Joint Power and Delay Optimization Based Resource Allocation in Mu ‐ MIMO ‐ OFDM System Using Optimized Enhanced Elman Spiking Sparse Graph Neural Network

ABSTRACT In general, multi‐user multiple input multiple output orthogonal frequency division multiplexing (MU‐MIMO‐OFDM) allows multiple users to interconnect to a base station simultaneously using OFDM modulation and various antennas. However, managing resources like energy and minimizing delays is difficult, requiring smart solutions for smooth operation and better performance. Thus, a joint power and delay optimization based resource allocation using Enhanced Elman Spiking Sparse Graph Networks (EESS‐Gnet) with Humboldt Squid Optimization Algorithm (HSOA) and Reuse‐Based Online Joint Routing Scheduling Optimization (ROJR) (EESS‐GNet‐HSOA‐ROJR) in MU‐MIMO‐OFDM system is proposed in this manuscript. The proposed mechanism is performed in two stages that are power allocation and delay optimization. The goal of the first phase is to maximize throughput by allocating network resources to user equipments (UEs) based on transmission rate and power through an EESS‐Gnet. In order to reduce the loss function, HSOA is proposed to optimize the layers of EESS‐Gnet. In the second stage, ROJR is proposed for optimizing delay in the MU‐MIMO‐OFDM system. In the ROJR approach, the delay bound value is estimated by scheduling the transmission flows in the channel. The simulations of EESS‐GNet‐HSOA‐ROJR were conducted using MATLAB software. The suggested resource allocation algorithm's performance is assessed and contrasted with the current method of measuring different QoS metrics, including throughput, delay, fairness index, power consumption, spectrum capacity, and loss rate. Thus, the proposed approach has attained 26.46%, 23.09%, and 21.98% higher throughput, 29.78%, 26.86%, and 20.25% improved energy efficiency, 17.45%, 15.98%, and 14.02% lower processing time, and 27.89%, 34.87%, and 23.56% lower loss rate than other conventional approaches like PDO‐URA, PCO‐OBT, and ADNN‐ALSTM‐TRDA methods respectively.