Base Station Selection in M2M Communication Using Q-Learning Algorithm in LTE-A Networks

A major problem faced by machine type communication (MTC) devices in machine to machine (M2M) communication is the congestion and traffic overloading when incorporating into LTE Advanced networks. In this paper, we present an approach to tackle this problem by providing an efficient way for multiple access in the network and minimizing network overload. We consider the random access network (RAN) between the LTE base stations and MTC devices in the cell. We propose an unsupervised learning algorithm, based on Q-learning, as a means of base station selection scheme where MTC devices continuously adapt to changing network traffic and decide which base station is to be selected on the basis of QoS parameters. Simulation results demonstrate that the proposed algorithm helps MTC devices achieve better performance and, therefore, enhances the M2M communication performance.

[1]  Matti Latva-aho,et al.  Learning based mechanisms for interference mitigation in self-organized femtocell networks , 2010, 2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers.

[2]  Dusit Niyato,et al.  Random access for machine-to-machine communication in LTE-advanced networks: issues and approaches , 2013, IEEE Communications Magazine.

[3]  Kuei-Li Huang,et al.  An energy-efficient scheme for WiFi-capable M2M devices in hybrid LTE network , 2012, 2012 IEEE International Conference on Advanced Networks and Telecommunciations Systems (ANTS).

[4]  Dorin Panaitopol,et al.  Reinforcement learning approach to dynamic activation of base station resources in wireless networks , 2013, 2013 IEEE 24th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[5]  David Grace,et al.  Application of Q-Learning for RACH Access to Support M2M Traffic over a Cellular Network , 2014 .

[6]  Soo Young Shin,et al.  Radio resource control scheme for machine-to-machine communication in LTE infrastructure , 2012, 2012 International Conference on ICT Convergence (ICTC).

[7]  Kwang-Cheng Chen,et al.  Toward ubiquitous massive accesses in 3GPP machine-to-machine communications , 2011, IEEE Communications Magazine.

[8]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[9]  Mehdi Bennis,et al.  A Q-learning based approach to interference avoidance in self-organized femtocell networks , 2010, 2010 IEEE Globecom Workshops.