Online short-term forecast of greenhouse heat load using a weather forecast service

P. J.C. Vogler-Finck*, P. Bacher, Henrik Madsen

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

56 Downloads (Pure)

Abstract

In some district heating systems, greenhouses represent a significant share of the total load, and can lead to operational challenges. Short term load forecast of such consumers has a strong potential to contribute to the improvement of the overall system efficiency. This work investigates the performance of recursive least squares for predicting the heat load of individual greenhouses in an online manner. Predictor inputs (weekly curves terms and weather forecast inputs) are selected in an automated manner using a forward selection approach. Historical load measurements from 5 Danish greenhouses with different operational characteristics were used, together with weather measurements and a weather forecast service. It was found that these predictors of reduced complexity and computational load performed well at capturing recurring load profiles, but not fast frequency random changes. Overall, the root mean square error of the prediction was within 8–20% of the peak load for the set of consumers over the 8 months period considered.

Original languageEnglish
JournalApplied Energy
Volume205
Pages (from-to)1298-1310
ISSN0306-2619
DOIs
Publication statusPublished - 1 Nov 2017

Keywords

  • Greenhouses
  • Heat demand
  • Load forecast
  • Model selection
  • Recursive least squares
  • Weather forecast service

Cite this

@article{117368d7281a434fba6931a2f52da56f,
title = "Online short-term forecast of greenhouse heat load using a weather forecast service",
abstract = "In some district heating systems, greenhouses represent a significant share of the total load, and can lead to operational challenges. Short term load forecast of such consumers has a strong potential to contribute to the improvement of the overall system efficiency. This work investigates the performance of recursive least squares for predicting the heat load of individual greenhouses in an online manner. Predictor inputs (weekly curves terms and weather forecast inputs) are selected in an automated manner using a forward selection approach. Historical load measurements from 5 Danish greenhouses with different operational characteristics were used, together with weather measurements and a weather forecast service. It was found that these predictors of reduced complexity and computational load performed well at capturing recurring load profiles, but not fast frequency random changes. Overall, the root mean square error of the prediction was within 8–20{\%} of the peak load for the set of consumers over the 8 months period considered.",
keywords = "Greenhouses, Heat demand, Load forecast, Model selection, Recursive least squares, Weather forecast service",
author = "Vogler-Finck, {P. J.C.} and P. Bacher and Henrik Madsen",
year = "2017",
month = "11",
day = "1",
doi = "10.1016/j.apenergy.2017.08.013",
language = "English",
volume = "205",
pages = "1298--1310",
journal = "Applied Energy",
issn = "0306-2619",
publisher = "Pergamon Press",

}

Online short-term forecast of greenhouse heat load using a weather forecast service. / Vogler-Finck, P. J.C.; Bacher, P.; Madsen, Henrik.

In: Applied Energy, Vol. 205, 01.11.2017, p. 1298-1310.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Online short-term forecast of greenhouse heat load using a weather forecast service

AU - Vogler-Finck, P. J.C.

AU - Bacher, P.

AU - Madsen, Henrik

PY - 2017/11/1

Y1 - 2017/11/1

N2 - In some district heating systems, greenhouses represent a significant share of the total load, and can lead to operational challenges. Short term load forecast of such consumers has a strong potential to contribute to the improvement of the overall system efficiency. This work investigates the performance of recursive least squares for predicting the heat load of individual greenhouses in an online manner. Predictor inputs (weekly curves terms and weather forecast inputs) are selected in an automated manner using a forward selection approach. Historical load measurements from 5 Danish greenhouses with different operational characteristics were used, together with weather measurements and a weather forecast service. It was found that these predictors of reduced complexity and computational load performed well at capturing recurring load profiles, but not fast frequency random changes. Overall, the root mean square error of the prediction was within 8–20% of the peak load for the set of consumers over the 8 months period considered.

AB - In some district heating systems, greenhouses represent a significant share of the total load, and can lead to operational challenges. Short term load forecast of such consumers has a strong potential to contribute to the improvement of the overall system efficiency. This work investigates the performance of recursive least squares for predicting the heat load of individual greenhouses in an online manner. Predictor inputs (weekly curves terms and weather forecast inputs) are selected in an automated manner using a forward selection approach. Historical load measurements from 5 Danish greenhouses with different operational characteristics were used, together with weather measurements and a weather forecast service. It was found that these predictors of reduced complexity and computational load performed well at capturing recurring load profiles, but not fast frequency random changes. Overall, the root mean square error of the prediction was within 8–20% of the peak load for the set of consumers over the 8 months period considered.

KW - Greenhouses

KW - Heat demand

KW - Load forecast

KW - Model selection

KW - Recursive least squares

KW - Weather forecast service

U2 - 10.1016/j.apenergy.2017.08.013

DO - 10.1016/j.apenergy.2017.08.013

M3 - Journal article

AN - SCOPUS:85028435570

VL - 205

SP - 1298

EP - 1310

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

ER -