Long runtimes in real-world genetic algorithms
The example programs we’ve explored so far, while addressing practical problems, were intentionally designed to converge quickly to a reasonable solution. However, in the context of real-world applications, the use of genetic algorithms often proves to be highly time-consuming due to the way they operate – exploring the solution space by considering a diverse set of potential solutions. The main factors affecting the running time of a typical genetic algorithm are as follows:
- The number of generations: Genetic algorithms operate through a series of generations, each involving the evaluation, selection, and manipulation of the population.
- The population size: Genetic algorithms maintain a population of potential solutions; more complex problems typically require larger populations. This increases the number of individuals that need evaluation, selection, and manipulation in each generation.
- Fitness evaluation...
