Hourly cooling load forecasting using time-indexed ARX models with two-stage weighted least squares regression

Yin Guo, Ehsan Nazarian, Jeonghan Ko, Kamlakar P Rajurkar

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

This paper presents a robust hourly cooling-load forecasting method based on time-indexed autoregressive with exogenous inputs (ARX) models, in which the coefficients are estimated through a two-stage weighted least squares regression. The prediction method includes a combination of two separate time-indexed ARX models to improve prediction accuracy of the cooling load over different forecasting periods. The two-stage weighted least-squares regression approach in this study is robust to outliers and suitable for fast and adaptive coefficient estimation. The proposed method is tested on a large-scale central cooling system in an academic institution. The numerical case studies show the proposed prediction method performs better than some ANN and ARX forecasting models for the given test data set.

Original languageEnglish (US)
Pages (from-to)46-53
Number of pages8
JournalEnergy Conversion and Management
Volume80
DOIs
StatePublished - Apr 1 2014

Fingerprint

Cooling
Cooling systems

Keywords

  • ARX
  • Cooling load
  • Forecasting
  • Weighted least squares

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Nuclear Energy and Engineering
  • Fuel Technology
  • Energy Engineering and Power Technology

Cite this

Hourly cooling load forecasting using time-indexed ARX models with two-stage weighted least squares regression. / Guo, Yin; Nazarian, Ehsan; Ko, Jeonghan; Rajurkar, Kamlakar P.

In: Energy Conversion and Management, Vol. 80, 01.04.2014, p. 46-53.

Research output: Contribution to journalArticle

@article{cd9495d0b9364f3aa5fdff691d24b2df,
title = "Hourly cooling load forecasting using time-indexed ARX models with two-stage weighted least squares regression",
abstract = "This paper presents a robust hourly cooling-load forecasting method based on time-indexed autoregressive with exogenous inputs (ARX) models, in which the coefficients are estimated through a two-stage weighted least squares regression. The prediction method includes a combination of two separate time-indexed ARX models to improve prediction accuracy of the cooling load over different forecasting periods. The two-stage weighted least-squares regression approach in this study is robust to outliers and suitable for fast and adaptive coefficient estimation. The proposed method is tested on a large-scale central cooling system in an academic institution. The numerical case studies show the proposed prediction method performs better than some ANN and ARX forecasting models for the given test data set.",
keywords = "ARX, Cooling load, Forecasting, Weighted least squares",
author = "Yin Guo and Ehsan Nazarian and Jeonghan Ko and Rajurkar, {Kamlakar P}",
year = "2014",
month = "4",
day = "1",
doi = "10.1016/j.enconman.2013.12.060",
language = "English (US)",
volume = "80",
pages = "46--53",
journal = "Energy Conversion and Management",
issn = "0196-8904",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Hourly cooling load forecasting using time-indexed ARX models with two-stage weighted least squares regression

AU - Guo, Yin

AU - Nazarian, Ehsan

AU - Ko, Jeonghan

AU - Rajurkar, Kamlakar P

PY - 2014/4/1

Y1 - 2014/4/1

N2 - This paper presents a robust hourly cooling-load forecasting method based on time-indexed autoregressive with exogenous inputs (ARX) models, in which the coefficients are estimated through a two-stage weighted least squares regression. The prediction method includes a combination of two separate time-indexed ARX models to improve prediction accuracy of the cooling load over different forecasting periods. The two-stage weighted least-squares regression approach in this study is robust to outliers and suitable for fast and adaptive coefficient estimation. The proposed method is tested on a large-scale central cooling system in an academic institution. The numerical case studies show the proposed prediction method performs better than some ANN and ARX forecasting models for the given test data set.

AB - This paper presents a robust hourly cooling-load forecasting method based on time-indexed autoregressive with exogenous inputs (ARX) models, in which the coefficients are estimated through a two-stage weighted least squares regression. The prediction method includes a combination of two separate time-indexed ARX models to improve prediction accuracy of the cooling load over different forecasting periods. The two-stage weighted least-squares regression approach in this study is robust to outliers and suitable for fast and adaptive coefficient estimation. The proposed method is tested on a large-scale central cooling system in an academic institution. The numerical case studies show the proposed prediction method performs better than some ANN and ARX forecasting models for the given test data set.

KW - ARX

KW - Cooling load

KW - Forecasting

KW - Weighted least squares

UR - http://www.scopus.com/inward/record.url?scp=84893442440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893442440&partnerID=8YFLogxK

U2 - 10.1016/j.enconman.2013.12.060

DO - 10.1016/j.enconman.2013.12.060

M3 - Article

VL - 80

SP - 46

EP - 53

JO - Energy Conversion and Management

JF - Energy Conversion and Management

SN - 0196-8904

ER -