Predicting Electricity Consumption at La Trobe University Using Machine Learning Algorithms
Journal Title: Advance Knowledge for Executives - Year 2024, Vol 3, Issue 1
Abstract
Objective: This study aims to predict and optimise electricity consumption patterns at La Trobe University's Bundoora Campus from 2018 to 2021. The research involves rigorous feature extraction and model evaluation using the UNICON dataset. Method: This study employs machine learning algorithms, including Random Forest, CatBoost, and XGBoost, to predict and optimise electricity consumption. The methodology adopted in this study is designed as a multi-step, iterative process to construct a highly accurate and robust. Result: Achieving an R2 value of 0.99 with a stacked model. The study not only shows high predictive accuracy but also offers practical, cost-saving recommendations, particularly in HVAC tuning and demonstrates the model's utility for real-world energy management. Conclusion: We have comprehensively evaluated the performance of multiple machine learning algorithms in predicting building electricity consumption. By analysing the discrepancies between predicted and actual consumption, facility managers can gain valuable insights into building performance, thereby allowing for more targeted energy-saving interventions. Recommendation & Implication: Not only does the study show high predictive accuracy, but it also offers practical, cost-saving recommendations, particularly in HVAC tuning, and demonstrates the model's utility for real-world energy management. The findings contribute to achieving Net Zero Carbon Emissions by 2029 at La Trobe University. Although the study focuses on one campus, the methodology has broader implications which can be applied to other institutions.
Authors and Affiliations
Pothisakha, C. , Subkrajang, K. , Utakrit, N. , Nuchitprasitchai, S. , & Bhumpenpein, N.
Keywords
Related Articles
- EP ID EP731717
- DOI -
- Views 49
- Downloads 0
Audit Committee Effectiveness and Financial Reporting Quality in Vietnamese Stocks Exchange
Objective: The objective of this research is to examine the connection between the efficiency of the audit committee and the quality of audits on the accuracy of financial reports. Method: The study collected data fro...
Designing a Debit Card for Visually Impaired Children: Challenges and Solutions
Objective: The objective is to develop a debit card that allows visually impaired children to use it independently without external assistance. This research explains the challenges and solutions in designing a blind deb...
The Effects of School Feeding Programs on Students’ Academic Achievement in Public Primary Schools of Wolaita Zone, Southern Ethiopia
Objective: The study aimed to assess the effects of the School Feeding Program on Students' academic achievement by comparing beneficiary School feeding with non – beneficiaries of School feeding in SNNPR Wolaita Zone....
NVivo for Social Sciences and Management Studies: A Systematic Review
Objective: This systematic review aims to explore the utilisation and impact of NVivo, a qualitative data analysis software, in the fields of Social Sciences and Management Studies. Method: A narrative synthesis was e...
A Review of Digital Marketing and Service Marketing during the COVID-19 and the Digital Economy
Objective: As the COVID-19 pandemic expands its influence across the globe, businesses are continuously adopting techniques for developing the business model that incorporates organisational change due to digital economy...