Estefania Coronado
Abin Thomas
Roberto Riggio
2020-03-17
<p>Software-Defined Networking (SDN) is gaining a lot of traction in wireless systems<br>
with several practical implementations and numerous proposals being made. Despite<br>
instigating a shift from monolithic network architectures towards more modulated<br>
operations, automated network management requires the ability to extract, utilise<br>
and improve knowledge over time. Beyond simply scrutinizing data, Machine<br>
Learning (ML) is evolving from a simple tool applied in networking to an active<br>
component in what is known as Knowledge-Defined Networking (KDN). This work<br>
discusses the inclusion of ML techniques in the specific case of Software-Defined<br>
Wireless Local Area Networks (SD-WLANs), paying particular attention to the<br>
frame length optimization problem. With this in mind, we propose an adaptive MLbased<br>
approach for frame size selection on a per-user basis by taking into account<br>
both specific channel conditions and global performance indicators. By relying on<br>
standard frame aggregation mechanisms, the model can be seamlessly embedded<br>
into any Enterprise SD-WLAN by obtaining the data needed from the control plane,<br>
and then returning the output back to this in order to efficiently adapt the frame size<br>
to the needs of each user. Our approach has been gauged by analysing a multitude of<br>
scenarios, with the results showing an average improvement of 18.36% in goodput<br>
over standard aggregation mechanisms.</p>
https://doi.org/10.1007/s10922-020-09527-y
oai:zenodo.org:4627935
eng
Zenodo
https://zenodo.org/communities/5gzorro-h2020
https://zenodo.org/communities/eu
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Journal of Network and Systems Management, (2020-03-17)
Machine learning · Supervised learning · WLANs · IEEE 802.11 · Frame length optimization · Aggregation · SDN · Network management
Adaptive ML‑Based Frame Length Optimisation in Enterprise SD‑WLANs
info:eu-repo/semantics/article