Machine learning based energy evaluation using air temperature and air velocity

• Main Author: Mohamed Farhan Mohamed Farouk
• Other Authors: Soh Yeng Chai
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Computer science and engineering::Software::Programming languages; Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/138742
• Institution: Nanyang Technological University

The talk of the generation has been on one particular topic, climate change. Though it has been ongoing for years or even decades, it still is a topic of concern amongst many. Development in technology and quality of life has put humans on the forefront but the very environment we are living in may be subjected to damages which may go unrealised. A large part of climate and environmental changes has to do with inefficient usage and wastage of energy and electricity. Climate change affects the entire planet and Singapore is no exception. Despite several efforts to reduce carbon emissions, as a nation there are plenty more to be done to deliver greater positive impacts. In Singapore, buildings, both residential and non-residential consume plenty of energy through the use of Heating Ventilation and Air Conditioning (HVAC) and Air Conditioning and Mechanical Ventilation (ACMV) systems. Apart from focusing on energy efficiency and cost savings, this project aims to increase energy efficiency of these systems whilst maintaining a satisfactory level of thermal comfort for occupants in buildings. Machine Learning is employed in MATLAB to analyse the association of energy consumption with thermal comfort levels. Neural Networks models and Extreme Learning Machine are experimented with the data obtained to evaluate thermal comfort and the Predicted Mean Vote (PMV) Index. Ultimately, the optimisation algorithm would be able to provide a solution to attain energy efficiency in HVAC systems without compromising on the thermal comfort levels of the occupants in rooms and buildings.