Hybrid Simulated Annealing: An Efficient Optimization Technique

Abstract

Genetic Algorithm falls under the category of evolutionary algorithm that follows the principles of natural selection and genetics, where the best adapted individuals in a population are more likely to survive and reproduce, passing on their advantageous traits to their offsprings. Crossover is a crucial operator in genetic algorithms as it allows the genetic material of two or more individuals in the population to combine and create new individuals. Optimizing it can potentially lead to better solutions and faster convergence of the genetic algorithm. The proposed crossover operator gradually changes the alpha value as the search proceeds, similar to the temperature in simulated annealing. The performance of the proposed crossover operator is compared with the simple arithmetic crossover operator. The experiments are conducted using Python and results show that the proposed crossover operator outperforms the simple arithmetic crossover operator. This paper also emphasizes the importance of optimizing genetic operators, particularly crossover operators, to improve the overall performance of genetic algorithms.