OccurrenceswithinLTE分析.PDFVIP

A Kernel Methods Approach to Reducing Handover Occurrences within LTE Neil Sinclair, David Harle, Ian A. Glover, and Robert C. Atkinson Department of EEE University of Strathclyde Glasgow, UK Email: neil.sinclair@strath.ac.uk, d.harle, ian.glover, r.atkinson@eee.strath.ac.uk Abstract— This paper presents a kernel-based approach to both the CAPital EXpenditure (CAPEX) and the OPerational indoor-outdoor handover management for 4G femtocells. It is a EXpenditure (OPEX) of their networks by introducing a necessary but difficult task to perform seamless handover from degree of self management. Within LTE, the self management indoor femtocells to outdoor macrocells whilst maintaining call continuity. This paper describes a machine learning algorithm to functionality is referred to as a Self Organizing Network operate in conjunction with 4G handover triggering mechanisms (SON) [3] [4], a multi-faceted term that encompasses self- to reduce the rate of unnecessary handovers between femtocells configuration, self-healing, self-protection and self optimisa- and macrocells. The results of this algorithm show that handovers tion. SON offers LTE a plug-n-play functionality that allows can be reduced by 65% by detecting where unnecessary han- both macrocells (eNodeBs) and femtocells (HeNodeBs) to dovers are likely to occur and minimising them. By reducing the number of unnecessary handovers, the system resources efficiency first be deployed and then autonomically self-configure to may be improved as a result of the p