ORCID Identifier(s)


Graduation Semester and Year




Document Type


Degree Name

Master of Science in Mechanical Engineering


Mechanical and Aerospace Engineering

First Advisor

Alan P Bowling

Second Advisor

Dereje Agonafer


Data Center has become a definitive element of Modern IT infrastructure. With the development of high performance computing architectures and equipment, data centers consume large amount of electricity. Due to low Demand/Supply ratio of electricity production there is need to develop ways to reduce power footprint. Many researchers are working on approaches to resolve problems related to en- ergy usage of Data Center. One of these approaches is to develop a model-based control system that would control data centers in efficient way to reduce power footprint. Computational Fluid Dynamic (CFD) has been used to model the dynamic and complex environment of the data center. However, the drawback of this approach is its computational inefficiency. The effects of changing a single input may take an entire day to compute. Thus the CFD model is not well suited for model-based control. Instead we propose to use an Artificial Neural Network (ANN) model which predicts and control server temperatures in significantly less time.The Artificial Neural Network will be trained by using CFD data where first we will show that ANN can be used to predict temperature of data center servers.Both the steady state as well as transient data will be tested and then Neural Network model based controller will be used to control the temperature of data center.


Data center, Artificial neural networks, Neural network controller


Aerospace Engineering | Engineering | Mechanical Engineering


Degree granted by The University of Texas at Arlington