Efficient Framework for Analysis of 5G Network Slicing Optimization Using Advanced Deep Learning Techniques

Abstract

Network slicing makes it possible to design customized networks that may accommodate various use cases. Each
slice can be customized to meet certain needs regarding security, mobility, latency, bandwidth, and dependability.
Unmanned aerial vehicle (UAV)-based Mobile Edge computational (MEC) for 5G/6G networks is a new paradigm
that unites the capabilities of UAVs with the computing capability and low-latency connectivity of MEC. To facilitate
real-time processing of data, analysis, and provision of services on the network edge, it involves placing MEC servers
or alternative computing resources on board UAVs. The term "IIoT" denotes an industrial setting's network of
equipment, sensors, and systems connected to one another, communicating and sharing data in order to optimize
operational efficiency. We considered the Industrial Internet of Things (IIoT) scenario in our study, which links IoTs
to systems deployed in industrial manufacturing. We utilized to assign the resources to the slices to cater to the needs
of the 5G/6G slices. We even used UAV in our system model, which can hold base stations. We developed the disaster
situation in which outside connection of the ground base station has been disrupted, and using UAV-based mMTC,
we are establishing ground device connections via the outside devices in a bid to communicate and exchange data.
Another situation we used as UAV-enabled IIoT which is 5G/6G compliant and given that UAV are battery-scarce
devices we want to minimize the power usage and decrease the overall latency.