Open access
Journal
SINTA 1
Analysing feature selection: impacts towards forecasting electricity power consumption
International Journal of Reconfigurable and Embedded Systems (IJRES) · Vol. 14 No. 1 (2025) · pp. 265–272
ISSN 2722-2608, 2089-4864
Published 2025-03-01
Publisher Institute of Advanced Engineering and Science
Language eng
Abstract
This study focuses on the development of electrical power forecasting based on electricity usage in Wuzhou, China. To develop a forecasting model, the important features need to be identified. Therefore, this study investigates the performance of the feature selection method, focusing on the mutual information as a filter and random forest as a wrapper-based feature selection. From the experiment, six features have been chosen, whereby both feature selection methods chose almost identical features. Later, the selected features are trained and tested with common machine learning models, namely random forest regressor, support vector regression (SVR), k-nearest neighbor (KNN) regressor, and extreme gradient boosting (XGBoost) regressor. The performances of the feature selections tested on each of the models are measured in terms of mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R²). Findings from the experiment revealed that XGBoost outperform the other machine learning models with RMSE 0.9566 and R² indicated with 0.2561. However, SVR outperformed XGBoost and other model by obtaining MAE 0.6028. It can be concluded that the performance of filter-based outperformed the embedded feature selection.
Collaboration network of the authors
19 authors ·
65 co-authorship links
· 16 across different organisations
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
Universiti Teknologi MARA Universiti Sains Malaysia Penang Development Corporation Affiliation unknown
Different organisations
Same organisation
Affiliation unknown
Thicker line = more joint articles · bigger circle = more articles
Show as table
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.
Metadata source: OAI-PMH (metadata jurnal) http://ijres.iaescore.com/index.php/IJRES/oai, first harvested 8 Nov 2026, last seen 16 Nov 2026.
Original metadata (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title xml:lang="en-US">Analysing feature selection: impacts towards forecasting electricity power consumption</dc:title>
<dc:creator>Malik, Azman Ab</dc:creator>
<dc:creator>Tao, Lyu</dc:creator>
<dc:creator>Allias, Noormadinah</dc:creator>
<dc:creator>Hamzah, Irni Hamiza</dc:creator>
<dc:subject xml:lang="en-US">Coefficient of determination; Extreme gradient boosting; Forecasting model; K-nearest neighbor; Machine learning algorithm; Random forest; Support vector regressor</dc:subject>
<dc:description xml:lang="en-US">This study focuses on the development of electrical power forecasting based on electricity usage in Wuzhou, China. To develop a forecasting model, the important features need to be identified. Therefore, this study investigates the performance of the feature selection method, focusing on the mutual information as a filter and random forest as a wrapper-based feature selection. From the experiment, six features have been chosen, whereby both feature selection methods chose almost identical features. Later, the selected features are trained and tested with common machine learning models, namely random forest regressor, support vector regression (SVR), k-nearest neighbor (KNN) regressor, and extreme gradient boosting (XGBoost) regressor. The performances of the feature selections tested on each of the models are measured in terms of mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R²). Findings from the experiment revealed that XGBoost outperform the other machine learning models with RMSE 0.9566 and R² indicated with 0.2561. However, SVR outperformed XGBoost and other model by obtaining MAE 0.6028. It can be concluded that the performance of filter-based outperformed the embedded feature selection.</dc:description>
<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
<dc:contributor xml:lang="en-US"></dc:contributor>
<dc:date>2025-03-01</dc:date>
<dc:type>info:eu-repo/semantics/article</dc:type>
<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
<dc:type xml:lang="en-US"></dc:type>
<dc:format>application/pdf</dc:format>
<dc:identifier>https://ijres.iaescore.com/index.php/IJRES/article/view/21323</dc:identifier>
<dc:identifier>10.11591/ijres.v14.i1.pp265-272</dc:identifier>
<dc:source xml:lang="en-US">International Journal of Reconfigurable and Embedded Systems (IJRES); Vol 14, No 1: March 2025; 265-272</dc:source>
<dc:source>2722-2608</dc:source>
<dc:source>2089-4864</dc:source>
<dc:source>10.11591/ijres.v14.i1</dc:source>
<dc:language>eng</dc:language>
<dc:relation>https://ijres.iaescore.com/index.php/IJRES/article/view/21323/pdf</dc:relation>
<dc:rights xml:lang="en-US">Copyright (c) 2025 Institute of Advanced Engineering and Science (IAES)</dc:rights>
<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>
Citations and indexing
OpenAlex
Indexed
via DOI
2 citations
Crossref
Indexed
via DOI
1 citation
Counts as reported by each index on 13 Nov 2026; indexes count citations differently.
OpenAlex also lists this work in: crossref.
Cite this article
APA 7
Malik, A. A., Tao, L., Allias, N., & Hamzah, I. H. (2025). Analysing feature selection: impacts towards forecasting electricity power consumption. International Journal of Reconfigurable and Embedded Systems (IJRES), 14(1), 265–272. https://doi.org/10.11591/ijres.v14.i1.pp265-272
Copy
IEEE
A. A. Malik, L. Tao, N. Allias, and I. H. Hamzah, “Analysing feature selection: impacts towards forecasting electricity power consumption,” International Journal of Reconfigurable and Embedded Systems (IJRES), vol. 14, no. 1, pp. 265–272, 2025, doi: 10.11591/ijres.v14.i1.pp265-272.
Copy
Generated from the journal's metadata; check author names before use.