Explainable Artificial Intelligence for Site Energy Usage Intensity Prediction
- The findings of this study demonstrate that the Random Forest (RF) algorithm provided the most accurate predictions in comparison with other boosting machine learning algorithms. Key drivers of energy consumption identified through XAI techniques such as SHAP and LIME include energy star rating, facility type, and floor area. These XAI methods helped enhance the interpretability of the models, making them more accessible for non-expert users, such as building managers and policymakers. By leveraging machine learning and XAI, this research provides a transparent and actionable framework for optimizing building energy efficiency and supporting sustainable energy management.
Author: | Aman Singla |
---|---|
URN: | urn:nbn:de:hbz:kob7-25164 |
Referee: | Frank Hopfgartner |
Advisor: | Stefania Zourlidou |
Document Type: | Master's Thesis |
Language: | English |
Date of completion: | 2024/09/20 |
Date of publication: | 2024/10/17 |
Publishing institution: | Universität Koblenz, Universitätsbibliothek |
Granting institution: | Universität Koblenz, Fachbereich 4 |
Date of final exam: | 2024/09/26 |
Release Date: | 2024/10/17 |
Number of pages: | xiv, 84 Seiten |
Institutes: | Fachbereich 4 / Institute for Web Science and Technologies |
Licence (German): | CC BY |