Levenberg Marquardt algorithm based economic load dispatch

Author

Chaturvedi, Krishna Teerth ; Srivastava, Laxmi ; Pandit, Manjaree

Author_Institution

Dept. of Electr. Eng., MITS, Gwalior

fYear

0

fDate

0-0 0

Abstract

This paper presents Levenberg Marquardt algorithm based multi-layer feed-forward neural network for economic load dispatch, which is trained to provide the optimal value of lambda and economic generation allocation on all the committed generating units for a given power demand. Since the training of the ANN is extremely fast, it may be used for on-line implementation at energy control centre. Test results of two sample systems with 3 generating units and 6 generating units are given to illustrate the effectiveness of the proposed method

Keywords

feedforward neural nets; iterative methods; learning (artificial intelligence); multilayer perceptrons; power engineering computing; power generation dispatch; power generation economics; ANN training; Levenberg Marquardt algorithm; economic generation allocation; economic load dispatch; energy control centre; generating unit; lambda iteration method; multi layer perceptron network; multi-layer feed-forward neural network; power demand; Artificial neural networks; Feedforward neural networks; Feedforward systems; Multi-layer neural network; Neural networks; Power demand; Power generation; Power generation economics; Power system economics; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Power India Conference, 2006 IEEE

Conference_Location

New Delhi

Print_ISBN

0-7803-9525-5

Type

conf

DOI

10.1109/POWERI.2006.1632615

Filename

1632615