Treffer: Multi-Objective Optimization of Building Energy Consumption: A Case Study of Temporary Buildings on Construction Sites.

Title:
Multi-Objective Optimization of Building Energy Consumption: A Case Study of Temporary Buildings on Construction Sites.
Source:
Buildings (2075-5309); Feb2025, Vol. 15 Issue 3, p420, 33p
Database:
Complementary Index

Weitere Informationen

Building energy consumption management significantly impacts energy efficiency, environmental effects, and economic benefits throughout a building's life cycle. Optimizing building energy consumption has become a great challenge in the field of green buildings. This paper proposes an automated simulation method that integrates the EnergyPlus energy consumption simulation tool with Python scripting. This approach efficiently generates large volumes of energy consumption data and supports the development of machine learning surrogate models, thereby enhancing simulation efficiency and reducing computational costs. Based on this foundation, the multi-objective optimization algorithm NSGA-III is introduced to achieve a balanced optimization of three primary objectives: building energy consumption, photovoltaic electricity generation, and thermal comfort. Through a systematic analysis of a case study involving an office building and dormitory at a construction site in China, the effects of building envelope, air conditioning systems, and occupant behavior on energy consumption are examined. The optimization results indicate that energy consumption is reduced by 41% for the office building and 38% for the dormitory. Additionally, photovoltaic electricity generation increases by 176% and 169% compared to the baseline model, while thermal comfort improves by 19% and 6%, respectively. These improvements significantly enhance energy self-sufficiency and residential comfort. [ABSTRACT FROM AUTHOR]

Copyright of Buildings (2075-5309) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)