Abstract:

Abstract Wireless communication has become increasingly popular in the past two decades. The purpose of 5G is to provide higher bandwidth, lower latency, greater capacity and enhanced QoS (quality of service) than 4G. The 5G cellular network combines two technologies, SDN (software-defined network) and NFV (network function virtualization), for advanced management of the Network. This paper presents the main concepts related to RA (resource allocation) in a 5G network, which is the idea of dividing the network into multiple independent networks, each satisfying specific requirements while offering superior QoS. 5G network services can be classified into three verticals – (i). enhanced-Mobile Broadband (e-MBB), (ii). ultra-Reliable and Low Latency Communication (u-RLLC), and (iii). Massive-Machine Type Communications (m-MTC). Users require well-organized resource allocation and management. In this work, we implement a resource allocation module with Deep Reinforcement Learning (DRL) to estimate the Q-value function that utilizes a deep neural network, which learns from previous experience and adjusts to changing environments. The outcomes demonstrate that the implemented simulation reaches better in resource allocation compared to previous models, leading to lower latency and better throughput.

Keywords: