Study on Based Reinforcement Q-Learning for Mobile Load Balancing Techniques in LTE-A HetNets

Mobile-broadband traffic has experienced a large increase and the network has continuously expanded over the past few years. Picocells are envisioned to cope with such a demand of capacity in network environments. Since those small cells are low-cost nodes, a thorough deployment is not typically performed, particularly in LTE-A Het Nets. As a result, the matching between traffic demand and network resources is rarely optimal. In this paper, several common load balancing algorithms are studied and compared to solve localized congestion problems. In particular, these techniques are implemented by reinforcement Q-Learning algorithm that forecasts load status for every node, and combined with the related concepts of self-organization network which is the current research focus to adaptive parameters so that improve network performance.