Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications
Electricity has been a key driver of global socioeconomic development and sustainability for both developed and developing nations. In Malaysia, electricity is primarily generated by burning fossil fuels, emitting greenhouse gases (GHG) that adversely impact the environment and public health. Theref...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Teknologi Malaysia
2024
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/43571/1/Matematika%20%282024%29.pdf |
| _version_ | 1824451750426312704 |
|---|---|
| author | Chuan, Zun Liang Tan, Lit Ken Wee, Angel Chi Chyin Yim Hin, Tham Shao, Jie Ong Jia, Yi Low Chong, Yeh Sai |
| author_facet | Chuan, Zun Liang Tan, Lit Ken Wee, Angel Chi Chyin Yim Hin, Tham Shao, Jie Ong Jia, Yi Low Chong, Yeh Sai |
| author_sort | Chuan, Zun Liang |
| collection | UMP |
| description | Electricity has been a key driver of global socioeconomic development and sustainability for both developed and developing nations. In Malaysia, electricity is primarily generated by burning fossil fuels, emitting greenhouse gases (GHG) that adversely impact the environment and public health. Therefore, accurately predicting electricity consumption is crucial for economic management, security analysis, facility scheduling for generation and distribution, and maintenance planning. This study aimed to develop a modified stacked ensemble multivariable Artificial Intelligence (AI)-based predictive algorithm, specifically Stacked Simple Linear Regression and Multiple Linear Regression (SLR-MLR), and Stacked Simple Linear Regression and Multiple Non-Linear Regression (SLR-MNLR) utilizing the Cross Industry Standard Process for Data Mining (CRISP-DM) data science methodology. The proposed AI-based predictive algorithm aimed to provide predictive insights and interpret the impact of significant economic, environmental, and social clustered determinants on electricity consumption in Malaysia. The analysis revealed that the SLR-MLR predictive algorithm better fits Malaysia's limited electricity consumption dataset compared to the existing Stacked SLR and -Support Vector Regression (SLR--SVR) and SLR-MNLR predictive algorithms. It identified key economic and environmental clustered determinants that significantly impact electricity consumption in Malaysia. In academia, this study proposed an innovative SLR-MLR predictive algorithm and utilized a novel statistical approach to evaluate and select the superior predictive algorithm. Practically, it offered valuable insights for policymakers to craft efficient regulations, manage the energy sector proactively, and anticipate electricity generation and consumption trends. These contributions align with Malaysia's economic and environmental sustainability goals outlined in the Twelfth Malaysia Plan, the Madani Economy Framework, the National Energy Policy 2022-2040, and the National Energy Transition Roadmap (NETR) agenda. |
| first_indexed | 2025-02-19T02:39:35Z |
| format | Article |
| id | UMPir43571 |
| institution | Universiti Malaysia Pahang |
| language | English |
| last_indexed | 2025-02-19T02:39:35Z |
| publishDate | 2024 |
| publisher | Universiti Teknologi Malaysia |
| record_format | dspace |
| spelling | UMPir435712025-01-15T05:48:03Z http://umpir.ump.edu.my/id/eprint/43571/ Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications Chuan, Zun Liang Tan, Lit Ken Wee, Angel Chi Chyin Yim Hin, Tham Shao, Jie Ong Jia, Yi Low Chong, Yeh Sai QA Mathematics Electricity has been a key driver of global socioeconomic development and sustainability for both developed and developing nations. In Malaysia, electricity is primarily generated by burning fossil fuels, emitting greenhouse gases (GHG) that adversely impact the environment and public health. Therefore, accurately predicting electricity consumption is crucial for economic management, security analysis, facility scheduling for generation and distribution, and maintenance planning. This study aimed to develop a modified stacked ensemble multivariable Artificial Intelligence (AI)-based predictive algorithm, specifically Stacked Simple Linear Regression and Multiple Linear Regression (SLR-MLR), and Stacked Simple Linear Regression and Multiple Non-Linear Regression (SLR-MNLR) utilizing the Cross Industry Standard Process for Data Mining (CRISP-DM) data science methodology. The proposed AI-based predictive algorithm aimed to provide predictive insights and interpret the impact of significant economic, environmental, and social clustered determinants on electricity consumption in Malaysia. The analysis revealed that the SLR-MLR predictive algorithm better fits Malaysia's limited electricity consumption dataset compared to the existing Stacked SLR and -Support Vector Regression (SLR--SVR) and SLR-MNLR predictive algorithms. It identified key economic and environmental clustered determinants that significantly impact electricity consumption in Malaysia. In academia, this study proposed an innovative SLR-MLR predictive algorithm and utilized a novel statistical approach to evaluate and select the superior predictive algorithm. Practically, it offered valuable insights for policymakers to craft efficient regulations, manage the energy sector proactively, and anticipate electricity generation and consumption trends. These contributions align with Malaysia's economic and environmental sustainability goals outlined in the Twelfth Malaysia Plan, the Madani Economy Framework, the National Energy Policy 2022-2040, and the National Energy Transition Roadmap (NETR) agenda. Universiti Teknologi Malaysia 2024-12-31 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/43571/1/Matematika%20%282024%29.pdf Chuan, Zun Liang and Tan, Lit Ken and Wee, Angel Chi Chyin and Yim Hin, Tham and Shao, Jie Ong and Jia, Yi Low and Chong, Yeh Sai (2024) Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications. MATEMATIKA, 40 (3). pp. 143-167. ISSN 0127-8274. (Published) https://doi.org/10.11113/matematika.v40.n3.1594 10.11113/matematika.v40.n3.1594 |
| spellingShingle | QA Mathematics Chuan, Zun Liang Tan, Lit Ken Wee, Angel Chi Chyin Yim Hin, Tham Shao, Jie Ong Jia, Yi Low Chong, Yeh Sai Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications |
| title | Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications |
| title_full | Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications |
| title_fullStr | Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications |
| title_full_unstemmed | Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications |
| title_short | Sustainable energy management: Artificial intelligence-based electricity consumption prediction in limited dataset environment for industry applications |
| title_sort | sustainable energy management artificial intelligence based electricity consumption prediction in limited dataset environment for industry applications |
| topic | QA Mathematics |
| url | http://umpir.ump.edu.my/id/eprint/43571/1/Matematika%20%282024%29.pdf |
| work_keys_str_mv | AT chuanzunliang sustainableenergymanagementartificialintelligencebasedelectricityconsumptionpredictioninlimiteddatasetenvironmentforindustryapplications AT tanlitken sustainableenergymanagementartificialintelligencebasedelectricityconsumptionpredictioninlimiteddatasetenvironmentforindustryapplications AT weeangelchichyin sustainableenergymanagementartificialintelligencebasedelectricityconsumptionpredictioninlimiteddatasetenvironmentforindustryapplications AT yimhintham sustainableenergymanagementartificialintelligencebasedelectricityconsumptionpredictioninlimiteddatasetenvironmentforindustryapplications AT shaojieong sustainableenergymanagementartificialintelligencebasedelectricityconsumptionpredictioninlimiteddatasetenvironmentforindustryapplications AT jiayilow sustainableenergymanagementartificialintelligencebasedelectricityconsumptionpredictioninlimiteddatasetenvironmentforindustryapplications AT chongyehsai sustainableenergymanagementartificialintelligencebasedelectricityconsumptionpredictioninlimiteddatasetenvironmentforindustryapplications |