aiOS: An Intelligence Layer for SD-WLANs

Estefanía Coronado; Abin Thomas; Suzan  Bayhan; Roberto Riggio

doi:10.1109/NOMS47738.2020.9110260

aiOS: An Intelligence Layer for SD-WLANs

Estefanía Coronado, Abin Thomas, Suzan Bayhan, Roberto Riggio

Design and Analysis of Communication Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

7 Citations (Scopus)

106 Downloads (Pure)

Abstract

Software-Defined Networking promises to deliver a more manageable network whose behaviour could be easily changed using applications written in high-level declarative languages running on top of a logically centralized control plane resulting, on the one hand, in the mushrooming of complex point solutions to very specific problems and, on the other hand, in the creation of a multitude of network configuration options. This fact is especially true for 802.11-based Software-Defined WLANs (SD-WLANs). It is our standpoint that to tame this increase in complexity, future SD-WLANs must follow an Artificial Intelligence (AI) native approach. In this paper we present aiOS, an AI-based Operating System for SD-WLANs. Then, we use aiOS to implement several Machine Learning (ML) models for user-adaptive frame length selection in SD-WLANs. An extensive performance evaluation carried out on a real-world testbed shows that this approach improves the aggregated network throughput by up to 55%. Finally, we release the entire implementation including the controller, the ML models, and the programmable data-path under a permissive license for academic use.

Original language	English
Title of host publication	2020 IEEE/IFIP Network Operations and Management Symposium (NOMS 2020)
Subtitle of host publication	Management in the Age of Softwarization and Artificial Intelligence
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	9
ISBN (Electronic)	978-1-7281-4973-8
ISBN (Print)	978-1-7281-4974-5
DOIs	https://doi.org/10.1109/NOMS47738.2020.9110260
Publication status	Published - 8 Jun 2020
Event	17th IEEE/IFIP Network Operations and Management Symposium, NOMS 2020: Management in the Age of Softwarization and Artificial Intelligence - Virtual conference, Budapest, Hungary Duration: 20 Apr 2020 → 24 Apr 2020 Conference number: 17 https://noms2020.ieee-noms.org/ (Conference)

Publication series

Name	IEEE/IFIP Network Operations and Management Symposium (NOMS)
Publisher	IEEE
Volume	2020
ISSN (Print)	1542-1201
ISSN (Electronic)	2374-9709

Conference

Conference	17th IEEE/IFIP Network Operations and Management Symposium, NOMS 2020
Abbreviated title	NOMS
Country/Territory	Hungary
City	Budapest
Period	20/04/20 → 24/04/20
Internet address	https://noms2020.ieee-noms.org/ (Conference)

Keywords

IEEE 802.11
Machine learning
Software-defined networking
WLANs
Aggregation
Frame length selection
22/3 OA procedure

Access to Document

10.1109/NOMS47738.2020.9110260

Coronado2020aiosFinal published version, 1.41 MBLicence: Taverne

Cite this

Estefanía Coronado, Abin Thomas, Bayhan, S., & Roberto Riggio (2020). aiOS: An Intelligence Layer for SD-WLANs. In 2020 IEEE/IFIP Network Operations and Management Symposium (NOMS 2020): Management in the Age of Softwarization and Artificial Intelligence Article 9110260 (IEEE/IFIP Network Operations and Management Symposium (NOMS); Vol. 2020). IEEE. https://doi.org/10.1109/NOMS47738.2020.9110260

@inproceedings{8df6e3ee74684e2f87be6ca958242bd7,

title = "aiOS: An Intelligence Layer for SD-WLANs",

abstract = "Software-Defined Networking promises to deliver a more manageable network whose behaviour could be easily changed using applications written in high-level declarative languages running on top of a logically centralized control plane resulting, on the one hand, in the mushrooming of complex point solutions to very specific problems and, on the other hand, in the creation of a multitude of network configuration options. This fact is especially true for 802.11-based Software-Defined WLANs (SD-WLANs). It is our standpoint that to tame this increase in complexity, future SD-WLANs must follow an Artificial Intelligence (AI) native approach. In this paper we present aiOS, an AI-based Operating System for SD-WLANs. Then, we use aiOS to implement several Machine Learning (ML) models for user-adaptive frame length selection in SD-WLANs. An extensive performance evaluation carried out on a real-world testbed shows that this approach improves the aggregated network throughput by up to 55%. Finally, we release the entire implementation including the controller, the ML models, and the programmable data-path under a permissive license for academic use.",

keywords = "IEEE 802.11, Machine learning, Software-defined networking, WLANs, Aggregation, Frame length selection, 22/3 OA procedure",

author = "{Estefan{\'i}a Coronado} and {Abin Thomas} and Suzan Bayhan and {Roberto Riggio}",

year = "2020",

month = jun,

day = "8",

doi = "10.1109/NOMS47738.2020.9110260",

language = "English",

isbn = "978-1-7281-4974-5",

series = "IEEE/IFIP Network Operations and Management Symposium (NOMS)",

publisher = "IEEE",

booktitle = "2020 IEEE/IFIP Network Operations and Management Symposium (NOMS 2020)",

