RT Journal Article
T1 Automatic Feature Selection Technique for Next Generation Self-Organizing Networks
A1 Palacios, David
A1 De la Bandera Cascales, Isabel
A1 Gómez-Andrades, Ana
A1 Flores, Lydia
A1 Barco-Moreno, Raquel
K1 Sistemas de comunicaciones inalámbricos
AB Despite self-organizing networks (SONs) pursue theautomation of management tasks in current cellular networks,the selection of the most useful performance indicators (PIs),used as inputs for SON functions, is still performed by networkexperts. In this letter, a novel supervised technique for theautomatic selection of PIs for self-healing functions is proposed,relying on the dissimilarity of their statistical behavior underdifferent network states. Results using data from a live networkshow that the proposed method outperforms an expert’sselection, allowing the volume and complexity of both networkdatabases and SON functions to be reduced without an expert’sintervention.
PB IEEE
YR 2018
FD 2018
LK https://hdl.handle.net/10630/30226
UL https://hdl.handle.net/10630/30226
LA eng
NO D. Palacios, I. de-la-Bandera, A. Gómez-Andrades, L. Flores and R. Barco, "Automatic Feature Selection Technique for Next Generation Self-Organizing Networks," in IEEE Communications Letters, vol. 22, no. 6, pp. 1272-1275, June 2018.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026