In the evolving landscape of 5G networks, effective admission control plays a crucial role in max... more In the evolving landscape of 5G networks, effective admission control plays a crucial role in maximizing network operator revenue and ensuring Quality of Service (QoS) and Quality of Experience (QoE) for diverse vertical applications. This paper presents a modified Deep Reinforcement Learning (DRL) approach for admission control in 5G networks, addressing the limitations of existing Reinforcement Learning (RL) and DRL-based methods. Our proposed methodology incorporates a custom state space, action space, and a modified Deep Q-Network (DQN) algorithm to balance the acceptance of different network slice types while considering QoS/QoE requirements and available network resources. Using a custom-built Python-based event-driven simulator, we demonstrate that our modified DRL-based admission control approach significantly outperforms existing algorithms in terms of profit and acceptance ratio. The results reveal a 9% increase in profit and improved acceptance ratios compared to state-of-the-art algorithms, attributed to the enhanced learning capability and better action selection provided by our modified DQN algorithm. This study covers the way for further research and development of advanced DRL-based admission control techniques for 5G/6G networks, ensuring optimal resource utilization and meeting the performance demands of emerging vertical applications.
Biometrics systems have come into existence from the birth of a human being in different forms, a... more Biometrics systems have come into existence from the birth of a human being in different forms, and measure physical characteristics. It differs from man to man and it provides a measurement of physical characteristics. The system speaks about all psychological characteristics considering the permanent identification of each and every person. Actually, these physical characteristics of a human being are permanent ones and do not change throughout life. This paper presents various biometrics techniques in the field of security and identification purposes. Each method covers a number of advantages in comparison to others. Although there are various biometric methods available, still there is a need to compare these methods in order to provide the best and efficient method. Index terms-Biometrics system, Technique, Psychological.
Mathematical Statistician and Engineering Applications, 2022
Wireless communication system growth has been changing rapidly. The main goal of the paper is a d... more Wireless communication system growth has been changing rapidly. The main goal of the paper is a deep study on 5 th Generation Wireless Technology, this is also called Real wireless world. 5G is a new type of networks which is design to connect almost all things together as well as objects, devices, and technologies. The key aim of the fifthgeneration wireless network is to have fast speeds, less latency, base station's (BSs) efficiency and high Quality of Service (QoS) for consumers as compared with the fourth-generation networks. To deal with technologies and connectivity in the form of machines, objects and devices, the broadband data usage increased at superior rate. This paper briefly discusses on the architecture and applications of 5G. Fifthgeneration provides more features than fourth-generation. This also focuses on comparison of fourth generation and fifth generation technology, in relative to their latency, speed, frequency, core network, and design of network.
Wireless communication has become increasingly popular in the past two decades. The purpose of 5G... more 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.
Uploads
Papers by Amanpreet Kaur