Mobility Prediction: A Survey on State-of-the-Art Schemes and Future Applications

Abstract

Recently, mobility has gathered tremendous interest as the users' desire for consecutive connections and better quality of service has increased. An accurate prediction of user mobility in mobile networks provides efficient resource and handover management, which can avoid unacceptable degradation of the perceived quality. Therefore, mobility prediction in wireless networks is of great importance and many works have been dedicated to this issue. In this paper, the necessity of mobility prediction, together with its intrinsic characteristics in terms of movement predictability, prediction outputs, and performance metrics is discussed. Moreover, the learning perspective of solutions to mobility prediction has been studied. Specifically, an overview of the state-of-the-art approaches is provided, including Markov chain, hidden Markov model, artificial neural network, Bayesian network, and data mining based on different kinds of knowledge. At last, this paper also explores the open research challenges due to the advent of the fifthgeneration mobile system and puts forward some potential trends in the near future. INDEX TERMS Mobility prediction, quality of service (QoS), resource reservation, handover management, the fifth-generation mobile system (5G).

Mobility Prediction-Based Optimisation and Encryption of Passenger Traffic-Flows Using Machine Learning

“…The movements are user trajectories from source to destination with regular intervals, expected or unexpected. Several comprehensive surveys for mobility prediction are available in [14][15][16] that exploit various methods of predicting user mobility patterns where Markov chain-based is a popular predictor due to being less complex in nature [12,15,17]. However, with the limitations of real-time datasets that have complexity involved, ML predictors can be a viable alternative in order to study traffic flow and provide encryption to it.…”

On the Challenges of Mobility Prediction in Smart Cities

“…We give also the main conclusions obtained in the cited works. Table 2 is established on the basis of a study described in (Zhang, Dai, 2018), summarizing some works dealing with mobility prediction. The following criteria are considered: objective, technique used, movement type, context consideration, precision, and complexity/costs generated (calculation time, memory space…).…”

“…The following criteria are considered: objective, technique used, movement type, context consideration, precision, and complexity/costs generated (calculation time, memory space…). The "technique used" and "precision" criteria are reported from (Zhang, Dai, 2018). The remaining criteria are new and are useful to the identification of mobility prediction issues.…”

“…b-Markov models (standard and hidden) are widely used in the field of mobility prediction. Standard MCs are simple and easy to implement (Zhang, Dai, 2018) but their performance, in terms of precision, are often subject to certain constraints (transition matrix's values (Amirrudin et al, 2013a), movement type (Jiang et al, 2016) …). The hidden Markov models are also efficient in terms of accuracy (Zhang, Dai, 2018) (about 53% in (Lv et al, 2014), sometimes exceeds 80% in (Qiao et al, 2015) and even greater than 90% in (Amirrudin et al, 2013b)).…”

Key Challenges, Drivers and Solutions for Mobility Management in 5G Networks: A Survey

“…Recently, a few studies have focused on mobility management issues in terms of mobility prediction, autonomic vertical handover, security, Software-Defined Network (SDN), Software Defined Network Virtualization (SDNV), Network Function Virtualization (NFV), and battery consumption models [33][34][35][36][37][38]. On top of that, a survey based on real measurement data conducted shown how Long Term Evolution -Advanced (LTE-A) network performs during the mobility of users in comparison with the first phase of LTE releases.…”