Improved Deep Reinforcement Learning Based Resource Allocation for 5G and Beyond Networks in Edge Computing Environment

Energy-efficient Resource Management (RM) for 5G and beyond networks has become challenging because of increasing Small Cells (SCs) densities and high Quality of Experience (QoE) requirements of business users. However, demands generated through plethora of innovations and concurrent IT services need high quality of service and quality of experience level overwhelm the resource available in 5G and Beyond scenarios. In this manuscript, developed the novel solution based on improved Deep Reinforcement Learning (DRL) which considers maximizing of overall value of data delivered to end users as coherent and comprehensive criterion of resource management. The developed algorithm has ability of learning efficient automatic resource management increasing total value delivered to end-users. The developed resource allocation and optimization technique addresses the changing user QoE requirements and minimizes energy consumption policies which allocates service metrics for in 5G networks. Based on simulations, it is clear that the developed method is highly effective and minimizes energy consumption to provide the QoE for users compared to conventional methods.