A Hybrid Intelligent Simulation System for Node Placement in WMNs Considering Load Balancing: A Comparison Study for Exponential and Normal Distribution of Mesh Clients Seiji Ohara 1(B ) , Heidi Durresi 4 , Admir Barolli 2 , Shinji Sakamoto 3 , and Leonard Barolli 4 1 Graduate School of Engineering, Fukuoka Institute of Technology, 3-30-1 Wajiro-Higashi, Higashi-Ku, Fukuoka 811-0295, Japan seiji.ohara.19@gmail.com 2 Department of Information Technology, Aleksander Moisiu University of Durres, L.1, Rruga e Currilave, Durres, Albania admir.barolli@gmail.com 3 Department of Computer and Information Science, Seikei University, 3-3-1 Kichijoji-Kitamachi, Musashino-shi, Tokyo 180-8633, Japan shinji.sakamoto@ieee.org 4 Department of Information and Communication Engineering, Fukuoka Institute of Technology, 3-30-1 Wajiro-Higashi, Higashi-Ku, Fukuoka 811-0295, Japan hdurresi@gmail.com , barolli@fit.ac.jp Abstract. Wireless Mesh Networks (WMNs) are becoming an impor- tant networking infrastructure because it has many advantages such as low cost and increased high-speed wireless Internet connectivity. In our previous work, we implemented a Particle Swarm Optimization (PSO) based simulation system, called WMN-PSO, and a simulation system based on Genetic Algorithm (GA), called WMN-GA, for solving node placement problem in WMNs. Then, we implemented a hybrid simula- tion system based on PSO and distributed GA (DGA), called WMN- PSODGA. Moreover, we added in the fitness function a new parameter for the load balancing of the mesh routers called NCMCpR (Number of Covered Mesh Clients per Router). In this paper, we consider Expo- nential and Normal distributions of mesh clients and carry out a com- parison study. The simulation results show that the performance of the Exponential and Normal distribution was improved by considering load balancing when using WMN-PSODGA. Moreover, for the same num- ber of mesh clients, the Normal distribution has better behavior than the Exponential distribution, because all mesh clients are covered by a smaller number of mesh routers. c  Springer Nature Switzerland AG 2020 L. Barolli et al. (Eds.): BWCCA 2019, LNNS 97, pp. 555–569, 2020. https://doi.org/10.1007/978-3-030-33506-9_50