| G. Vonitsanos, A. Kanavos, Ph. Mylonas |
| Evaluating Machine Learning Techniques for Enhanced Prediction of Building Energy Consumption |
| 9th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM 2024), Athens, Greece, September 20-22, 2024 |
|
ABSTRACT
|
| Accurate prediction of energy usage is crucial for optimizing resource allocation, enhancing energy efficiency, and reducing environmental impact, pivotal for sustainable development. This study examines electricity consumption in three Cornell University buildings, utilizing advanced machine learning techniques to tackle the challenges of sustainable energy management effectively. We specifically evaluated the performance of Support Vector Machine (SVM), Random Forest, Decision Tree, and K-Nearest Neighbors (KNN) in forecasting electricity usage. Our findings reveal that SVM consistently outperforms the other models across various performance metrics, including accuracy and efficiency. These results provide vital insights into the efficacy of these algorithms in predicting energy consumption, thereby supporting strategic energy management decisions in educational institutions and potentially other similar settings.
|
| 20 September, 2024 |
| G. Vonitsanos, A. Kanavos, Ph. Mylonas, "Evaluating Machine Learning Techniques for Enhanced Prediction of Building Energy Consumption", 9th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM 2024), Athens, Greece, September 20-22, 2024 |
[  PDF] [
BibTex] [
Print] [
 Back] |
