Various island-based parallel genetic algorithms for the 2-page drawing problem

2006-09-25T13:40:25Z (GMT) by Hongmei He Ondrej Sykora Ana Salagean
Genetic algorithms have been applied to solve the 2-page drawing problem successfully, but they work with one global population, so the search time and space are limited. Parallelization provides an attractive prospect in improving the efficiency and solution quality of genetic algorithms. One of the most popular tools for parallel computing is Message Passing Interface (MPI). In this paper, we present four island models of Parallel Genetic Algorithms with MPI: island models with linear, grid, random graph topologies, and island model with periodical synchronisation. We compare their efficiency and quality of solutions for the 2-page drawing problem on a variety of graphs.