Load Balancing Models based on Reinforcement Learning for Self-Optimized Macro-Femto LTE-Advanced Heterogeneous Network

Abstract

Heterogeneous Long Term Evolution-Advanced (LTE-A) network (HetNet) utilizes small cells to enhance its capacity and coverage. The intensive deployment of small cells such as pico- and femto-cells to complement macro-cells resulted in unbalanced distribution of traffic-load among cells. Machine learning techniques are employed in cooperation with Self-Organizing Network (SON) features to achieve load balancing between highly loaded Macro cells and underlay small cells such as Femto cells. In this paper, two algorithms have been proposed to balance the traffic load between Macro and Femto cells. The two proposed algorithms are named as Load Balancing based on Reinforcement Learning of end-user SINR (LBRL-SINR) and Load Balancing based on Reinforcement Learning of Macro cell-throughput (LBRL-T). Both of the proposed algorithms utilize Reinforcement Learning (RL) technique to control the reference signal power of each Femto cell that underlays a highly loaded Macro cell. At the same time, the algorithm monitors any degradation in the performance metrics of both Macro and its neighbor Femto cells and reacts to troubleshoot the degradation in real time. The simulation results showed that both of the proposed algorithms are able to off-load end-users from highly loaded Macro cell and redistribute the traffic load fairly with its neighbor Femto cells. As a result, both of call drop rate and call block rate of a highly loaded Macro cell are decreased.