No Detail Found!

Neuro-genetic hybrid approach for the solution of non-convex economic dispatch problem.

Author(s)
Tahir Nadeem Malik Department of Electrical Engineering, University of Engineering and Technology, Taxila, Pakistan
Azzam-Ul-Asar Department of Electrical Engineering, NWFP, University of Engineering & Technology, Peshawar, Pakistan
Abstract
ED (Economic Dispatch) is non-convex constrained optimization problem, and is used for both on line and off line studies in power system operation. Conventionally, it is solved as convex problem using optimization techniques by approximating generator input/output characteristic curves of monotonically increasing nature thus resulting in an inaccurate dispatch. The GA (Genetic Algorithm) has been used for the solution of this problem owing to its inherent ability to address the convex and non-convex problems equally. This approach brings the solution to the global minimum region of search space in a short time and then takes longer time to converge to near optimal results. GA based hybrid approaches are used to fine tune the near optimal results produced by Ga. This paper proposes NGH (Neuro Genetic Hybrid) approach to solve the economic dispatch with valve point effect. The proposed approach combines the GA with the ANN (Artificial Neural Network) using SI (Swarm Intelligence) learning rule. The GA acts as a global optimizer and the neural network fine tunes the GA results to the desired targets. Three machines standard test system has been tested for validation of the approach. Comparing the results with GA and NGH model based on back-propagation learning, the proposed approach gives contrast improvements showing the promise of the approach.
Publication Details
Page(s) 289-302
DOI DOI not available
Published Journal: Mehran University Research Journal of Engineering and Technology, Volume: 28, Issue: 3, Year: 2009

Request the full text from PASTIC

0

Citations

0

Downloads

40

Views