Computational offloading and resource allocation scheme for mobile edge computing underlaying uav using machine learning in 5g and beyond

Abstract

The growth of information and communication resources and technology over the last two three decades has driven the growth of wireless communication network devices to the next stage, which also a reason behind the growth of mobile users. The growth of mobile devices newlinecreates a massive amount of data traffic on the wireless network. According to [1], worldwide newlinewireless data traffic will roughly double from 2023 to 2030, offering a variety of difficulties newlinesuch as; processing and offloading, energy, latency, and throughput. newlineTo address such challenges, a novel computing technique called Mobile edge computing newline(MEC) is being developed. MEC has been presented as an effective strategy for future 6G newlinesystems, with the capability to provide a wide range of unique capabilities [2, 3]. MEC is newlinea computing approach that allows for data handling and storage at the network edge, closest newlineto end users. This minimizes latency and increases the speed of immediate data processing newlineapplications as well as services [4, 5]. MEC takes advantage of the features of the cloud, network, and edge to deliver an enhanced and scalable data processing structure. MEC, on the newlineother hand, enhances MD computing capabilities by offloading limited resource activities to newlinethe MEC server. As an outcome, considerable actions to decrease delay and energy usage are newlinerequired to achieve the full benefits of MEC [6, 7]. newlineAccording to research findings, the use of UAV-assisted wireless communications has increased significantly. Because UAVs are so flexible, wireless service providers may be capable newlineto offer movable MEC servers by developing a UAV-MEC system. Mobility-assisted technological developments may not only match user experience standards, but also the requirements newlineof a wide range of applications [8 10]. UAVs have been commonly used in many IoT situations, such as environmental monitoring, traffic surveillance, aerial photography, and so on, newlinebecause to their benefits of flexible deployment, quick reaction, and vast coverage.