Wireless Mesh Network (WMNs) offer a cost-effective communication, but finding the optimal mesh router allocation is an NP-hard problem. To deal with this issue, in our previous work, we implemented a hybrid intelligent system based on Particle Swarm Optimization (PSO), Hill Climbing (HC), and a Distributed Genetic Algorithm (DGA). In this paper, we implement in Genetic Algorithm of our simulation system four crossover methods (UNDX, BLX \(\alpha \) , SPX, psBLX) and two mutation methods (Boundary Mutation and Uniform Mutation). We carry out a comparison study for these methods considering Subway distribution of mesh clients, Constriction Method (CM), and a middle scale WMN. The simulation results show that the combination of psBLX with Boundary Mutation achieves the best performance.