Enhancing Energy Efficiency in UAV Cognitive Radio Networks: A Machine Learning-Based Optimization Approach

Abstract

The unmanned aerial vehicle has gained much popularity in these years due to the broad utilization in performing various tasks that range from monitoring, collecting data, and surveillance. However, all these are limited by the battery life of UAVs, which further determines the fly distance and time. Different methods have, therefore, been suggested for the optimization of energy for UAVs. One approach that can be employed to enable energy efficiency in UAVs with dynamic access to available spectrum resources is by considering cognitive radio networks. This article presents the study of UAVs cognitive radio networks for energy efficiency optimization. Since UAVs can offer effective and flexible communication services, their usage in cognitive radio networks has attracted a lot of attention. However, owing to the limited energy resources of UAVs, dependable and sustainable communication is difficult to achieve. This work may provide great insight into the design and optimization of UAV-based cognitive radio networks toward reliable and sustainable communication services. In this paper, we present an energy-efficient optimization strategy taking into consideration the network dynamic structure and different energy usages for the UAVs. The following is proposed in this paper as an algorithm that uses ML techniques for the estimation of energy consumption for UAVs, which then tunes the adjustment of the routing pathways. Simulation results show that the proposed method enhances energy efficiency with constant network performance.