A Simple Reinforcement Learning Mechanism for Resource Allocation in LTE-A Networks with Markov Decision Process and Q-Learning

Resource allocation is still a difficult issue to deal with in wireless networks. The unstable channel condition and traffic demand for Quality of Service (QoS) raise some barriers that interfere with the process. It is significant that an optimal policy takes into account some resources available to each traffic class while considering the spectral efficiency and other related channel issues. Reinforcement learning is a dynamic and effective method to support the accomplishment of resource allocation properly maintaining QoS levels for applications. The technique can track the system state as feedback to enhance the performance of a given task. Herein, it is proposed a simple reinforcement learning mechanism introduced in LTE-A networks and aimed to choose and limit the number of resources allocated for each traffic class, regarding the QoS Class Identifier (QCI), at each Transmission Time Interval (TTI) along the scheduling procedure. The proposed mechanism implements a Markov Decision Process (MDP) solved by the Q-Learning algorithm to find an optimal action-state decision policy. The results obtained from simulation exhibit good performance, especially for the real-time Video application.