Study on energy management systems for buildings
Tutor / director / evaluatorDelgado Prieto, Miquel
CovenanteeOdisee Technologiecampus Gent
Document typeBachelor thesis
Rights accessRestricted access - author's decision
This bachelor thesis contains the study and realization of a part of a system that controls the energy consumption of the GAIA building, located in Terrassa (Barcelona, Spain). The goal of this project is to optimize the energy consumption related to the Heating Ventilation and Air Conditioning (HVAC) system within this building. In order to reduce this energy consumption, the approach is to understand the requirements in the short and middle term future. The core of this project is thus to optimize the energy consumption by controlling the energy requirements considering the building usage patterns such occupancy level and external temperature. More specifically, the aim or objective of this study is to use and understand the machine learning techniques in order to characterize past trends so that the future trends can be predicted. The machine learning technique is based on an artificial intelligence (AI) technique called Adaptive Neuro Fuzzy Inference System (ANFIS). This technique configurates the Fuzzy Inference System (FIS) parameters in order to change the output of the methodology depending on the temperature setpoint. Everything within this project is realized within the software MATLAB, which is an advanced mathematical engineering environment. This project is in collaboration with and in function of the Motion Control and Industrial Applications (MCIA) research group. This group is a part of the Universitat Politècnica de Catalunya (UPC) or the Technical University of Catalonia, the tutors and students of this research group provided the necessary information and support for this project.
SubjectsEnergy consumption, Machine learning, Artificial intelligence, Energia -- Consum, Aprenentatge automàtic, Intel·ligència artificial
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder