Efficient Communication for Extremely Large-Scale MIMO Systems Networks: Integrating Firefly Optimization and Machine Learning

This paper proposes a novel approach for tuning the parameters of 6th generation (6G) extremely large-scale MIMO (Multiple Input Multiple Output) systems using the Firefly optimization algorithm. The main objective is to achieve accurate estimation of the hybrid field in the MIMO system. The proposed method optimizes MIMO system parameters by minimizing the cost function through a hybrid pre-coding and combining technique. This optimization problem is formulated as a nonlinear programming problem and solved using the Firefly algorithm. Experimental results demonstrate that the proposed approach provides accurate hybrid field estimation with improved system performance compared to existing state-of-the-art methods. The Firefly optimization algorithm proves to be an efficient and effective method for tuning 6G MIMO system parameters, with potential applications in future wireless communication systems. In addition to the Firefly optimization algorithm, this paper introduces a complementary machine learning-assisted resource allocation strategy to optimize network resource utilization. By leveraging machine learning algorithms, dynamic resource allocation based on real-time network conditions is ensured, enhancing overall system performance. The integration of the Firefly optimization algorithm for parameter tuning and machine learning-assisted resource allocation aims to achieve holistic optimization in 6G networks. Experimental results demonstrate that this integrated approach not only refines parameter tuning but also dynamically adapts resource allocation, leading to superior system efficiency and throughput compared to conventional methods. This comprehensive strategy addresses the evolving demands of future wireless communication systems. Results showed that using a sparsity value of 8, with 600 beams and 300 pilots, minimizes the mean square error of estimation to less than -13 dB