Smart adaptive collision avoidance for IEEE 802.11

Yalda Edalat; Katia Obraczka; Jong Suk Ahn

doi:10.1016/j.adhoc.2021.102721

Smart adaptive collision avoidance for IEEE 802.11

Yalda Edalat, Katia Obraczka, Jong Suk Ahn

Department of Computer Science and Artificial Intelligence

University of California at Santa Cruz

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

In this paper, we introduce a novel algorithm that uses machine learning to dynamically decide whether to enable or disable IEEE 802.11 DCF's RTS/CTS. Our algorithm continuously learns current networking conditions, namely air time, i.e. the ratio between the size of data/control information being transmitted and transmission rate, and network contention to compare the cost between using RTS/CTS or retransmitting data, and dynamically switches RTS/CTS on and off accordingly. Simulation results using a variety of WLAN- as well as wireless multi-hop ad-hoc network scenarios, including synthetic and real traffic traces, demonstrate that the proposed approach consistently outperforms current best practices, such as never enabling RTS/CTS or using a pre-specified threshold to decide whether to switch RTS/CTS on or off.

Original language	English
Article number	102721
Journal	Ad Hoc Networks
Volume	124
DOIs	https://doi.org/10.1016/j.adhoc.2021.102721
State	Published - 1 Jan 2022

Keywords

Congestion avoidance
CSMA/CA
Enabling/disabling RTS/CTS
IEEE 802.11
Machine learning

Access to Document

10.1016/j.adhoc.2021.102721

Cite this

@article{ac187e11e4a14f38bc13fe628276f006,

title = "Smart adaptive collision avoidance for IEEE 802.11",

abstract = "In this paper, we introduce a novel algorithm that uses machine learning to dynamically decide whether to enable or disable IEEE 802.11 DCF's RTS/CTS. Our algorithm continuously learns current networking conditions, namely air time, i.e. the ratio between the size of data/control information being transmitted and transmission rate, and network contention to compare the cost between using RTS/CTS or retransmitting data, and dynamically switches RTS/CTS on and off accordingly. Simulation results using a variety of WLAN- as well as wireless multi-hop ad-hoc network scenarios, including synthetic and real traffic traces, demonstrate that the proposed approach consistently outperforms current best practices, such as never enabling RTS/CTS or using a pre-specified threshold to decide whether to switch RTS/CTS on or off.",

keywords = "Congestion avoidance, CSMA/CA, Enabling/disabling RTS/CTS, IEEE 802.11, Machine learning",

author = "Yalda Edalat and Katia Obraczka and Ahn, \{Jong Suk\}",

note = "Publisher Copyright: {\textcopyright} 2021 The Authors",

year = "2022",

month = jan,

day = "1",

doi = "10.1016/j.adhoc.2021.102721",

language = "English",

volume = "124",

journal = "Ad Hoc Networks",

issn = "1570-8705",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Smart adaptive collision avoidance for IEEE 802.11

AU - Edalat, Yalda

AU - Obraczka, Katia

AU - Ahn, Jong Suk

PY - 2022/1/1

Y1 - 2022/1/1

N2 - In this paper, we introduce a novel algorithm that uses machine learning to dynamically decide whether to enable or disable IEEE 802.11 DCF's RTS/CTS. Our algorithm continuously learns current networking conditions, namely air time, i.e. the ratio between the size of data/control information being transmitted and transmission rate, and network contention to compare the cost between using RTS/CTS or retransmitting data, and dynamically switches RTS/CTS on and off accordingly. Simulation results using a variety of WLAN- as well as wireless multi-hop ad-hoc network scenarios, including synthetic and real traffic traces, demonstrate that the proposed approach consistently outperforms current best practices, such as never enabling RTS/CTS or using a pre-specified threshold to decide whether to switch RTS/CTS on or off.

AB - In this paper, we introduce a novel algorithm that uses machine learning to dynamically decide whether to enable or disable IEEE 802.11 DCF's RTS/CTS. Our algorithm continuously learns current networking conditions, namely air time, i.e. the ratio between the size of data/control information being transmitted and transmission rate, and network contention to compare the cost between using RTS/CTS or retransmitting data, and dynamically switches RTS/CTS on and off accordingly. Simulation results using a variety of WLAN- as well as wireless multi-hop ad-hoc network scenarios, including synthetic and real traffic traces, demonstrate that the proposed approach consistently outperforms current best practices, such as never enabling RTS/CTS or using a pre-specified threshold to decide whether to switch RTS/CTS on or off.

KW - Congestion avoidance

KW - CSMA/CA

KW - Enabling/disabling RTS/CTS

KW - IEEE 802.11

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85118510845&partnerID=8YFLogxK

U2 - 10.1016/j.adhoc.2021.102721

DO - 10.1016/j.adhoc.2021.102721

M3 - Article

AN - SCOPUS:85118510845

SN - 1570-8705

VL - 124

JO - Ad Hoc Networks

JF - Ad Hoc Networks

M1 - 102721

ER -

Smart adaptive collision avoidance for IEEE 802.11

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this