeration",
abstract = "This paper presents a novel study of models for forecasting the electrical load for supermarket refrigeration. The data used for building the models consists of load measurements, local climate measurements and weather forecasts. The load measurements are from a supermarket located in a village in Denmark. Every hour the hourly electrical load for refrigeration is forecasted for the following 42 h. The forecast models are adaptive linear time series models. The model has two regimes; one for opening hours and one for closing hours, this is modeled by a regime switching model and two different methods for predicting the regimes are tested. The dynamic relation between the weather and the load is modeled by simple transfer functions and the non-linearities are described using spline functions. The results are thoroughly evaluated and it is shown that the spline functions are suitable for handling the non-linear relations and that after applying an auto-regressive noise model the one-step ahead residuals do not contain further significant information.",
keywords = "Refrigeration, Load forecasting, Numerical weather predictions, Adaptive models, Base splines, Time series analysis",
author = "Rasmussen, {Lisa Buth} and Peder Bacher and Henrik Madsen and Nielsen, {Henrik Aalborg} and Christian Heerup and Torben Green",
year = "2016",
doi = "10.1016/j.apenergy.2015.10.046",
language = "English",
volume = "163",
pages = "32--40",
journal = "Applied Energy",
issn = "0306-2619",
publisher = "Pergamon Press",
number = "Februar 2016",

}

Rasmussen, LB, Bacher, P, Madsen, H, Nielsen, HA, Heerup, C & Green, T 2016, 'Load forecasting of supermarket refrigeration', Applied Energy, vol. 163, no. Februar 2016, pp. 32-40. https://doi.org/10.1016/j.apenergy.2015.10.046

Load forecasting of supermarket refrigeration. / Rasmussen, Lisa Buth; Bacher, Peder; Madsen, Henrik; Nielsen, Henrik Aalborg; Heerup, Christian; Green, Torben.

In: Applied Energy, Vol. 163, No. Februar 2016, 2016, p. 32-40.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Load forecasting of supermarket refrigeration

AU - Rasmussen, Lisa Buth

AU - Bacher, Peder

AU - Madsen, Henrik

AU - Nielsen, Henrik Aalborg

AU - Heerup, Christian

AU - Green, Torben

PY - 2016

Y1 - 2016

N2 - This paper presents a novel study of models for forecasting the electrical load for supermarket refrigeration. The data used for building the models consists of load measurements, local climate measurements and weather forecasts. The load measurements are from a supermarket located in a village in Denmark. Every hour the hourly electrical load for refrigeration is forecasted for the following 42 h. The forecast models are adaptive linear time series models. The model has two regimes; one for opening hours and one for closing hours, this is modeled by a regime switching model and two different methods for predicting the regimes are tested. The dynamic relation between the weather and the load is modeled by simple transfer functions and the non-linearities are described using spline functions. The results are thoroughly evaluated and it is shown that the spline functions are suitable for handling the non-linear relations and that after applying an auto-regressive noise model the one-step ahead residuals do not contain further significant information.

AB - This paper presents a novel study of models for forecasting the electrical load for supermarket refrigeration. The data used for building the models consists of load measurements, local climate measurements and weather forecasts. The load measurements are from a supermarket located in a village in Denmark. Every hour the hourly electrical load for refrigeration is forecasted for the following 42 h. The forecast models are adaptive linear time series models. The model has two regimes; one for opening hours and one for closing hours, this is modeled by a regime switching model and two different methods for predicting the regimes are tested. The dynamic relation between the weather and the load is modeled by simple transfer functions and the non-linearities are described using spline functions. The results are thoroughly evaluated and it is shown that the spline functions are suitable for handling the non-linear relations and that after applying an auto-regressive noise model the one-step ahead residuals do not contain further significant information.

KW - Refrigeration

KW - Load forecasting

KW - Numerical weather predictions

KW - Adaptive models

KW - Base splines

KW - Time series analysis

U2 - 10.1016/j.apenergy.2015.10.046

DO - 10.1016/j.apenergy.2015.10.046

M3 - Journal article

VL - 163

SP - 32

EP - 40

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

IS - Februar 2016

ER -