A Nouvelle Optimal Intelligent Learning (OIL) Framework for Secured Data Transmission and Link Quality Analysis in UAV Systems

Unmanned Aerial Vehicles (UAVs), also known as drones, have gained popularity recently and are being used for a number of reasons. They are common aerial vehicles that have connections with the internet and are capable of identifying themselves and interact with other devices by transmitting information through intelligent gadgets. UAVs are flying vehicles that can fly on their own or with manned operator assistance. For certain crucial applications, the security of UAVs and their wireless communications is crucial. This research presents a new framework, the Optimal Intelligent Learning (OIL) model that facilitates successful data exchange in UAV systems. In order to provide reliable data transfer with the least amount of information loss, a Deep Attention Predictor (DAP) methodology is applied in this instance to precisely detect the links between communication devices. The Heap Optimized Routing Model (HORM) is then used to determine plausible, reliable routes from the source to the destination. In addition, the Recurrent Auto Encoding based Assault Detector (RAE-AD) method looks at a number of characteristics, including travel duration, signal strength, packet size, delivery rate, connection quality, and data transmission priority, in order to identify malicious nodes inside the communication network. Moreover, three d’s such as delivery rate, detection rate, and latency-are used to compare and contrast the simulation results and conclusions of the suggested OIL framework.