by Melhem El Helou, Marc Ibrahim, Samer Lahoud, Kinda Khawam, Dany Mezher, Bernard Cousin
Abstract:
When several radio access technologies (e.g., HSPA, LTE, WiFi, and WiMAX) cover the same region, deciding to which one mobiles connect is known as the Radio Access Technology (RAT) selection problem. To reduce network signaling and processing load, decisions are generally delegated to mobile users. Mobile users aim to selfishly maximize their utility. However, as they do not cooperate, their decisions may lead to performance inefficiency. In this paper, to overcome this limitation, we propose a network-assisted approach. The network provides information for the mobiles to make more accurate decisions. By appropriately tuning network information, user decisions are globally expected to meet operator objectives, avoiding undesirable network states. Deriving network information is formulated as a semi-Markov decision process (SMDP), and optimal policies are computed using the Policy Iteration algorithm. Also, and since network parameters may not be easily obtained, a reinforcement learning approach is introduced to derive what to signal to mobiles. The performances of optimal, learning-based, and heuristic policies, such as blocking probability and average throughput, are analyzed. When tuning thresholds are pertinently set, our heuristic achieves performance very close to the optimal solution. Moreover, although it provides lower performance, our learning-based algorithm has the crucial advantage of requiring no prior parameterization.
Reference:
A Network-Assisted Approach for RAT Selection in Heterogeneous Cellular Networks (Melhem El Helou, Marc Ibrahim, Samer Lahoud, Kinda Khawam, Dany Mezher, Bernard Cousin), In IEEE Journal on Selected Areas in Communications - Special Issue on Recent Advances in Heterogenous Cellular Networks (JSAC - HCN), volume 33, 2015.
Bibtex Entry:
@article{el-helou:2015cr,
abstract = {When several radio access technologies (e.g., HSPA, LTE,
WiFi, and WiMAX) cover the same region, deciding to which
one mobiles connect is known as the Radio Access Technology
(RAT) selection problem. To reduce network signaling and
processing load, decisions are generally delegated to
mobile users. Mobile users aim to selfishly maximize their
utility. However, as they do not cooperate, their decisions
may lead to performance inefficiency. In this paper, to
overcome this limitation, we propose a network-assisted
approach. The network provides information for the mobiles
to make more accurate decisions. By appropriately tuning
network information, user decisions are globally expected
to meet operator objectives, avoiding undesirable network
states. Deriving network information is formulated as a
semi-Markov decision process (SMDP), and optimal policies
are computed using the Policy Iteration algorithm. Also,
and since network parameters may not be easily obtained, a
reinforcement learning approach is introduced to derive
what to signal to mobiles. The performances of optimal,
learning-based, and heuristic policies, such as blocking
probability and average throughput, are analyzed. When
tuning thresholds are pertinently set, our heuristic
achieves performance very close to the optimal solution.
Moreover, although it provides lower performance, our
learning-based algorithm has the crucial advantage of
requiring no prior parameterization.},
author = {Melhem {El Helou} and Marc Ibrahim and Samer Lahoud and Kinda Khawam and Dany Mezher and Bernard Cousin},
doi = {10.1109/JSAC.2015.2416987},
issn = {0733-8716},
journal = {IEEE Journal on Selected Areas in Communications - Special Issue on Recent Advances in Heterogenous Cellular Networks (JSAC - HCN)},
keywords = {Radio access technology selection; semi-Markov decision process; reinforcement learning; heterogeneous cellular networks},
month = {June},
number = {6},
pages = {1055-1067},
pdf = {http://samer.lahoud.fr/pub-pdf/jsac-15.pdf},
title = {A Network-Assisted Approach for {RAT} Selection in Heterogeneous Cellular Networks},
volume = {33},
year = {2015},
bdsk-url-1 = {https://doi.org/10.1109/JSAC.2015.2416987}}