Dynamic Positioning and Energy-Efficient Path Planning for Disaster Scenarios in 5G-Assisted Multi-UAV Environments

Abstract

The integration of fifth-generation (5G) and unmanned aerial vehicle (UAV) technologies has become a promising solution for providing seamless communication in applications, such as disaster management, because of its bandwidth availability, cost-efficacy, and mobile nature. The state-of-the-art research in UAV communication concentrates on effective positioning and path planning. Despite this, these systems performed poorly due to a lack of dynamic control and external factors, such as weather. The solution presented in this paper addresses the problems listed above by using dynamic positioning and energy-efficient path planning for disaster scenarios in the 5G-assisted multi-UAV environments (Dynamic-UAV) to maximize the performance metrics. The lightweight gated recurrent unit (LGRU) is used for weather and event prediction to determine the disaster and non-disaster area and the context of the disaster. The density-based optics clustering (DBOC) algorithm is used to achieve reliability during communication with cluster IoT devices in disaster and non-disaster regions. The satellite determines the number of UAVs required and positions the UAVs using the dynamic positioning-based soft actor–critic (DPSAC) algorithm to achieve maximum throughput. Moreover, the UAVs’ path planning is performed using the shuffled shepherd optimization with dynamic-window method (SSO-DWM) to reduce energy consumption. The proposed approach is simulated using the NS 3.26 simulator and validated by comparing the results with existing techniques regarding the quality of service (QoS), reliability, and energy efficiency. Experimental results indicate that the proposed method achieved maximum throughput (1.59 bit/s), packet delivery ratio (0.88), coverage probability (0.82), number of collected packets (7109–5875), energy efficiency (1.544), minimum delay (16.4 ms–18.5 ms), and energy consumption (7.48 KJ).

DQN-Based Proactive Trajectory Planning of UAVs in Multi-Access Edge Computing

“…Due to the high probability of line of sight (LoS) linkages with GUs, UAVs are less impacted by channel limitations. With the help of these features, UAVs can contribute significantly to MEC systems and overcomes terrestrial server deployment deficiencies [14][15][16][17]. UAV-enabled edge computing is an obvious and viable option for future networks.…”