Reference signal power control for load balancing in downlink LTE-A self-organizing networks

Self-organizing network (SON) is considered as a driving technology for the deployment of next generation radio access networks. This paper addresses the problem of load balancing (LB) for multi-hop cellular network (MCN) with fixed relays such as LTE-A network in the context of SON. The designed SON algorithm, namely RSPC-RL, is based on two ideas: relay node reference signal power control (RSPC) and multi-agent reinforcement learning (RL). In the proposed RSPC-RL algorithm, the relay node is modeled as an agent that learns an optimal policy of reference signal power control from its interaction with environment to balance the load distribution of the network through dynamically changing its coverage area. Numerical results show the significant performance gain brought about by the proposed algorithm RSPC-RL.