Over the last few years, the worldwide cellular communication market has undergone exponential growth. This can be attributed to several factors like decreasing prices, improved radio coverage, lightweight and compact terminals. In order to accommodate higher subscriber densities, the standard technique used is to reduce the radio cell size. However, reduction in cell size increases signaling for location management procedure, which reduces the effective bandwidth available for the user traffic. Location management in general and location prediction in particular incorporates procedures with which system can locate particular mobile subscriber at any given time. Number of location prediction algorithms have been developed in the recent past. In this study, an artificial neural network technique has been used for location prediction of a mobile subscriber. Learning methods like backpropagation, backpropagation with momentum, quick propagation and resilient propagation have been applied. Results are compared with the conventional Box Jenkins forecasting technique.
[1]
Ian F. Akyildiz,et al.
Mobility Management in Next Generation Wireless Systems
,
1999,
ICCCN.
[2]
Ian F. Akyildiz,et al.
Mobile user location update and paging under delay constraints
,
1995,
Wirel. Networks.
[3]
Ian F. Akyildiz,et al.
Dynamic mobile user location update for wireless PCS networks
,
1995,
Wirel. Networks.
[4]
Ian F. Akyildiz,et al.
A dynamic location management scheme for next-generation multitier PCS systems
,
2002,
IEEE Trans. Wirel. Commun..
[5]
Amotz Bar-Noy,et al.
Mobile users: To update or not to update?
,
1994,
Proceedings of INFOCOM '94 Conference on Computer Communications.
[6]
Xian Zhou,et al.
Locating Strategies for Personal Communication Networks: A Novel Tracking Strategy
,
1997,
IEEE J. Sel. Areas Commun..