Citation

Tan, Yi Fei and Zhao, Ge Zhi and Cheeng, Tze Hang and Ooi, Chee Pun and Tan, Wooi Haw and Cheong, Soon Nyean (2023) Supervised Machine Learning Techniques for Power Consumption Usage Level Prediction. In: 2023 6th International Conference on Software Engineering and Computer Science (CSECS), 22-24 December 2023, Chengdu, China.

Text 54.pdf - Published Version Restricted to Repository staff only Download (591kB)

Abstract

Electricity is an essential part of modern life and is crucial for many aspects of society and the economy. It is essential for industries to operate and create products, for transportation systems to function, and for communication and information technology to function. As the world continues to become more connected and technologically advanced, the demand for electricity is likely to increase, making it an even more critical resource in the future. Overusing electricity will lead to higher energy bills, which can put a strain on household or business budgets. In this paper, the authors developed a model to predict the level of electricity consumption usage. The model is developed in 2 stages. First stage is to categorize the electricity usage into several levels by using equally divided method. Second stage is to use supervised machine learning techniques to develop a prediction model for the level of electricity consumption. The experimental results indicated that using the Random Forest classifier leads to better performance in terms of accuracy, precision, recall, F1 score, and kappa score. Besides that, the results show that 2-level prediction performed better than 4-level prediction.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	power consumption level, prediction, supervised machine learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics T Technology > TJ Mechanical Engineering and Machinery > TJ163.13-163.25 Power resources
Divisions:	Faculty of Computing and Informatics (FCI) Faculty of Creative Multimedia (FCM) Faculty of Engineering (FOE)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	27 Mar 2024 03:15
Last Modified:	27 Mar 2024 03:15
URII:	http://shdl.mmu.edu.my/id/eprint/12213

Downloads

Edit (login required)