Transit Archimedes optimization algorithm enabled deep learning for power and resource allocation NOMA technique for 5G cellular systems

Abstract

5G communication technology is projected to provide extreme data rates that surpass user exposure, low power consumption, and greater short latency. A diverged multi-layer approach is implemented by cellular networks with macro-cells and various schemes of small cells to aid users with diverged quality of service (QoS) that affects more research by employing intervention management in 5G networks. Along with the escalating requirement for cellular services and adequate resources to furnish it and capable of handling the network traffic has become a resource distribution concern. The major concern is to facilitate the network jam having QoS. To overcome this concern, a potent investigation is developed for power and resource allocation, which is named as transit Archimedes optimization algorithm (TAOA). First, the non-orthogonal multiple access (NOMA) system module is created with the aid of power consumption and energy modules. Then, user clustering (UC) is performed to gather the NOMA users into single or multiple clusters utilizing deep embedded clustering (DEC) in accordance with user grouping parameters, like signal-to-interference and noise ratio (SINR), position, initial power, and channel gain. After that, sub-channel assignment and power allocation are done by the back propagation neural network (BPNN). Lastly, the presented module TAOA is performed to update the network parameters of BPNN, where TAOA is developed by the fusion of transit search (TS) optimization and Archimedes optimization algorithm (AOA). The analytic metrics utilized for finding the performance of the proposed TAOA-BPNN are achievable rate, energy efficiency, sum rate, and throughput. The experimental results demonstrate that the proposed method offers good performance with the achievable rate of 3.273 Mbits, energy efficiency of 0.00000000473 J, sum rate of 0.00000248 s, and throughput of 0.00000346 Mbps.