Mobility Management in 5G and Beyond: A Novel Smart Handover With Adaptive Time-to-Trigger and Hysteresis Margin

Abstract

The 5th Generation (5G) New Radio (NR) and beyond technologies will support enhanced mobile broadband, very low latency communications, and huge numbers of mobile devices. Therefore, for very high speed users, seamless mobility needs to be maintained during the migration from one cell to another in the handover. Due to the presence of a massive number of mobile devices, the management of the high mobility of a dense network becomes crucial. Moreover, a dynamic adaptation is required for the Time-to-Trigger (TTT) and hysteresis margin, which significantly impact the handover latency and overall throughput. Therefore, in this paper, we propose an online learning-based mechanism, known as Learning-based Intelligent Mobility Management (LIM2), for mobility management in 5G and beyond, with an intelligent adaptation of the TTT and hysteresis values. LIM2 uses a Kalman filter to predict the future signal quality of the serving and neighbor cells, selects the target cell for the handover using state-action-reward-state-action (SARSA)-based reinforcement learning, and adapts the TTT and hysteresis using the -greedy policy. We implement a prototype of the LIM2 in NS-3 and extensively analyze its performance, where it is observed that the LIM2 algorithm can significantly improve the handover operation in very high speed mobility scenarios.

Advanced Mobility Robustness Optimization Models in Future Mobile Networks Based on Machine Learning Solutions

“…Moreover, high number of connected devices in ultra-dense networks need a proper HO algorithm to auto-tunes the TTT and HOM. Therefore, Raja et al proposed learning-based intelligent mobility management mechanism to self-optimize the TTT and HOM based on HOF, latency, and throughput [41]. Kalman filter has been used to predict the RSRP of the serving and target BSs.…”

“…Furthermore, a prototype for learning-based intelligent mobility management has been created using the network simulator (NS-3) over 5G deployment scenario. In addition, several mobile speed scenarios (i.e., 50 km/hr, 100 km/hr, 150 km/hr, 200 km/hr, 250 km/hr, 300 km/hr, 350 km/hr) were applied in [41]. However, the results show that the average throughput of the proposed mechanism is 19 % and 68 % higher than the mechanisms applied in the literature which are the reliable extreme mobility [85] and contextual multi-armed bandit [86], respectively.…”

“…Based on the algorithms addressed in this study, HCPs of the MRO were optimized under a several network topologies. These topologies includes 5G network [8], [41], [48], [89], HetNet [23], [30], [38], [56], [59], [60], [71], [75], [82], LTE-network [14], [29], [32], [33], [34], [39], [70], [74], [76], [77]. Moreover, several network topologies are addressed in Tables 2, 3.…”

“…Manhattan grid mobility model and random way point mobility model are presented in [40], the random way point mobility model used in pedestrian environment at user speed of 5 km/hr. Constant velocity mobility model is introduced in [41].…”

“…The common types of ML have been implemented to optimize the HCPs of MRO functions, such as the supervised ML [21], [22], [23], [24], [25], [26], [27], unsupervised ML [28], and reinforcement learning [14], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42]. Several ML techniques under each type have been addressed as a solution method.…”