Golden Tortoise Beetle Optimized Deep Learning Framework for Resource Allocation in 6G Networks
International journal of intelligent engineering and systems · 2024
6G(Sixth-generation) technology is the next generation of mobile wireless communication networks, designed to deliver more inclusive and long-lasting wireless connectivity.Great security, secrecy, and privacy should be the fundamental qualities of 6G.However, 6G faces challenges in overcoming limitations like congested networks that lead to poor Quality of experience (QoE) and high energy consumption for continuous operation.In this work, a novel 6G Resource Allocation Detection USing Deep Learning (6G-RADIUS) technique has been proposed to allocate resources and enhance QoE efficiency and energy efficiency in a 6G network.Data from the user's equipment is sent to the base station to begin the procedure.The Golden Tortoise Beetle Optimizer (GTBO) assigns subbands, potentially choosing those with the most important information or strongest signals.The resource allocation method is carried out using a Multi-Head Attention-based Bidirectional Gated Recurrent Unit (MHA-BiGRU) model.The output of the MHA-BiGRU model is supplied into the BaseBand Unit (BBU) pool, which regulates and distributes resources among many BBU.The proposed techniques' performance is assessed using QoE, resource utilization, energy efficiency, Mean Square Error (MSE), Cumulative Distribution Function (CDF), and spectral efficiency.The proposed method has a higher resource utilization factor of 8.16%, 6.12%, and 3.06% compared to existing QJEEO, EKF and SDWN techniques, respectively.