A deterministic annular crossover genetic algorithm optimisation for the unit commitment problem

作者:

Highlights:

摘要

One of the disadvantages of traditional genetic algorithms is premature convergence because the selection operator depends on the quality of the individual, with the result that the genetic information of the best individuals tends to dominate the characteristics of the population. Furthermore, when the representation of the chromosome is linear, the crossover is sensitive to the encoding or depends on the gene position. The ends of this type of chromosome have only a very low probability of changing by mutation. In this work a genetic algorithm is applied to the unit commitment problem using a deterministic selection operator, where all the individuals of the population are selected as parents according to an established strategy, and an annular crossover operator where the chromosome is in the shape of a ring. The results obtained show that, with the application of the proposed operators to the unit commitment problem, better convergences and solutions are obtained than with the application of traditional genetic operators.

论文关键词:Genetic algorithm,Unit commitment,Deterministic selection,Annular crossover

论文评审过程:Available online 18 November 2010.

论文官网地址:https://doi.org/10.1016/j.eswa.2010.11.089