Handoff management in wireless data networks using topography-aware mobility prediction

Authors:
AlaaEldin Sleem;Anup Kumar
Affiliations:
Computer Engineering and Computer Science Department, University of Louisville, Louisville, KY 40292, USA;Computer Engineering and Computer Science Department, University of Louisville, Louisville, KY 40292, USA
Venue:
Journal of Parallel and Distributed Computing
Year:
2005

Citing 9
Cited 3

Multilayer feedforward networks are universal approximators

Neural Networks
On the approximate realization of continuous mappings by neural networks

Neural Networks
The shadow cluster concept for resource allocation and call admission in ATM-based wireless networks

MobiCom '95 Proceedings of the 1st annual international conference on Mobile computing and networking
Mobility-based predictive call admission control and bandwidth reservation in wireless cellular networks

Computer Networks: The International Journal of Computer and Telecommunications Networking
Call Admission Control Using the Moving Pattern of Mobile User for Mobile Multimedia Networks

LCN '02 Proceedings of the 27th Annual IEEE Conference on Local Computer Networks
New Mobility Based Call Admission Control with On-Demand Borrowing Scheme for QOS Provisioning

ITCC '03 Proceedings of the International Conference on Information Technology: Computers and Communications
Motion prediction in mobile/wireless networks

Motion prediction in mobile/wireless networks
Mobility modeling, location tracking, and trajectory prediction in wireless ATM networks

IEEE Journal on Selected Areas in Communications
An alternative strategy for location tracking

IEEE Journal on Selected Areas in Communications

QoS provisioning by EFuNNs-based handoff planning in cellular MPLS networks

Computer Communications
A comprehensive mobility management solution for handling peak load in cellular network scenarios

Proceedings of the 6th ACM international symposium on Mobility management and wireless access
A personalized QoE-aware handover decision based on distributed reinforcement learning

Wireless Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce a Handoff prediction and enhancement scheme (HOPES) that aims to explore the use of prediction techniques in mobility managements in order to improve the end-to-end traffic quality. The fundamental difference between HOPES and other predictive mobility management techniques is that HOPES uses topography-aware predictive approach that combines the mobile host's movement history, current state, and the topography of the cells. The proposed architecture provides the network with timely information necessary to proactively respond to user movements instead of passively handling it after it happens. The effectiveness of this work is demonstrated through a comparative study that included other mobility prediction models. The comparison involves monitoring of several performance metrics to asses the end-to-end traffic improvement achieved from the proposed model. These metrics include; Packet Loss, Data Delivery Ratio, Reserved Bandwidth, Retransmitted Packets per Received Packet, and TCP Session Duration. The results obtained for HOPES show a significant improvement in traffic quality without sacrificing the utilization of network resources. This can be attributed to the nature of the topography-aware mobility modeling and prediction suggested by HOPES which is more accurate in predicting mobility patterns when topographical features have impact on mobile users' movements.