Neural network based energy management for renewable energy sources

مرکز و کتابخانه مطالعات اسلامی به زبان های اروپایی

منو

" Neural network based energy management for renewable energy sources "
Samson Gebrewahid El-Sharkh, Mohamed Y.

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	803752
Doc. No	:	TL48553
Call number	:	‭1748045972;‮ ‬1604767‬
Main Entry	:	Lamey, Emeel S.
Title & Author	:	Neural network based energy management for renewable energy sources\ Samson GebrewahidEl-Sharkh, Mohamed Y.
College	:	University of South Alabama
Date	:	2015
Degree	:	M.S.E.E.
field of study	:	Electrical and Computer Engineering
student score	:	2015
Page No	:	74
Note	:	Committee members: El-Sharkh, Mohamed Y.; Islam, Samantha; Lazarou, Georgios
Note	:	Place of publication: United States, Ann Arbor; ISBN=978-1-339-28799-7
Abstract	:	As the technology and the population growth, the demand for energy also growth. However, energy resources are scarce. Thus, a smart energy management methodology is essential to prevent wasting a valuable portion of energy while minimizing the operational cost. In this thesis, two types of artificial neural network (ANN) based energy management techniques are developed to manage a proton exchange membrane fuel cell (PEMFC) power plant system while considering the cogenerated thermal energy and hydrogen production and storage. The feedforward and the dynamic neural networks produce the near optimal management decision in a very short time compared to other known management techniques such as evolutionary programming (EP). Comparison of the performance of the ANN with the EP indicates that the ANN produces the near optimal management decision in a fraction of a second while EP takes 3 to 4 hours. Based on the test results, a conclusion can be made that ANN is an excellent online management tool for the PEMFC system or any other renewable energy source.
Subject	:	Electrical engineering
Descriptor	:	Applied sciences;Artificial neural network - ann;Energy management;Evolutionary programming;Neural network based energy management;Neural network based energy management for renewable energy sources;Renewable energy sources
Added Entry	:	El-Sharkh, Mohamed Y.
Added Entry	:	Electrical and Computer EngineeringUniversity of South Alabama