Context-Aware Handover Policies in HetNets

Guidolin, Francesco; Pappalardo, Irene; Zanella, Andréa; Zorzi, Michele

doi:10.1109/twc.2015.2496958

Cited by 65 publications

(44 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [12], a TTT selection policy was proposed by assuming the knowledge of the UE trajectory distribution and channel propagation model. All the above results [10]- [12] adopted a similar methodology, which is to first compute certain transit probabilities with the knowledge of some network dynamics, e.g., UE trajectories [12] or load state transition probabilities [11], and then use the derived transit probabilities to derive the optimal HO decision policy. In other words, the above methods to obtain the HO decision policy are falling into the traditional model-based framework.…”

Section: Introductionmentioning

confidence: 99%

Handover Control in Wireless Systems via Asynchronous Multiuser Deep Reinforcement Learning

Wang

et al. 2018

IEEE Internet Things J.

126

View full text Add to dashboard Cite

In this paper, we propose a two-layer framework to learn the optimal handover (HO) controllers in possibly large-scale wireless systems supporting mobile Internet-of-Things (IoT) users or traditional cellular users, where the user mobility patterns could be heterogeneous. In particular, our proposed framework first partitions the user equipments (UEs) with different mobility patterns into clusters, where the mobility patterns are similar in the same cluster. Then, within each cluster, an asynchronous multi-user deep reinforcement learning scheme is developed to control the HO processes across the UEs in each cluster, in the goal of lowering the HO rate while ensuring certain system throughput. In this scheme, we use a deep neural network (DNN) as an HO controller learned by each UE via reinforcement learning in a collaborative fashion. Moreover, we use supervised learning in initializing the DNN controller before the execution of reinforcement learning to exploit what we already know with traditional HO schemes and to mitigate the negative effects of random exploration at the initial stage. Furthermore, we show that the adopted global-parameter-based asynchronous framework enables us to train faster with more UEs, which could nicely address the scalability issue to support large systems. Finally, simulation results demonstrate that the proposed framework can achieve better performance than the state-of-art on-line schemes, in terms of HO rates.

show abstract

Section: Introductionmentioning

confidence: 99%

Handover Control in Wireless Systems via Asynchronous Multiuser Deep Reinforcement Learning

Wang

et al. 2018

IEEE Internet Things J.

126

View full text Add to dashboard Cite

show abstract

“…The work presented in [25] focuses on optimization of HO procedure in HetNets by incorporating context information such as user speed, channel gains and traffic load in the cells. This work proposes a Markov chain-based framework to model the HO process for the mobile user and derives an optimal context-dependent HO criterion.…”

Section: Introductionmentioning

confidence: 99%

“…This work clearly demonstrates that context-awareness can indeed improve the HO process and significantly increase the performance of mobile UEs in HetNets. In contrast to [25], this study aims to address the question of how much signalling is generated in case of HOs for CDSA based HetNets. On the other hand, the works presented in [26] does provide HO analysis for CDSA based HetNets.…”

Section: Introductionmentioning

confidence: 99%

Analytical Modeling for Mobility Signalling in Ultradense HetNets

Taufique

Mohamed

Farooq

et al. 2019

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

Multi-band and multi-tier network densification is being considered as the most promising solution to overcome the capacity crunch problem of cellular networks. In this direction, small cells (SCs) are being deployed within the macro cell (MC) coverage, to off-load some of the users associated with the MCs. This deployment scenario raises several problems. Among others, signalling overhead and mobility management will become critical considerations. Frequent handovers (HOs) in ultra dense SC deployments could lead to a dramatic increase in signalling overhead. This suggests a paradigm shift towards a signalling conscious cellular architecture with smart mobility management. In this regards, the control/data separation architecture (CDSA) with dual connectivity is being considered for the future radio access. Considering the CDSA as the radio access network (RAN) architecture, we quantify the reduction in HO signalling w.r.t. the conventional approach. We develop analytical models which compare the signalling generated during various HO scenarios in the CDSA and conventionally deployed networks. New parameters are introduced which can with optimum value significantly reduce the HO signalling load. The derived model includes HO success and HO failure scenarios along with specific derivations for continuous and non-continuous mobility users. Numerical results show promising CDSA gains in terms of saving in HO signalling overhead.Index Terms-Cellular networks; control data separation architecture; dual connectivity handover; signalling load; radio access networks.

show abstract

“…Another type of HO optimization strategies is based on the user's mobility status. The authors in [9] propose a time-to-trigger parameter selection policy by assuming that the user's trajectory is already known and trying to balance the handover failure probability and the ping-pong effect. The authors in [10] put forward an approach for the prediction of user's movement direction and residence time in the target cell to reduce unnecessary HOs.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Intelligent Dual Connectivity for Mobility Management in Dense Network

Wang

Zhao

Sun

et al. 2018

2018 IEEE 88th Vehicular Technology Conference (VTC-Fall)

View full text Add to dashboard Cite

Ultra-dense network deployment has been proposed as a key technique for achieving capacity goals in the fifthgeneration (5G) mobile communication system. However, the deployment of smaller cells inevitably leads to more frequent handovers, thus making mobility management more challenging and reducing the capacity gains offered by the dense network deployment. In order to fully reap the gains for mobile users in such a network environment, we propose an intelligent dual connectivity mechanism for mobility management through deep learning-based mobility prediction. We first use LSTM (Long Short Term Memory) algorithm, one of deep learning algorithms, to learn every user equipment's (UE's) mobility pattern from its historical trajectories and predict its movement trends in the future. Based on the corresponding prediction results, the network will judge whether a handover is required for the UE. For the handover case, a dual connection will be established for the related UE. Thus, the UE can get the radio signal from two base stations in the handover process. Simulation results verify that the proposed intelligent dual connectivity mechanism can significantly improve the quality of service of mobile users in the handover process while guaranteeing the network energy efficiency.

show abstract

Context-Aware Handover Policies in HetNets

Cited by 65 publications

References 27 publications

Handover Control in Wireless Systems via Asynchronous Multiuser Deep Reinforcement Learning

Handover Control in Wireless Systems via Asynchronous Multiuser Deep Reinforcement Learning

Analytical Modeling for Mobility Signalling in Ultradense HetNets

Deep Learning-Based Intelligent Dual Connectivity for Mobility Management in Dense Network

Contact Info

Product

Resources

About