This repository is dedicated to the research and development of a computational intelligence method aimed at improving anomaly detection in electrical consumption profiles. Our approach utilizes historical power consumption data from multiple buildings across different countries to identify anomalous variations in energy use and infer potential causes.
- Utilization of five datasets from buildings in Ecuador, Spain, France, and Canada.
- Statistical analysis to determine daily consumption patterns.
- Machine learning model for cataloging consumption based on anomaly types.
- Evaluation showing improvement in accuracy, false positive rate (FPR), and false negative rate (FNR).
For a detailed explanation of our methods, findings, and implications, refer to our published paper: "A Computational Intelligence Method for Anomalies Detection Improvement in Electrical Consumption Profiles".
Contributions to this project are welcome. Please review the CONTRIBUTING.md
file for guidelines on how to contribute.
This project is licensed under the MIT License - see the LICENSE.md
file for details.