Machine learning based energy evaluation using air temperature and air velocity
Tan, Wei Chong
Date of Issue2017-05-12
School of Electrical and Electronic Engineering
In recent years, green building and energy efficient building are on the rise. Numerous research was conducted to reduce energy consumption of the building and achieve energy savings. Thereafter, intelligent building technology was highly sought after to tackle this problem. In this paper, machine learning techniques were used to develop a model to analyze the relationship between energy consumption and thermal comfort of buildings. The model started by training their respective class of Artificial Neural Network (ANN). Moreover, thermal comfort level will be represented by Predicted Mean Vote (PMV) to analysis the comfort zone of the occupants. The optimization problem was formulated by both energy and PMV model function. Subsequently, optimization algorithm such as Genetic Algorithm (GA) was then applied to the given optimization problem. MATLAB was used to simulate the GA and searched for the optimal solution of the HVAC system. The exhaustive search method was also employed to validate the optimal solution obtained from the GA. Using the derived model, the building’s owner could operate the HVAC system at the recommended optimal operating frequency and achieve energy savings without compromising thermal comfort level.
DRNTU::Engineering::Electrical and electronic engineering
Final Year Project (FYP)
Nanyang Technological University