Currently, cellular networks are one of the essential communication methods for people. Providing proper coverage for the users and also offering high-quality services to them are two of the most important issues of concern in cellular networks. The fifth-generation cellular communication networks can provide higher data transmission rates, which lead to a higher quality of service but this higher rate has let to reduced antenna coverage in these networks. Besides this, natural and unnatural events in the environment can also affect the coverage of users in the cellular network. One way to resolve this issue is by using drones as cellular antennas. The most important factor in providing good coverage and high-quality service for users is the optimal placement of antennas. In this article, the problem of finding the appropriate locations of drone base stations (DBSs) is modeled as a P-median optimization problem, where P is the number of required antennas to cover the users. We have used a fuzzy clustering algorithm to define a set of specified candidate points that are required to select the locations of DBSs in the P-median model. The optimal value of P was obtained using the bisection algorithm. Finally, the optimal positions of DBSs have been determined by solving the optimization problem. According to the results, in the case of a proper selection of fuzzy clustering parameters, better results will be obtained in comparison to the results of other approaches.

Keywords