In the recent years , the deployment of smart devices that can autonomously connect to the internet has become a new dynamic area of research which is known as Machine-to-Machine (M2M) communications . M2M network is a network of machine type communication devices (MTD) which make smart decisions based on the transferred data over the internet . M2M communications is one of the key enablers of the Internet of Things (IoT) . The most viable option of implementing M2M communications is over cellular networks such as LTE/LTE-A . However , these networks have been mainly used to support Human-to-Human (H2H) communications , which is characterized by smaller number of connection requests and longer connection times . While in M2M networks it is possible that a huge part of MTDs try to connect simultaneously to transmit only a minimum amount of data . The random access channel of LTE/LTE-A suffers from congestion and overloading in the presence of the thousands of MTDs . Therefore , one of the key challenges is the need to enhance the operation of RACH of LTE/LTE-A . The different alternatives are provided to overcome the congestion during the random access procedure . The most of the solutions are based on the base station operation and therefore they need to change the cellular network standards . In this thesis , we propose a distributed solution based on reinforcement learning which extends the uplink resources for random access procedure along the time to overcome the congestion on RACH . Different from the centralized methods , in our distributed methods the MTDs autonomously and independently learn their optimal actions to minimize the collisions over RACH . We compare the performance of the proposed method with the baseline approach in the LTE standards in terms of energy consumption , average delay , success probability and collision probability . Simulation results show that this method significantly lowers the collision probability and reduces the energy consumption of the MTDs in their access request procedure . Key words : 1- machine to machine (M2M) communications, 2- random access channel (RACH), 3- machine learning, 4- LTE/LTE-A networks.
