Metrics
1 File views/ downloads
41 Record Views
Thesis
DEVELOPMENT OF SYSTEM-CENTRIC CONTROL APPROACHES USING NEURAL NETWORKS FOR POWER SYSTEM STABILIZATION
University of West Florida
Master of Science (MS), University of West Florida
2010
Abstract
In this research, an intelligent approach based on system-centric controller to develop a power system stabilizer is proposed. This thesis designs and develops a system-centric control algorithm based on supervisory loop principle. It combines a Dual Heuristic Programming (DHP) controller and an adaptive controller implemented as a Model Reference Adaptive Controller (MRAC), to perform a hybrid control operation. A neuro-control identifier is used to approximate the nonlinear plant function and the MRAC control adapts when plant parametric set changes. A feed-forward Neural Network (NN) identifier is used to predict system response to control values and those values are adjusted to obtain improved system response. The DHP is trained offline with extensive test data and is also adjusted online. Moreover, an online neural network produces a plant functional approximation. The theoretical results are validated by conducting simulation studies on a single machine infinite bus system for electric generator control and testing on a five generator, eight bus, two area multi-machine simulation.
Details
- Title
- DEVELOPMENT OF SYSTEM-CENTRIC CONTROL APPROACHES USING NEURAL NETWORKS FOR POWER SYSTEM STABILIZATION
- Resource Type
- Thesis
- Publisher
- University of West Florida
- Format
- text
- Copyright
- http://rightsstatements.org/vocab/InC-EDU/1.0/
- Identifiers
- 99380090744706600
- Academic Unit
- Computer Science
- Language
- English
- Awarding Institution
- University of West Florida; Master of Science (MS)
- Theses and Dissertations
- Master of Science (MS), University of West Florida