.png){kind=icon}
.png){kind=icon}
Return
Evolutionary Coverage Optimization for a Self-Organizing UAV-Based Wireless Communication System
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2021.3121905.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Self-organized wireless networks based on unmanned aerial vehicles (UAVs) are receiving increasing attention due to their flexible deployment opportunities. Typically, UAVs are used as supplementary access points to existing ground infrastructure to extend network coverage and capacity. Therefore, finding the optimal position for each UAV is a crucial task that can be resolved by multiobjective optimization. In this paper, a self-organizing UAV swarm model is introduced as an evolutionary type of heuristic that can be adjusted in real time based on the network's key performance indicators (KPIs). The exogenous dynamics of the wireless communication system are reflected by an end-user mobility model based on Ornstein-Uhlenbeck processes. To achieve versatility in the positioning of UAVs, a model of virtual forces is adopted to enable control of the movement of each UAV via a collection of persistent and mutable parameters of the system. Evolution is controlled by eleven strategic versions of parametric mutations, including a neutral benchmark process. The simulation results reveal that the suggested solution allows for a substantial increase in the KPI efficiency metrics relative to those of the nonmutated system. The results also addressed the presence of the Pareto front, where it is not possible to improve the selected KPIs without negatively affecting others. While existing research that focuses on evolutionary methods usually considers offline approaches, this work uses an online evolutionary approach that is able to solve the presented problem by taking the dynamic nature of the environment into account.
Keywords:
Unmanned aerial vehicles
Wireless communication
Trajectory
Dynamics
Optimization
Task analysis
Stability analysis
UAV swarm
virtual forces
parametric evolution
self-organization
wireless communication
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
View more organizations