OCCUPANCY MODELING USING POPULATION STATISTICS AND MACHINE LEARNING IN THE RESIDENTIAL BUILT ENVIRONMENT

Date

2024-9-16

Author

İşeri , Orçun Koral

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

72
views

0
downloads

Cite This

The emphasis of Urban Building Energy Modeling (UBEM) in informing urban design, building assessments, and energy system strategies for understanding the climate change impact on urban environment is challenged by the performance gap which is a disparity between simulated and actual energy demand and can be linked to insufficient modeling of occupant behavior. Thus, this thesis introduces a datadriven occupancy modeling methodology for UBEM. For realistic representation, occupancy modeling necessitates a comprehensive exploration of daily activities and rhythms of occupants. Drawing on data from the population statistics of Italy, this study employs a data-driven approach by incorporating deep learning techniques for holistic occupant modeling with both temporal and non-temporal datasets. By analyzing occupants’ profiles, behaviors, and interactions, the study seeks to understand and propose solutions for recognized challenges, leveraging empirical occupancy data that can enhance precision of UBEM.

Subject Keywords

Building Occupancy Modeling, Urban Building Energy Modeling, Residential Energy Demand, Time-series datasets, Data-Driven Models

URI

https://hdl.handle.net/11511/111031

Collections

Graduate School of Natural and Applied Sciences, Thesis