Off-campus UNL users: To download campus access dissertations, please use the following link to log into our proxy server with your NU ID and password. When you are done browsing please remember to return to this page and log out.
Non-UNL users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Multilevel Data-Driven Framework for Operating HVAC Systems to Optimize Energy and Comfort in Modern Buildings
Humans spend more than 90% of their day inside buildings where their health and productivity are demonstrably linked to thermal comfort. Building comfort systems such as heating, ventilation and air conditioning (HVAC) systems account for the largest share of U.S energy consumption. However, due to building design complexity and the variety of building occupant needs, addressing thermal comfort while reducing the high-energy cost of HVAC systems remains a complex problem. This dissertation presents a novel two-level data-driven framework to efficiently model and control comfort in buildings to overcome this challenge. The first (low) level of this framework implements a controller to improve the energy consumption of an HVAC system. In this implementation, an adaptive model predictive control (AMPC) mechanism has been developed to continuously tune the gain values of the HVAC controller to maintain a particular parameter (superheat at the outlet of its evaporator) within the desired limit. Moreover, an adaptive set-point hunting algorithm is implemented to select the right superheat setpoint to achieve system stability. The performance of the controller has been experimentally validated using two different HVAC systems. However, a limitation of this approach is the requirement of expensive and hard-to-install-and-maintain pressure sensors to measure superheat. This dissertation presents a novel big-data-driven approach to estimate superheat from simple temperature measurements. The approach was validated experimentally on two different HVAC systems monitored over an extended period. The model showed good accuracy in predicting superheat. The second (high) level deals with modeling thermal comfort using wearable-device data to develop an intelligent controller to achieve maximum comfort. In this phase, various supervised machine-learning algorithms were implemented to produce accurate personal thermal comfort models for each building occupant. These models were used to simulate an intelligent comfort controller that uses the particle swarm optimization (PSO) method to search for optimal HVAC thermostat setpoint values to achieve maximum comfort. Simulation results using the PSO algorithm have shown superior performance compared to the average thermostat setpoint.
Tesfay, Mehari, "Multilevel Data-Driven Framework for Operating HVAC Systems to Optimize Energy and Comfort in Modern Buildings" (2021). ETD collection for University of Nebraska - Lincoln. AAI28865113.