Location Management Cost Estimation for PCS Using Neural Network

Authors:
Demin Li;Jie Zhou;Jiacun Wang;Guoliang Wei
Affiliations:
College of Information Science and Technology, Donghua University, Shanghai 201620, China;School of Sciences, Donghua University, Shanghai 201620, China;Department of Software Engineering, Monmouth University, West Long Branch, NJ 07762, USA;College of Information Science and Technology, Donghua University, Shanghai 201620, China
Venue:
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
Year:
2007

Citing 10
Cited 0

Movement-based location update and selective paging for PCS networks

IEEE/ACM Transactions on Networking (TON)
Reducing location update cost in a PCS network

IEEE/ACM Transactions on Networking (TON)
Mobile users: to update or not to update?

Wireless Networks
Mobile user location update and paging under delay constraints

Wireless Networks
Traffic model for third generation cellular mobile telecommunication systems

Wireless Networks
Cost reduction in location management using semi-realtime movement information

Wireless Networks
Estimation of the domain of attraction and the convergence rate of a Hopfield associative memory and an application

Journal of Computer and System Sciences
Predictive distance-based mobility management for multidimensional PCS networks

IEEE/ACM Transactions on Networking (TON)
A dynamic location management scheme for next-generation multitier PCS systems

IEEE Transactions on Wireless Communications
Location management for next-generation personal communications networks

IEEE Network: The Magazine of Global Internetworking

Quantified Score

Hi-index	0.00

Visualization

Abstract

The fluid-flow model is suitable for vehicle traffic on highways but not for pedestrian movements at variable velocities. Considering the change of a mobile's velocity within a short time is limited due to physical restrictions, therefore a mobile user's future velocity is likely to be correlated with its past and current velocity. Since Gauss-Markov model captures the essence of the correlation of a mobile's velocity in time, we propose a Gauss-Markov process based fluid model that it is suitable for both vehicle traffic on highways and pedestrian in street, and presents the total cost estimation of location management for the Gauss-Markov process based fluid model.Considering the importance of memory level in the Gauss-Markov model, we estimate the parameter using neural network. Considering the measurements of updating and paging cost is not consecutive but contain missing observations, we propose the methods of location management total cost estimation with missing measurement for PCS, and utilize the Kalman filter to deduce the steady covariance of the estimation error of total cost per unit time. A numerical example is given to illustrate the use of the proposed approach.