Grey-Wolf Optimization-based Efficient Data Dissemination for UAVs in Critical Scenarios

Unmanned Aerial Vehicles (UAVs) are experiencing a significant surge in their applications across various sectors, including healthcare, surveillance, agriculture, and military operations. This widespread adoption offers manifold advantages, such as effortless mobility, reduced human intervention, and the ability to cover vast areas efficiently. Emerging fields, such as the Internet of Things (IoT), Artificial Intelligence (AI), and cloud computing, have boosted its productivity. But UAVs are resource and energy-constrained devices, so their performance (regarding the transmission time and throughput) gets degraded as the number of service requests increases. Most of the existing solutions use AI, game theoretic models, and edge computing to improve the UAV’s network latency. However, their solutions are not optimized to reduce the UAV’s transmission time and enhance the network throughput. Inspired by the aforementioned challenge, the proposed work utilizes a bio-inspired algorithm, i.e., Grey wolf Optimization (GWO), in UAV communication. For that, a signal-to-noise-plus-interference ratio (SINR)-based fitness function is formulated for all UAVs participating in mission-critical applications. Then, based on the GWO exploration phase, it provides optimal UAVs iteratively that can send mission-critical data in a minimum time. Further, a 5G network is laid out between the UAVs and UAVs to the ground control station, improving overall network throughput and latency. The proposed system is evaluated using various and diverse performance parameters, such as network throughput, performance of fitness function with time, network latency, and GWO population analysis.