Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms

Aissa Boudjella; Manal Y. Boudjella; Samir Brahim Belhouari

doi:10.1007/978-3-030-92038-8_4

Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms

Aissa Boudjella^*, Manal Y. Boudjella, Samir Brahim Belhouari

^*Corresponding author for this work

CSE Information & Computing Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Simulations have been performed to analyze the performance metric characteristics in assessing the cooling load energy of building shapes system based on the K-Nearest Neighbor (KNN) classifier. The system is implemented and simulated in Anaconda, and its performance is tested on a real dataset that contains 8 features and 768 instances to classify the cooling load magnitude into four (04) classes (4 target name labels) created based on the captured load energy magnitude. The simulation results carried out under various setting parameters show that the performance metrics depend on the test size and k-neighbors, which gives better training accuracy, slightly higher than the test accuracy in the range of [79.4%–100%] and [75.0%–92.2%], respectively. For quality analysis, the present proposed methodology can serve as a test platform for measurement and verification of the energy cooling load performance. It can be used as a performance metrics guideline that tells us how much better the proposed model is making a prediction.

Original language	English
Title of host publication	Artificial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities - Case Study
Editors	Mustapha Hatti
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	34-45
Number of pages	12
ISBN (Print)	9783030920371
DOIs	https://doi.org/10.1007/978-3-030-92038-8_4
Publication status	Published - 2022
Event	5th International Conference on Artificial Intelligence in Renewable Energetic Systems, IC-AIRES 2021 - Tipasa, Algeria Duration: 24 Nov 2021 → 26 Nov 2021

Publication series

Name	Lecture Notes in Networks and Systems
Volume	361 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	5th International Conference on Artificial Intelligence in Renewable Energetic Systems, IC-AIRES 2021
Country/Territory	Algeria
City	Tipasa
Period	24/11/21 → 26/11/21

Keywords

Accuracy
Cooling load
F-score
K-Nearest Neighbor classifier
Kappa
Machine learning
Presicion-score
Recall
Specificity test size

Access to Document

10.1007/978-3-030-92038-8_4

Cite this

Boudjella, A., Boudjella, M. Y., & Belhouari, S. B. (2022). Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms. In M. Hatti (Ed.), Artificial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities - Case Study (pp. 34-45). (Lecture Notes in Networks and Systems; Vol. 361 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-92038-8_4

Boudjella, Aissa ; Boudjella, Manal Y. ; Belhouari, Samir Brahim. / Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms. Artificial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities - Case Study. editor / Mustapha Hatti. Springer Science and Business Media Deutschland GmbH, 2022. pp. 34-45 (Lecture Notes in Networks and Systems).

@inproceedings{6060cd9caf8c4364a452eeecd83fbf63,

title = "Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms",

abstract = "Simulations have been performed to analyze the performance metric characteristics in assessing the cooling load energy of building shapes system based on the K-Nearest Neighbor (KNN) classifier. The system is implemented and simulated in Anaconda, and its performance is tested on a real dataset that contains 8 features and 768 instances to classify the cooling load magnitude into four (04) classes (4 target name labels) created based on the captured load energy magnitude. The simulation results carried out under various setting parameters show that the performance metrics depend on the test size and k-neighbors, which gives better training accuracy, slightly higher than the test accuracy in the range of [79.4%–100%] and [75.0%–92.2%], respectively. For quality analysis, the present proposed methodology can serve as a test platform for measurement and verification of the energy cooling load performance. It can be used as a performance metrics guideline that tells us how much better the proposed model is making a prediction.",

keywords = "Accuracy, Cooling load, F-score, K-Nearest Neighbor classifier, Kappa, Machine learning, Presicion-score, Recall, Specificity test size",

author = "Aissa Boudjella and Boudjella, {Manal Y.} and Belhouari, {Samir Brahim}",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 5th International Conference on Artificial Intelligence in Renewable Energetic Systems, IC-AIRES 2021 ; Conference date: 24-11-2021 Through 26-11-2021",

