Modeling Residential Energy Consumption Patterns with Machine Learning Methods Based on a Case Study in Brazil

• Published in: Mathematics (Basel) Vol. 12; no. 13; p. 1961
• Main Authors: Henriques, Lucas, Castro, Cecilia, Prata, Felipe, Leiva, Víctor, Venegas, René
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2024
• Subjects: Algorithms; artificial intelligence; Climate models; Cluster analysis; Clustering; consumption profiles; Data analysis; Datasets; Efficiency; Energy consumption; Energy management; Households; Machine learning; Management methods; Methodology; multi-class classification; Neural networks; pattern recognition; Policies; Power consumption; Residential energy; residential energy use; Resource management; Self organizing maps; Support vector machines; Vector quantization; Brazil
• ISSN: 2227-7390; 2227-7390
• DOI: 10.3390/math12131961

Developing efficient energy conservation and strategies is relevant in the context of climate change and rising energy demands. The objective of this study is to model and predict the electrical power consumption patterns in Brazilian households, considering the thresholds for energy use. Our methodology utilizes advanced machine learning methods, such as agglomerative hierarchical clustering, k-means clustering, and self-organizing maps, to identify such patterns. Gradient boosting, chosen for its robustness and accuracy, is used as a benchmark to evaluate the performance of these methods. Our methodology reveals consumption patterns from the perspectives of both users and energy providers, assessing the corresponding effectiveness according to stakeholder needs. Consequently, the methodology provides a comprehensive empirical framework that supports strategic decision making in the management of energy consumption. Our findings demonstrate that k-means clustering outperforms other methods, offering a more precise classification of consumption patterns. This finding aids in the development of targeted energy policies and enhances resource management strategies. The present research shows the applicability of advanced analytical methods in specific contexts, showing their potential to shape future energy policies and practices.