Enhancing Energy Efficiency in Residential Buildings: A Comparative Analysis of Supervised and Unsupervised Learning Techniques

In this paper different machine learning algorithms are used to predict the energy performance of residential buildings. Prediction of energy consumption has a major role in energy conservation, management, and planning. The data is classified using a variety of supervised and unsupervised techniques. For generating predictive models, predictive modelling algorithms are employed for regression as well as classification. It is examined to determine how well the various predictive models perform and contrast with each other. A comparative analysis was implemented to assess the surmising performance of the model. From the results, we can infer that the Decision Tree Classifier performs the best in terms of classification and in clustering algorithms produced on the dataset, the AdaBoost algorithm performs better compared to the K-Means algorithm. While in Ensemble methods, a combination of Decision tree and Logistic regression exhibits higher performance Finally, this paper substructures the expediency of using machine learning algorithms to estimate the energy performance of buildings as a beneficial and authentic approach.