• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.3
• /
• pp.203-211
• /
• 1999

This paper presents a new approach on genetic on genetic algorithm to economic dispatch problem for valve point discontinuities. Proposed approach in this paper on genetic algorithms improves the performance to solve economic dispatch problem for valve point discontivuities through improved death penalty method, generation-apart elitism, atavism and sexual selection with sexual distinction. Numerical results on a test system consisting of 13 thermal units show that the proposed approach is faster, more robust and powerful than conventional genetic algorithms.

• Proceedings of the KIEE Conference
• /
• 1997.07c
• /
• pp.1106-1108
• /
• 1997

This paper presents a new approach on genetic algorithms to economic dispatch problem for valve point discontinuities. Proposed approach in this paper on genetic algorithms improves the performance to solve economic dispatch problem for valve point discontinuities through combination in penalty function with death penalty, generation-apart elitism, atavism and heuristic crossover. Numerical results on an actual utility system consisted of 13 thermal units show that the proposed approach is faster and robuster than classical genetic algorithm.

• Proceedings of the KIEE Conference
• /
• 1996.11a
• /
• pp.172-174
• /
• 1996

This paper presents a new approach on genetic algorithms to economic dispatch problem for valve point discontinuities. Although it has been already shown that genetic algorithm was more powerful to economic dispatch problem for valve point discontinuities than other optimization algorithms, proposed approach in this paper on genetic algorithms improves the performance to solve economic dispatch problem for valve point discontinuities through combination in penalty function with death penalty, generation-apart elitism and heuristic crossover. Numerical results on an actural utility system consisted of 13 thermal units show that the proposed approach is faster and robuster than the classical genetic algorithm.