Fuzzy Logic and Accelerated Reinforcement Learning-Based User Association for Dense C-RANs

Cloud radio access network (C-RAN) is a potential mobile network architecture providing seamless connectivity to users with high data rates by integrating it with the small-cell technology of 5G mobile communication systems. In C-RAN, base station functionality is divided into a baseband unit (BBU) and remote radio head (RRH); the BBUs from multiple sites are centralized and virtualized using cloud computing and virtualization techniques. Frequent handovers occur in the network, which results in control message flooding and repeated service outages because of the dense deployment of short-range RRHs and user mobility. It is necessary to optimize handover control parameters before the handover and re-associate the user with an RRH to minimize unnecessary handovers in the network. Traditional handover schemes rely on signal strengths of RRHs, which cause a large number of unnecessary handovers when a user moves within the coverage of multiple-overlapped RRHs. This study investigates the handover in C-RAN by carefully optimizing the handover control parameter and selecting the target RRH for handover. Our main goal is associating the user with an RRH such that association after the handover remains possible for as long as possible while maintaining the quality of service (QoS) requirements of the users. We have used fuzzy logic to optimize the handover control parameter and a reinforcement learning-based algorithm to select the target RRH. A key component of the proposed RL-based scheme is using an acceleration technique for the faster convergence of the algorithm. Numerical results show that the proposed scheme can significantly reduce the number of handovers while ensuring QoS requirements.