An empirical comparison of three novel genetic algorithms

Genetic algorithms have been extensively used in different domains as a type of robust optimization method. They have a much better chance of achieving global optima than conventional gradient-based methods which usually converge to local sub-optima. However, convergence speeds of genetic algorithms are often not good enough at their current stage. For this reason, improving the existing algorithms becomes a very important aspect of accelerating the development of the algorithms. Three improved strategies for genetic algorithms are proposed based on Holland's simple genetic algorithm (SGA). The three resultant improved models are studied empirically and compared, in feasibility and performance evaluation, with a set of artificial test functions which are usually used as performance benchmarks for genetic algorithms. The simulation results demonstrate that the three proposed strategies can significantly improve the SGA.