Lca-based semantically-enabled framework for the dynamic optimisation of a building’s energy and environmental performance

Fnais, Abdulrahman 2023. Lca-based semantically-enabled framework for the dynamic optimisation of a building’s energy and environmental performance. PhD Thesis, Cardiff University. Item availability restricted.

	PDF - Accepted Post-Print Version Restricted to Repository staff only until 22 November 2024 due to copyright restrictions. Download (14MB)
	PDF (Cardiff University Electronic Publication Form) - Supplemental Material Restricted to Repository staff only Download (208kB)

Abstract

The rapid growth of cities, and the high energy consumption and Greenhouse Gases (GHGs) emissions of the buildings are significant challenges to reducing the environmental impact of the built environment. Life Cycle Assessment (LCA) can help to address these challenges by assessing the full life cycle of buildings and identifying areas for improvement. However, the complexity of the building sector, including variations in building usage, energy supply, and regulations, makes it difficult to consistently apply LCA methodologies to buildings. Thus, a different approach or methodology is required to improve the adoption and streamline the application of LCA in the building domain. This thesis presents a comprehensive approach to facilitate the application of LCA in buildings, with a focus on enhancing their energy and environmental performance. A framework was developed to overcome the limitations of current LCA solutions and provide a comprehensive approach to explore various scenarios during the operation of buildings by integrating various domain models and data sources. This study demonstrated the practical application of the developed framework in addressing the research questions through a specific use case. The use case showed how the framework that was developed during this work could be applied to address the challenges of reducing the environmental impacts of building energy consumption during the operation phase. The proposed optimisation strategy for mechanical ventilation systems using genetic algorithms, coupled with machine learning models, provided a practical solution that minimises energy consumption while ensuring that indoor CO2 levels remain within acceptable limits. Finally, a lightweight ontology was developed for semantically-enabled LCA in buildings. The ontology was created by identifying the domain concepts and the relationships between the identified concepts. The ontology schema was developed using a modular approach, with three interconnected modules: the Observation module, Service module, and Building module. The ontology was evaluated through SPARQL queries and was effective in providing answers to questions from various domains. The developed ontology highlights the importance of leveraging semantics to integrate information and data from different sources, facilitating the application of LCA, and enhancing interoperability and information exchange across domains.

Item Type:	Thesis (PhD)
Date Type:	Completion
Status:	Unpublished
Schools:	Engineering
Uncontrolled Keywords:	1). Life Cycle Assessment 2). Machine Learning 3). Semantic Modelling 4). Ontology 5). Dynamic Data 6). Building Energy
Date of First Compliant Deposit:	22 November 2023
Last Modified:	22 Nov 2023 16:47
URI:	https://orca.cardiff.ac.uk/id/eprint/164127

Actions (repository staff only)

Edit Item