Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/674
Title: Short Term Load Forecasting using Neural Network trained with Genetic Algorithm
Authors: Mishra, Sanjib
Patra, S K
Keywords: Short term load forecasting
Genetic Algorithm
Back Propagation
Issue Date: 2008
Citation: Proceedings of the National Conference on "Power Conversion, systems, drives, control technology conferences - 2008 Dindigul, Tamilnadu
Abstract: A computationally efficient artificial neural network for the purpose of short term load forecasting is proposed. The major drawback of feed forward neural networks such as a multilayer perceptron (MLP) or dynamic neural network such as Hopfield, Elman, MFLNN trained with back propagation algorithm is that it requires a large amount of computation for learning. We propose a three-layer multi layer neural network trained with genetic algorithm in which the need for computationally intensive back propagation is eliminated. The results of which are better than a MLP trained by back propagation algorithm, which require more number of hidden neurons. The whole project is carried out for Orissa Power Transmission Corporation Limited, taking into the load data of Orissa.
Description: Copyright for the paper belongs to the proceedings publisher
URI: http://hdl.handle.net/2080/674
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
smishra-conf.pdf266.78 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.