Reinforcement learning-based joint self-optimisation method for the fuzzy logic handover algorithm in 5G HetNets

5G heterogeneous networks (HetNets) can provide higher network coverage and system capacity to the user by deploying massive small base stations (BSs) within 4G macrosystem. However, large-scale deployment of BSs significantly increases complexity workload maintenance optimisation. The current handover (HO) triggering mechanism A3 event was designed only for mobility management in Directly implementing 5G-HetNets may degrade robustness. Motivated concept self-organisation (SON), this study developed a self-optimisation enable automated enhance robustness 5G-HetNets. proposed method integrates advantages subtractive clustering Q-learning frameworks into conventional fuzzy logic-based HO algorithm (FLHA). Subtractive is first adopted generate membership function (MF) FLHA with self-configuration feature. Subsequently, utilised learn optimal policy from environment as rules that empower function. SON functionality also overcomes limitations must rely heavily on professional experience design. simulation results show effectively MF FLHA. approach minimise HO, ping-pong failure ratios while improving throughput latency comparing mechanisms.