Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia
Rapid population growth and urbanization, coupled with technological advancements, have driven higher electricity demand, predominantly sourced from contributors to climate change. This article introduces a novel artificial intelligence (AI) time-series algorithm, a simple stacked ensemble of simple...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Penerbit UTM
2025
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/43575/1/IJBES%20%282025%29.pdf http://umpir.ump.edu.my/id/eprint/43575/7/Enhancing%20electricity%20consumption%20forecasting%20in%20limited%20dataset_A%20simple%20stacked%20ensemble%20approach%20incorporating%20simple%20linear%20and%20support%20vector%20regression%20for%20Malaysia_abs.pdf |
| _version_ | 1824451750822674432 |
|---|---|
| author | Chuan, Zun Liang Shao Jie, Ong Yim Hin, Tham Siti Nur Syamimi, Mat Zain Yunalis Amani, Abdul Rashid Ainur Naseiha, Kamarudin |
| author_facet | Chuan, Zun Liang Shao Jie, Ong Yim Hin, Tham Siti Nur Syamimi, Mat Zain Yunalis Amani, Abdul Rashid Ainur Naseiha, Kamarudin |
| author_sort | Chuan, Zun Liang |
| collection | UMP |
| description | Rapid population growth and urbanization, coupled with technological advancements, have driven higher electricity demand, predominantly sourced from contributors to climate change. This article introduces a novel artificial intelligence (AI) time-series algorithm, a simple stacked ensemble of simple linear regression (SLR) and Support Vector Regression (SVR), designed to forecast Malaysia’s annual electricity consumption, particularly in scenarios with limited datasets utilizing the Cross Industry Standard Process for Data Mining (CRISP-DM) data science methodology. Analysis revealed that this simple stacked ensemble SVR-based time-series algorithm, employing an ε -insensitive loss function with a third-degree polynomial kernel, outperformed 71 other SVR-based algorithms, including four time-series algorithms from the previous study. The algorithm’s forecasting insights from the formulated algorithm could guide policymakers in establishing more effective regulations aligned with Sustainable Development Goals (SDGs) such as affordable and clean energy (SDG7), decent work and economic growth (SDG8), industry, innovation and infrastructure (SDG9), sustainable cities and communities (SDG11), responsible consumption and production (SDG12), and climate action (SDG13), which benefit economic, environmental, human, and social. |
| first_indexed | 2025-02-19T02:39:36Z |
| format | Article |
| id | UMPir43575 |
| institution | Universiti Malaysia Pahang |
| language | English English |
| last_indexed | 2025-02-19T02:39:36Z |
| publishDate | 2025 |
| publisher | Penerbit UTM |
| record_format | dspace |
| spelling | UMPir435752025-01-15T06:24:04Z http://umpir.ump.edu.my/id/eprint/43575/ Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia Chuan, Zun Liang Shao Jie, Ong Yim Hin, Tham Siti Nur Syamimi, Mat Zain Yunalis Amani, Abdul Rashid Ainur Naseiha, Kamarudin Q Science (General) QA Mathematics QD Chemistry T Technology (General) TP Chemical technology Rapid population growth and urbanization, coupled with technological advancements, have driven higher electricity demand, predominantly sourced from contributors to climate change. This article introduces a novel artificial intelligence (AI) time-series algorithm, a simple stacked ensemble of simple linear regression (SLR) and Support Vector Regression (SVR), designed to forecast Malaysia’s annual electricity consumption, particularly in scenarios with limited datasets utilizing the Cross Industry Standard Process for Data Mining (CRISP-DM) data science methodology. Analysis revealed that this simple stacked ensemble SVR-based time-series algorithm, employing an ε -insensitive loss function with a third-degree polynomial kernel, outperformed 71 other SVR-based algorithms, including four time-series algorithms from the previous study. The algorithm’s forecasting insights from the formulated algorithm could guide policymakers in establishing more effective regulations aligned with Sustainable Development Goals (SDGs) such as affordable and clean energy (SDG7), decent work and economic growth (SDG8), industry, innovation and infrastructure (SDG9), sustainable cities and communities (SDG11), responsible consumption and production (SDG12), and climate action (SDG13), which benefit economic, environmental, human, and social. Penerbit UTM 2025 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/43575/1/IJBES%20%282025%29.pdf pdf en http://umpir.ump.edu.my/id/eprint/43575/7/Enhancing%20electricity%20consumption%20forecasting%20in%20limited%20dataset_A%20simple%20stacked%20ensemble%20approach%20incorporating%20simple%20linear%20and%20support%20vector%20regression%20for%20Malaysia_abs.pdf Chuan, Zun Liang and Shao Jie, Ong and Yim Hin, Tham and Siti Nur Syamimi, Mat Zain and Yunalis Amani, Abdul Rashid and Ainur Naseiha, Kamarudin (2025) Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia. International Journal of Built Environment and Sustainability, 12 (1). pp. 9-21. ISSN 2289–8948 (eISSN). (Published) https://doi.org/10.11113/ijbes.v12.n1.1254 10.11113/ijbes.v12.n1.1254 |
| spellingShingle | Q Science (General) QA Mathematics QD Chemistry T Technology (General) TP Chemical technology Chuan, Zun Liang Shao Jie, Ong Yim Hin, Tham Siti Nur Syamimi, Mat Zain Yunalis Amani, Abdul Rashid Ainur Naseiha, Kamarudin Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia |
| title | Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia |
| title_full | Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia |
| title_fullStr | Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia |
| title_full_unstemmed | Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia |
| title_short | Enhancing electricity consumption forecasting in limited dataset: A simple stacked ensemble approach incorporating simple linear and support vector regression for Malaysia |
| title_sort | enhancing electricity consumption forecasting in limited dataset a simple stacked ensemble approach incorporating simple linear and support vector regression for malaysia |
| topic | Q Science (General) QA Mathematics QD Chemistry T Technology (General) TP Chemical technology |
| url | http://umpir.ump.edu.my/id/eprint/43575/1/IJBES%20%282025%29.pdf http://umpir.ump.edu.my/id/eprint/43575/7/Enhancing%20electricity%20consumption%20forecasting%20in%20limited%20dataset_A%20simple%20stacked%20ensemble%20approach%20incorporating%20simple%20linear%20and%20support%20vector%20regression%20for%20Malaysia_abs.pdf |
| work_keys_str_mv | AT chuanzunliang enhancingelectricityconsumptionforecastinginlimiteddatasetasimplestackedensembleapproachincorporatingsimplelinearandsupportvectorregressionformalaysia AT shaojieong enhancingelectricityconsumptionforecastinginlimiteddatasetasimplestackedensembleapproachincorporatingsimplelinearandsupportvectorregressionformalaysia AT yimhintham enhancingelectricityconsumptionforecastinginlimiteddatasetasimplestackedensembleapproachincorporatingsimplelinearandsupportvectorregressionformalaysia AT sitinursyamimimatzain enhancingelectricityconsumptionforecastinginlimiteddatasetasimplestackedensembleapproachincorporatingsimplelinearandsupportvectorregressionformalaysia AT yunalisamaniabdulrashid enhancingelectricityconsumptionforecastinginlimiteddatasetasimplestackedensembleapproachincorporatingsimplelinearandsupportvectorregressionformalaysia AT ainurnaseihakamarudin enhancingelectricityconsumptionforecastinginlimiteddatasetasimplestackedensembleapproachincorporatingsimplelinearandsupportvectorregressionformalaysia |