DEVELOPMENT OF NEURAL NETWORK BASED TECHNIQUES FOR POWER SYSTEM TRANSFER CAPABILITY CALCULATIONS AND RELIABILITY EVALUATION

منو

" DEVELOPMENT OF NEURAL NETWORK BASED TECHNIQUES FOR POWER SYSTEM TRANSFER CAPABILITY CALCULATIONS AND RELIABILITY EVALUATION "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	151416
Doc. No	:	ET23208
Main Entry	:	XIAOCHUAN LUO
Title Proper	:	DEVELOPMENT OF NEURAL NETWORK BASED TECHNIQUES FOR POWER SYSTEM TRANSFER CAPABILITY CALCULATIONS AND RELIABILITY EVALUATION
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Today transmission networks are used in a manner and to an extent notcontemplated when they were planned and designed. Transfer capability, acting as anindictor of the capability of a transmission network to reliably move electric power fromone area of supply to another of need, is used by system planners to indicate a system'sstrength and by system operators to determine current ability to transfer power. On theother hand, with the system growing in size and complexity, power system reliability isbecoming an increasingly important and complex issue. New techniques need to bedeveloped for power system transfer capability studies and power system reliabilityevaluation.This dissertation presents neural network based techniques for power systemtransfer capability studies and power system reliability evaluation. Multi-Layer Feed-Forward Neural Network. which has strong ability to model complex nonlinearrelationships between inputs and outputs, is used to develop the techniques for transfercapability studies. Two neural network based techniques are developed to speed up theMonte Carlo simulation for loss of load probability cdculation. The first one is based onthe Self-organizing Map, which has the ability to project input signals nonlinearly froma high-dimensional space to a 2-dimensional space while maintaining their originaltopological relationship. The other is based on the Learning Vector Quantization (LVQ),which has the strong classification ability that divides the data space into quantizationregions whose borders are hyper-planes.....-....,....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL46444.pdf
Title and statement of responsibility and	:	DEVELOPMENT OF NEURAL NETWORK BASED TECHNIQUES FOR POWER SYSTEM TRANSFER CAPABILITY CALCULATIONS AND RELIABILITY EVALUATION [Thesis]