Network planning problem typically involves large capital investment and can be formulated as an optimization problem where the objective is minimization of the first installed cost. We consider a passive optical network (PON) planning problem based on a residential area in Adana (Turkey). There are four possible primary node locations, twenty possible secondary node locations, and twenty-eight customers. We use genetic algorithm and mathematical modeling techniques to optimize the position of the primary and secondary nodes, I heir split levels and assigning customers to secondary nodes and secondary nodes to primary nodes under some constraints such as system's attenuations and technical characteristics of all the equipment. (C) 2011 Elsevier Inc. All rights reserved.