To Analyze the Maximized Energy Consumption by Algorithm Implementing Reinforcement Learning for Wireless Communication Technology

This paper presents the application of Reinforcement Learning algorithm for wireless communication technology with 5G. The 5G networks are characterized by multi-RAT (Radio Access Technology), heterogeneous networks, and ubiquitous coverage with the capability of self-organizing. To complete these objectives the application of Reinforcement Learning (RL) algorithms emerges as an excellent tool for optimizing network parameters. RL has been extensively used for optimization of power control, channel allocation and self-organizing network management in terms of some performance metrics like throughput, latency and quality of service. Moreover, through Q-learning approach network parameters can be optimized based on the successful or failed past actions. In this paper we focus on the methods and techniques used for the application of RL algorithms in wireless communication technology with 5G. We also analyze the existing challenges for successful implementation and deployment of such algorithms in 5G wireless networks. We conclude that despite the few challenges, RL algorithms because of the capability of high learning rate, low convergence time and better network performance can be successfully implemented in 5G wireless networks and will lead to a high quality and efficient modes of communication.