RA-S2En-MQP: Multifactor Channel Quality Index Precoder for user scheduling and resource allocation in the MIMO system

Abstract

Massive multiple-input multiple-output (MIMO) is an emerging technology that has the potential to significantly increase the spectral efficiency of 5G networks and beyond. On the other hand, multi-user beamforming's spectral efficiency is severely hindered by highly correlated user channels. Because of this, the base station must schedule the suitable user group in each time and frequency resource block in order to maximize spectrum efficiency while adhering to the user fairness constraints. Hence, the resource scheduling problem for huge MIMO systems with the optimal solution is considered as the NP-hard problem. Consequently, this research proposes the Reinforcement Learning-based Actor-Critic and Selective Search Entrapment-enabled Multifactor Channel Quality Index Precoder (RA-S2En-MQP) framework for effective user scheduling and resource allocation in the MIMO system. The proposed model utilizes the Reinforcement Learning-based Actor-Critic (RL-AC) model to prioritize the users for optimal scheduling, which enables flexibility and mitigates risks during resource allocation. Specifically, the Selective Search entrapment-enabled Multifactor Channel Quality Index Precoder technique (S2EnO-MQP) simplifies resource allocation and ensures quality data transmission over the network with the application of the S2EnO algorithm. The proposed S2EnO algorithm combines the selection, searching, and entrapment behaviors to find the optimal solution and improves the spectral efficiency. Experimental results demonstrate that the proposed RA-S2En-MQP model significantly outperforms other existing techniques attaining a high through put of 93.83Mbps, Normalized system utility of 0.95,andhigh Quality of Experience (QoE) of 4.36.