Deep Q-Networks Assisted Pre-connect Handover Management for 5G Networks

Handover management is crucial for wireless networks and is more challenging for Fifth Generation (5G) networks due to strict requirements in quality of service (QoS), such as ultra-reliable low latency communications (URLLC) services. This paper extends the pre-connect handover (PHO) mechanism for user equipment (UE) using Deep Q-Networks (DQN) to support challenging handover management requirements in 5G networks. The proposed DQN-assisted PHO management facilitates the sequential decision-making problem of the target cell selection based on the Reference Signal Received Quality (RSRQ) values and RSRQ change rates of all the candidate cells. The performance of the DQN-assisted PHO management solutions has been evaluated extensively with various configurations using Network Simulator 3 (NS-3) and NS3-Gym. The experimental results demonstrated the DQN-assisted PHO technique can productively accomplish the optimal target cell selection to maximize the success rate of PHO.