Date of Award


Document Type

Masters Thesis

Degree Name


Organizational Unit

Daniel Felix Ritchie School of Engineering and Computer Science

First Advisor

Wenzhong Gao, Ph.D.


Temperature control, Matlab, Fuzzy neural network


Temperature control is important for both human comfort and the need in industry. In the thesis, two good intelligent control methods are compared to find their advantages and disadvantages. Matlab is used as the tool to make models and process calculations. The building model is one simple room in Akwesasne in New York State and the target is to keep the temperature indoor around 22 degree Centigrade from 12/29/2013 to 12/31/2013. Heat pump is used to provide or absorb heat. All data in the experiments is from JRibal Environmental eXchange network and PJM. The first method is fuzzy neural network (FNN). With the control from fuzzy logic and the learning process in neural network, the temperature is kept around 22 degree Centigrade. Another method is model predictive control (MPC) with genetic algorithm (GA). And the temperature is also controlled around 22 degree Centigrade by predicting the temperature and solar radiation. In addition, the cost is saved by using genetic algorithm with an energy storage system added in the building model. In summary, FNN is easy to build but the result is not very accurate; while the result of MPC is more accurate but the model is hard to develop. And GA is a good optimization method.

Publication Statement

Copyright is held by the author. User is responsible for all copyright compliance.

Rights Holder

Feng Zhang


Received from ProQuest

File Format




File Size

121 p.


Electrical engineering