year = "2022",

doi = "10.1007/978-3-030-92038-8_4",

language = "English",

isbn = "9783030920371",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "34--45",

editor = "Mustapha Hatti",

booktitle = "Artificial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities - Case Study",

address = "Germany",

}

Boudjella, A, Boudjella, MY & Belhouari, SB 2022, Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms. in M Hatti (ed.), Artificial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities - Case Study. Lecture Notes in Networks and Systems, vol. 361 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 34-45, 5th International Conference on Artificial Intelligence in Renewable Energetic Systems, IC-AIRES 2021, Tipasa, Algeria, 24/11/21. https://doi.org/10.1007/978-3-030-92038-8_4

Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms. / Boudjella, Aissa; Boudjella, Manal Y.; Belhouari, Samir Brahim.
Artificial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities - Case Study. ed. / Mustapha Hatti. Springer Science and Business Media Deutschland GmbH, 2022. p. 34-45 (Lecture Notes in Networks and Systems; Vol. 361 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms

AU - Boudjella, Aissa

AU - Boudjella, Manal Y.

AU - Belhouari, Samir Brahim

PY - 2022

Y1 - 2022

N2 - Simulations have been performed to analyze the performance metric characteristics in assessing the cooling load energy of building shapes system based on the K-Nearest Neighbor (KNN) classifier. The system is implemented and simulated in Anaconda, and its performance is tested on a real dataset that contains 8 features and 768 instances to classify the cooling load magnitude into four (04) classes (4 target name labels) created based on the captured load energy magnitude. The simulation results carried out under various setting parameters show that the performance metrics depend on the test size and k-neighbors, which gives better training accuracy, slightly higher than the test accuracy in the range of [79.4%–100%] and [75.0%–92.2%], respectively. For quality analysis, the present proposed methodology can serve as a test platform for measurement and verification of the energy cooling load performance. It can be used as a performance metrics guideline that tells us how much better the proposed model is making a prediction.

AB - Simulations have been performed to analyze the performance metric characteristics in assessing the cooling load energy of building shapes system based on the K-Nearest Neighbor (KNN) classifier. The system is implemented and simulated in Anaconda, and its performance is tested on a real dataset that contains 8 features and 768 instances to classify the cooling load magnitude into four (04) classes (4 target name labels) created based on the captured load energy magnitude. The simulation results carried out under various setting parameters show that the performance metrics depend on the test size and k-neighbors, which gives better training accuracy, slightly higher than the test accuracy in the range of [79.4%–100%] and [75.0%–92.2%], respectively. For quality analysis, the present proposed methodology can serve as a test platform for measurement and verification of the energy cooling load performance. It can be used as a performance metrics guideline that tells us how much better the proposed model is making a prediction.

KW - Accuracy

KW - Cooling load

KW - F-score

KW - K-Nearest Neighbor classifier

KW - Kappa

KW - Machine learning

KW - Presicion-score

KW - Recall

KW - Specificity test size

UR - http://www.scopus.com/inward/record.url?scp=85121702519&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-92038-8_4

DO - 10.1007/978-3-030-92038-8_4

M3 - Conference contribution

AN - SCOPUS:85121702519

SN - 9783030920371

T3 - Lecture Notes in Networks and Systems

SP - 34

EP - 45

BT - Artificial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities - Case Study

A2 - Hatti, Mustapha

PB - Springer Science and Business Media Deutschland GmbH

T2 - 5th International Conference on Artificial Intelligence in Renewable Energetic Systems, IC-AIRES 2021

Y2 - 24 November 2021 through 26 November 2021

ER -

Boudjella A, Boudjella MY, Belhouari SB. Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms. In Hatti M, editor, Artificial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities - Case Study. Springer Science and Business Media Deutschland GmbH. 2022. p. 34-45. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-030-92038-8_4

Prediction and Characterization of Cooling Load Energy Performance of Residential Building Machine Learning Algorithms

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this