Building energy consumption forecast using multi-objective genetic programming

Amirhessam Tahmassebi, Amirhossein Gandomi

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

A multi-objective genetic programming (MOGP) technique with multiple genes is proposed to formulate the energy performance of residential buildings. Here, it is assumed that loads have linear relation in terms of genes. On this basis, an equation is developed by MOGP method to predict both heating and cooling loads. The proposed evolutionary approach optimizes the most significant predictor input variables in the model for both accuracy and complexity, while simultaneously solving the unknown parameters of the model. In the proposed energy performance model, relative compactness has the most and orientation the least contribution. The proposed MOGP model is simple and has a high degree of accuracy. The results show that MOGP is a suitable tool to generate solid models for complex nonlinear systems with capability of solving big data problems via parallel algorithms.

Original languageEnglish (US)
Pages (from-to)164-171
Number of pages8
JournalMeasurement: Journal of the International Measurement Confederation
Volume118
DOIs
StatePublished - Mar 1 2018

Fingerprint

Genetic programming
energy consumption
programming
forecasting
Energy utilization
genes
Genes
void ratio
nonlinear systems
Parallel algorithms
Nonlinear systems
Loads (forces)
Cooling
cooling
Heating
heating
energy
predictions

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

@article{30756f85838b45388a20c3b55ce320ae,
title = "Building energy consumption forecast using multi-objective genetic programming",
abstract = "A multi-objective genetic programming (MOGP) technique with multiple genes is proposed to formulate the energy performance of residential buildings. Here, it is assumed that loads have linear relation in terms of genes. On this basis, an equation is developed by MOGP method to predict both heating and cooling loads. The proposed evolutionary approach optimizes the most significant predictor input variables in the model for both accuracy and complexity, while simultaneously solving the unknown parameters of the model. In the proposed energy performance model, relative compactness has the most and orientation the least contribution. The proposed MOGP model is simple and has a high degree of accuracy. The results show that MOGP is a suitable tool to generate solid models for complex nonlinear systems with capability of solving big data problems via parallel algorithms.",
author = "Amirhessam Tahmassebi and Amirhossein Gandomi",
year = "2018",
month = "3",
day = "1",
doi = "https://doi.org/10.1016/j.measurement.2018.01.032",
language = "English (US)",
volume = "118",
pages = "164--171",
journal = "Measurement",
issn = "0263-2241",
publisher = "Elsevier",

}

Building energy consumption forecast using multi-objective genetic programming. / Tahmassebi, Amirhessam; Gandomi, Amirhossein.

In: Measurement: Journal of the International Measurement Confederation, Vol. 118, 01.03.2018, p. 164-171.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Building energy consumption forecast using multi-objective genetic programming

AU - Tahmassebi, Amirhessam

AU - Gandomi, Amirhossein

PY - 2018/3/1

Y1 - 2018/3/1

N2 - A multi-objective genetic programming (MOGP) technique with multiple genes is proposed to formulate the energy performance of residential buildings. Here, it is assumed that loads have linear relation in terms of genes. On this basis, an equation is developed by MOGP method to predict both heating and cooling loads. The proposed evolutionary approach optimizes the most significant predictor input variables in the model for both accuracy and complexity, while simultaneously solving the unknown parameters of the model. In the proposed energy performance model, relative compactness has the most and orientation the least contribution. The proposed MOGP model is simple and has a high degree of accuracy. The results show that MOGP is a suitable tool to generate solid models for complex nonlinear systems with capability of solving big data problems via parallel algorithms.

AB - A multi-objective genetic programming (MOGP) technique with multiple genes is proposed to formulate the energy performance of residential buildings. Here, it is assumed that loads have linear relation in terms of genes. On this basis, an equation is developed by MOGP method to predict both heating and cooling loads. The proposed evolutionary approach optimizes the most significant predictor input variables in the model for both accuracy and complexity, while simultaneously solving the unknown parameters of the model. In the proposed energy performance model, relative compactness has the most and orientation the least contribution. The proposed MOGP model is simple and has a high degree of accuracy. The results show that MOGP is a suitable tool to generate solid models for complex nonlinear systems with capability of solving big data problems via parallel algorithms.

UR - http://www.scopus.com/inward/record.url?scp=85041470719&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041470719&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.measurement.2018.01.032

DO - https://doi.org/10.1016/j.measurement.2018.01.032

M3 - Article

VL - 118

SP - 164

EP - 171

JO - Measurement

JF - Measurement

SN - 0263-2241

ER -