Electricity Consumption Classification using Various Machine Learning Models.

Paikaray, Bijay Kumar; Jena, Swarna Prabha; Mondal, Jayanta; Nguyen Van Thuan; Nguyen Trong Tung; Mallick, Chandrakant

INTRODUCTION: As population has increased over successive generations, human dependency on electricity has increased to the point where it has become a norm and indispensable, and the idea of living without it has become unthinkable. OBJECTIVES: Machine learning is emerging as a fundamental method for performing tasks autonomously without human intervention. Forecasting electricity consumption is challenging due to the many factors that influence it; embracing modern technology with its heavy focus on machine learning and artificial intelligence is a potential solution. METHODS: This study employs various machine learning algorithms to forecast power usage and determine which method performs best in predicting the dataset based on different variables. RESULTS: Eight models were tested, including Linear Regression, DT Classifier, RF Classifier, KNN, DT Regression, SVM, Logistic Regression, and GNB Classifier. The Decision Tree model had the greatest accuracy of 98.3%. CONCLUSION: The Decision Tree model's accuracy can facilitate efficient use of electricity, leading to both conservation of electricity and cost savings, and be a guiding light in future planning.

ELECTRIC power consumption; MACHINE learning; DECISION trees; ARTIFICIAL intelligence; ELECTRICITY

EAI Endorsed Transactions on the Energy Web, 2024, Vol 11, Issue 1, p1

2032-944X

Academic Journal

10.4108/ew.6274