Intelligent Optimal Resource-Sharing Algorithm for 6G Network

Wireless communication technology has advanced significantly over the last fifteen years, with the adoption of fourth and fifth generation cellular systems. It has also provided a solid foundation for the sixth generation (6G). 6G will embed AI technologies into the network. It will enable the use of sophisticated deep learning technologies, hence increasing network efficiency and administration. This study introduces the HLEVRA (Horned Lizard Ensemble Voting Resource Allocation), a new allocation approach based on AI principles in 6G cellular systems. The study simulates a 6G user experience with multiple cells and uses the HLEVRA architecture to include important 6G capabilities in the NS3 network simulator. The framework uses a biologically organized optimization method called prey-prediction to adaptively estimate the resource's requirements. Predicted resources are given to users, which helps to accelerate data transmission and reduce system congestion. The framework's performance is assessed using important parameters such as throughput, data transfer rate, energy consumption, communication delay, and packet drop rate. For example, if 100 users connect to a single 6G base station, the proposed HLEVRA method will achieve 14.7 Gbps throughput, 840 Kbps data rate, 0.33 mW energy consumption, 20 ms communication time, and 12.5% packet drop rate. This data demonstrates the framework's capacity to efficiently address critical resource allocation concerns in 6G networks while providing significant certainty.