address = "United States",

note = "17th IEEE/IFIP Network Operations and Management Symposium, NOMS 2020 : Management in the Age of Softwarization and Artificial Intelligence, NOMS ; Conference date: 20-04-2020 Through 24-04-2020",

url = "https://noms2020.ieee-noms.org/",

}

Estefanía Coronado, Abin Thomas, Bayhan, S & Roberto Riggio 2020, aiOS: An Intelligence Layer for SD-WLANs. in 2020 IEEE/IFIP Network Operations and Management Symposium (NOMS 2020): Management in the Age of Softwarization and Artificial Intelligence., 9110260, IEEE/IFIP Network Operations and Management Symposium (NOMS), vol. 2020, IEEE, Piscataway, NJ, 17th IEEE/IFIP Network Operations and Management Symposium, NOMS 2020, Budapest, Hungary, 20/04/20. https://doi.org/10.1109/NOMS47738.2020.9110260

aiOS: An Intelligence Layer for SD-WLANs. / Estefanía Coronado; Abin Thomas ; Bayhan, Suzan et al.
2020 IEEE/IFIP Network Operations and Management Symposium (NOMS 2020): Management in the Age of Softwarization and Artificial Intelligence. Piscataway, NJ: IEEE, 2020. 9110260 (IEEE/IFIP Network Operations and Management Symposium (NOMS); Vol. 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - aiOS: An Intelligence Layer for SD-WLANs

AU - Estefanía Coronado

AU - Abin Thomas

AU - Bayhan, Suzan

AU - Roberto Riggio

N1 - Conference code: 17

PY - 2020/6/8

Y1 - 2020/6/8

N2 - Software-Defined Networking promises to deliver a more manageable network whose behaviour could be easily changed using applications written in high-level declarative languages running on top of a logically centralized control plane resulting, on the one hand, in the mushrooming of complex point solutions to very specific problems and, on the other hand, in the creation of a multitude of network configuration options. This fact is especially true for 802.11-based Software-Defined WLANs (SD-WLANs). It is our standpoint that to tame this increase in complexity, future SD-WLANs must follow an Artificial Intelligence (AI) native approach. In this paper we present aiOS, an AI-based Operating System for SD-WLANs. Then, we use aiOS to implement several Machine Learning (ML) models for user-adaptive frame length selection in SD-WLANs. An extensive performance evaluation carried out on a real-world testbed shows that this approach improves the aggregated network throughput by up to 55%. Finally, we release the entire implementation including the controller, the ML models, and the programmable data-path under a permissive license for academic use.

AB - Software-Defined Networking promises to deliver a more manageable network whose behaviour could be easily changed using applications written in high-level declarative languages running on top of a logically centralized control plane resulting, on the one hand, in the mushrooming of complex point solutions to very specific problems and, on the other hand, in the creation of a multitude of network configuration options. This fact is especially true for 802.11-based Software-Defined WLANs (SD-WLANs). It is our standpoint that to tame this increase in complexity, future SD-WLANs must follow an Artificial Intelligence (AI) native approach. In this paper we present aiOS, an AI-based Operating System for SD-WLANs. Then, we use aiOS to implement several Machine Learning (ML) models for user-adaptive frame length selection in SD-WLANs. An extensive performance evaluation carried out on a real-world testbed shows that this approach improves the aggregated network throughput by up to 55%. Finally, we release the entire implementation including the controller, the ML models, and the programmable data-path under a permissive license for academic use.

KW - IEEE 802.11

KW - Machine learning

KW - Software-defined networking

KW - WLANs

KW - Aggregation

KW - Frame length selection

KW - 22/3 OA procedure

UR - http://www.scopus.com/inward/record.url?scp=85086756366&partnerID=8YFLogxK

U2 - 10.1109/NOMS47738.2020.9110260

DO - 10.1109/NOMS47738.2020.9110260

M3 - Conference contribution

SN - 978-1-7281-4974-5

T3 - IEEE/IFIP Network Operations and Management Symposium (NOMS)

BT - 2020 IEEE/IFIP Network Operations and Management Symposium (NOMS 2020)

PB - IEEE

CY - Piscataway, NJ

T2 - 17th IEEE/IFIP Network Operations and Management Symposium, NOMS 2020

Y2 - 20 April 2020 through 24 April 2020

ER -

Estefanía Coronado, Abin Thomas, Bayhan S, Roberto Riggio. aiOS: An Intelligence Layer for SD-WLANs. In 2020 IEEE/IFIP Network Operations and Management Symposium (NOMS 2020): Management in the Age of Softwarization and Artificial Intelligence. Piscataway, NJ: IEEE. 2020. 9110260. (IEEE/IFIP Network Operations and Management Symposium (NOMS)). doi: 10.1109/NOMS47738.2020.9110260

aiOS: An Intelligence Layer for SD-WLANs

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this