Prediction Of Energy Usage In IoT Devices
Authors
Ramesh, Sangeetha
Issue Date
2024-05
Degree
MSc in Business Analytics
Publisher
Dublin Business School
Rights holder
Rights
Abstract
Understanding energy consumption models can enhance energy management and cut expenses. This study aims to forecast energy usage considering different temporal and environmental factors. It specifically targets predicting the energy consumption of IoT devices, utilizing data from smart homes in Greece. Data collected from the smart home is analyzed using machine learning models including Random Forest, Support Vector Machine (SVM), Logistic Regression and XGBoost. Research involves data preprocessing, feature engineering, and applying these models to produce accurate predictions. The XGBoost and Random Forest models demonstrated the highest accuracy, highlighting their effectiveness in this context. This study provides valuable insights into energy management in smart homes, facilitating the development of efficient energy strategies and improving environmental sustainability. It also highlights the importance of using advanced machine learning techniques to accurately predict energy consumption.