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. 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 (CRISPDM) 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 Malaysias limited electricity consumption dataset compared to the existing Stacked SLR and e-Support Vector Regression (SLR-e-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 Malaysias 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.

Authors

Institutions

Publication Details

Journal
MATEMATIKA
Published
2024-12-31
DOI
https://doi.org/10.11113/matematika.v40.n3.1594
Citations
3
Primary Topic
Energy Load and Power Forecasting
Type
article
Field-Weighted Citation Impact
0.63
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Sustainable Energy Management: Artificial Intelligence-Based Electricity Consumption Prediction in Limited Dataset Environment for Industry Applications

Zun Liang Chuan, Sean Wei Xiang Ong, Y. Tham, Chong Yeh Sai et al.
3 citations
MATEMATIKA
Energy Load and Power Forecasting
0.63
article

Sustainable Energy Management: Artificial Intelligence-Based Electricity Consumption Prediction in Limited Dataset Environment for Industry Applications

Zun Liang Chuan, Sean Wei Xiang Ong, Y. Tham, Chong Yeh Sai, J. F. Low, Lit Ken Tan, Angel Wee Chi Chyin
article en
3 citations

Abstract

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 (CRISPDM) 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 Malaysias limited electricity consumption dataset compared to the existing Stacked SLR and e-Support Vector Regression (SLR-e-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 Malaysias 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.

MATEMATIKA
Universiti Malaysia Pahang Al-Sultan Abdullah (MY), Sirim Berhad (MY)
Openalex Percentile: Top 30%
Energy Load and Power Forecasting
0.63
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.