ARTIFICIAL NEURAL NETWORK BASED PREDICTION AND COOLING ENRGY OPTIMIZATION OF DATA CENTERS
- Project Research
- 1-5 Chapters
- Abstract : Available
- Table of Content: Available
- Reference Style: APA
- Recommended for : Student Researchers
- NGN 5000
ABSTRACT
Thermal management of data centers remains a challenge because of their everincreasing power densities and decreasing server footprints. Current lack of dynamic control over global provisioning and local distribution of cooling resources often result in wasteful overcooling. These trends motivate this thesis research, which focuses on the development of a reliable and energy-efficient framework for allocating cooling resources to meet thermal management requirements, while minimizing energy consumption and adverse environmental impacts. A key component of energy-efficient thermal management is real-time accurate prediction of temperature distribution in data centers. This first section of this dissertation focuses on development and comparison of four Data Driven Modeling (DDM) methods, namely Artificial Neural Networks (ANN), Support Vector Regression (SVR), Gaussian Process Regression (GPR) and Proper Orthogonal Decomposition (POD). These DDM methods were trained on datasets generated from offline Computational Fluid Dynamics/Heat Transfer (CFD/HT) simulations for real-time prediction of temperature and airflow distributions in a data center. Using CFD simulation results to train DDMs transfers computational complexity from model execution (in CFD) to model setup and development. To generate the training data, a physics-based and experimentally validated room-level CFD/HT model was developed using the commercial software Future Facilities 6Sigma Room.
Related Project Materials
INNOVATIONS IN INDUSTRY-ALIGNED CERTIFICATIONS FOR VOCATIONAL PROGRAMS
Abstract: Innovations in industry-aligned certifications for vocational programs are essent...
An Evaluation of the Role of Biostatistics in Evaluating Cancer Incidence in Katsina State
Background of the Study
Biostatistics is an essential tool in the field of public health and epidemiology, providing the me...
ASSESSMENT OF PETROLEUM PROFIT TAX UNDER THE NIGERIAN TAX LAWS
Problems of the Research
There are many problems affecting the petroleum profit tax in general and the petroleum profit...
An Investigation of Sentiment Analysis on Student Feedback for Course Improvement in Federal University Lokoja, Kogi State
Background of the Study
Student feedback is an invaluable resource for enhancing course content and delivery, yet traditio...
An Evaluation of Nurses’ Knowledge and Adherence to Infection Control in Burn Units in Kogi State Healthcare Facilities
Background of the Study
Burn injuries are highly susceptible to infections due to the destruction of th...
The impact of moral education on students' civic engagement in primary schools in Bauchi LGA, Bauchi State.
Background of the Study
Moral education is widely recognized as a catalyst for fostering civic engagement among young learners, especiall...
An Assessment of Hypertension Prevalence Among Older Adults in Edo State
Background of the Study
Hypertension, a leading risk factor for cardiovascular disease, is a significant p...
Exploring the Role of Speech Recognition Technology in Language Learning in Secondary Schools in Minna, Niger State
Background of the Study
Speech recognition technology enables computers and devices to understand and process human spee...
EFFECTS OF DRUGS ABUSE AMONG WOMEN OR PREGNANT MOTHERS
ABSTRACT
The study involved the investigation of the causes, effects and remedi of drug abuse among pregnant...
An appraisal of technological interventions in Igbo translation workflows in digital media
Background of the study
Digital media has transformed how languages are translated and disseminated, part...
