Dynamic Inter-Cell Interference Coordination in HetNets: A reinforcement learning approach

In this paper, we investigate enhanced Inter-Cell Interference Coordination (e-ICIC) techniques for Heterogeneous Networks (HetNets), consisting of a mix of macro and picocells. We model this strategic coexistence as a multi-agent system in which decentralized interference management and cell association strategies inspired from Reinforcement Learning (RL) are devised. Specifically, we focus on time and frequency domain ICIC techniques in which picocells optimally learn their cell range bias and downlink transmit power allocation. In turn, the macrocell optimizes its transmission by serving its own users while adhering to the picocell interference constraint. To substantiate our theoretical findings, system level simulations are carried out in which our proposed solution is compared with a number of existing ICIC approaches, such as resource partitioning, fixed cell range expansion (CRE) and fixed Almost Blank Subframe (ABS). Interestingly, our proposed solution is shown to yield substantial gains of up to 125% compared to static ICIC approaches.