Multi-criteria handover mobility management in 5G cellular network

Abstract

To fulfill the future demand and expansion of the coverage of the network, ultra-dense deployment of small cell (SC) is an optimal solution for future 5G networks, which will ensure the UEs (User Equipment) continuous connectivity. However, these small cells (SCs) lead to the issue of interference, additional unnecessary handover (HO), signaling overhead, and which in turn decreases the overall quality of service (QoS) of the users. In this paper, an intelligent mobility management system based on Enhanced Multi-Objective Optimization Method by Ratio Analysis (E-MOORA) and Q-learning approach is introduced for handover optimization. E-MOORA method is the combination of modified entropy weighting technique and Multi-Objective Optimization Method by Ratio Analysis (MOORA) which introduces vector normalization. The proposed E-MOORA method judicially exploits the performance parameters and thus reduces ranking abnormality when it selects a HO target cell. Q-learning approach is applied to select the optimal triggering points to minimize the effect of frequent unnecessary handovers for satisfying user QoS requirements. The performance analysis results depict significant performance improvement in terms of minimizing the unnecessary HO, radio link failure, and user throughput compared to other existing Multi-Criteria Decision Making (MCDM) methods.