Application of Machine Learning Models on Individual Household Electric Power Consumption

Authors

Eman Abdelfattah, Sacred Heart UniversityFollow
Kevin Bowlyn, Sacred Heart UniversityFollow

Document Type

Conference Proceeding

Publication Date

2023

Abstract

This paper presents research on the application of various machine learning models to predict power consumption usage within a household. The models used for prediction are Decision Tree Regressor, Random Forest Regressor, Extra Trees Regressor, XGBoost Regressor, and K Nearest Neighbors Regressor. Mean Absolute Error, Root Mean Square Error, and Coefficient of Determination are evaluated as different performance matrices to know the best model that can be used for prediction in this application. The results show that the XGBoost regressor outperforms the other models.

Comments

2023 IEEE World AI IoT Congress (AIIoT) Seattle, WA (June 7-10).

DOI

10.1109/AIIoT58121.2023.10174456

Recommended Citation

Abdelfattah, E., & Bowlyn, K. (2023). Application of machine learning models on individual household electric power consumption (pp. 0143-0146). 2023 IEEE World AI IoT Congress (AIIoT). Doi: 10.1109/AIIoT58121.2023.10174456