optimal k-medoid machine learning method for 3d placement of unmanned aerial vehicles in emergency or disaster areas

The use of unmanned aerial vehicles (uavs) is a promising approach to increase the agility and flexibility of future wireless networks. uavs are considered aerial bss that can increase the coverage or capacity of the network by moving the supply toward the demand if necessary. in emergency scenarios where many ground base stations are not available, mobile base stations based on uavs can provide a good solution to support ground terminals in the affected area thanks to their flexibility and affordability. in this paper, using the k-medoid machine learning method for clustering, the optimal 3d placement of uavs for various network objectives such as minimizing the number of uavs, minimizing transmission power, and maximizing the number of covered users in a network wireless is found in the affected area. finally, the numerical results show how the proposed algorithm improves the performance of previous algorithms in terms of maximum coverage and capacity.