Correlative Analysis of Deep Learning Techniques for Resource Allocation in 6G Mobile Networks

Abstract

The advent of sixth-generation (6G) mobile networks introduces unprecedented demands for ultra-low latency, terabit-per-second throughput, and dynamic resource allocation across heterogeneous services such as URLLC, eMBB, and mMTC. Traditional resource management approaches lack the adaptability and predictive intelligence required to operate under such conditions. This study proposes a comparative analysis of deep learning models—Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformer architectures—for intelligent resource allocation in 6G environments. Synthetic traffic patterns and benchmark datasets were used to emulate realistic 6G workloads, and models were evaluated using key performance metrics: accuracy, latency, throughput, energy efficiency, and fairness index. Simulations were conducted in Python using TensorFlow and PyTorch frameworks within SDN-based virtualized environments to replicate programmable 6G infrastructures. The proposed hybrid system, integrating CNN, RNN, and Transformer modules, achieved latency reduction of 38%, throughput improvement of 22%, energy savings of 26%, and fairness index gain of 18% compared to baseline models. These findings demonstrate the viability of deep learning for scalable, adaptive, and sustainable resource allocation in next-generation mobile networks. The study contributes a reproducible simulation framework, a performance benchmark across models, and a foundation for future research in federated learning, edge AI, and 6G deployments.