A hierarchical genetic algorithm with search space partitioning scheme

A new search technique of genetic algorithm (GA) called hierarchical genetic algorithm (HGA) has been proposed for optimizing various functions in Rⁿ space. Initially the entire search space is partitioned into a number of subspaces depending on the dimensionality of the search space. The HGA processes are then distributed. The algorithm thus independently runs in each subspace with the advancement of the search from one hypercube to a neighboring hypercube surrounding the current best individual depending on the convergence status of the population and the solution obtained so far in the same subspace. The search process passes through variable resolution (coarse-to-fine) search space as the hypercube dimension is modified with the shift of the search to the neighboring hypercube. The performance of HGA and conventional GA (CGA) has been evaluated for different function optimization problems.