DocumentCode :
2610495
Title :
Self-Organized Resource Allocation for LTE Pico Cells: A Reinforcement Learning Approach
Author :
Feki, Afef ; Capdevielle, Veronique ; Sorsy, Elom
Author_Institution :
Alcatel-Lucent Bell Labs., Marcoussis, France
fYear :
2012
fDate :
6-9 May 2012
Firstpage :
1
Lastpage :
5
Abstract :
This articles proposes a smart resource sharing algorithm to manage interference in LTE networks. Relying on reinforcement learning theory, the proposed Cyclic Multi Armed Bandit (CMAB) algorithm steers each cell in the choice of the most suitable frequency band portions, in autonomous manner. Thanks to the traffic aware feature, the algorithm adapts as well to the real needs of the cell. Adding to that, a refinement of the decision function is proposed to speed up the convergence time. The proposed approach is tested in LTE compliant simulator and the results shows its efficiency compared to conventional static reuse schemes.
Keywords :
Long Term Evolution; learning (artificial intelligence); picocellular radio; radiofrequency interference; resource allocation; telecommunication computing; LTE compliant simulator; LTE pico cell; convergence time; cyclic multiarmed bandit algorithm; decision function refinement; interference management; reinforcement learning approach; reinforcement learning theory; self-organized resource allocation; smart resource sharing algorithm; Convergence; Interference; Learning; Mathematical model; Resource management; Signal to noise ratio; Throughput;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Vehicular Technology Conference (VTC Spring), 2012 IEEE 75th
Conference_Location :
Yokohama
ISSN :
1550-2252
Print_ISBN :
978-1-4673-0989-9
Electronic_ISBN :
1550-2252
Type :
conf
DOI :
10.1109/VETECS.2012.6240019
Filename :
6240019
Link To Document :
بازگشت