Advanced Energy Performance Modelling: Case Study of an Engineering and Technology Precinct
Author(s): |
Faham Tahmasebinia
Lin Lin Shuo Wu Yifan Kang Samad Sepesgozar |
---|---|
Medium: | journal article |
Language(s): | English |
Published in: | Buildings, 19 June 2024, n. 6, v. 14 |
Page(s): | 1774 |
DOI: | 10.3390/buildings14061774 |
Abstract: |
The global demand for energy is significantly impacted by the consumption patterns within the building sector. As such, the importance of energy simulation and prediction is growing exponentially. This research leverages Building Information Modelling (BIM) methodologies, creating a synergy between traditional software methods and algorithm-driven approaches for comprehensive energy analysis. The study also proposes a method for monitoring select energy management factors, a step that could potentially pave the way for the integration of digital twins in energy management systems. The research is grounded in a case study of a newly constructed educational building in New South Wales, Australia. The digital physical model of the building was created using Autodesk Revit, a conventional software for BIM methodology. EnergyPlus, facilitated by OpenStudio, was employed for the traditional software-based energy analysis. The energy analysis output was then used to develop preliminary algorithm models using regression strategies in Python. In this regression analysis, the temperature and relative humidity of each energy unit were used as independent variables, with their energy consumption being the dependent variable. The sigmoid algorithm model, known for its accuracy and interpretability, was employed for advanced energy simulation. This was combined with sensor data for real-time energy prediction. A basic digital twin (DT) example was created to simulate the dynamic control of air conditioning and lighting, showcasing the adaptability and effectiveness of the system. The study also explores the potential of machine learning, specifically reinforcement learning, in optimizing energy management in response to environmental changes and usage conditions. Despite the current limitations, the study identifies potential future research directions. These include enhancing model accuracy and developing complex algorithms to boost energy efficiency and reduce costs. |
Copyright: | © 2024 by the authors; licensee MDPI, Basel, Switzerland. |
License: | This creative work has been published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license which allows copying, and redistribution as well as adaptation of the original work provided appropriate credit is given to the original author and the conditions of the license are met. |
28.62 MB
- About this
data sheet - Reference-ID
10787498 - Published on:
20/06/2024 - Last updated on:
20/06/2024