Unmanned Aerial Vehicle Localization for Device-to-Device Communication in Fifth Generation Networks using Modified Various Search Optimization (MVSO)

Abstract

The evolution of 5G networks and growing demand in high capacity and low latency communication has spurred the interest to implement unmanned aerial vehicles (UAVs) as aerial base stations to facilitate device to device (D2D) communications. Nevertheless, the problem of effective UAV localization is complicated, particularly in dynamic and high-density environments because the distribution of users and the conditions of a channel vary rapidly. The given study puts forward the Modified Various Search Optimization (MVSO) algorithm, composed of adaptive inertia weighting and chaotic mutation operators, to enhance the UAV positioning, coverage, and the quality of links as well as lower the expended energy. MATLAB simulated the algorithm and compared it to Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) based on user densities and UAVs at multiple densities. Experiments prove that MVSO performs better in terms of up to 19.2% on the coverage ratio, 20% on energy consumption, and 10 11 dB on signal to noise ratio (SNR) and convergence speeds are 25 35 faster than baseline approaches. Such increment in gains is explained by the ability of MVSO to flexibly balance between global exploration/local exploitation in a way that allows speed and energy-efficient how to respond to network dynamics. Its results demonstrate the feasibility of MVSO in terms of real-time deployment of UAVs fleets in an urban 5G D2D network, considering planned densification to support communication as well as in case of emergency.