Post-CCA and Reinforcement Learning Based Bandwidth Adaptation in 802.11ac Networks

Jang, Seowoo; Shin, Kang G.; Bahk, Saewoong

doi:10.1109/tmc.2017.2709309

Cited by 30 publications

(17 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…E necessário analisar o impacto nos requisitos de tráfego ao utilizar IEEE 802.11ac quando há sobreposição de canais, visto que o uso de bandas maiores influencia diretamente a eficiência de transmissão no ambiente. Apesar do problema da sobreposição de canais ter sido tratado por [Jang et al 2018], este autores não avaliaram o efeito sobre a latência. Este tópico pode ser tratado em uma etapa seguinte do presente trabalho.…”

Section: Resultsunclassified

Alocação dinâmica de largura de banda para redes sem fio infraestruturadas

Guimaraes

Moura

Vieira

et al. 2019

Anais Do XXXVII Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2019)

View full text Add to dashboard Cite

A demanda por redes sem fio tem crescido nos últimos anos, isto implica em uma maior necessidade de melhoria em seu desempenho. O padrão IEEE 802.11ac permite utilizar canais com largura de banda maiores que 20 MHz. Porém, os pontos de acesso alocam a largura de banda do canal estaticamente, independente das configurações dos clientes. Isso leva a um baixo desempenho da rede. Neste trabalho, propomos um sistema que permite aos clientes escolherem a largura de banda para se conectar aos pontos de acesso. O sistema foi validado através de experimentos reais. Destacamos o compromisso entre latência e vazão. Os resultados mostram que nosso sistema melhora o uso do espectro de frequência.

show abstract

Section: Resultsunclassified

Alocação dinâmica de largura de banda para redes sem fio infraestruturadas

Guimaraes

Moura

Vieira

et al. 2019

Anais Do XXXVII Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2019)

View full text Add to dashboard Cite

show abstract

“…Various variants such as 802.11a/b/g/n or 802.11ad are other standards in the whole series, and they define distinct types of products. Through the release of updated variants, the overall technology has been able to meet the growing request for more data and higher speeds [46]. Furthermore, two other types of WLAN networks can be built using Wi-Fi systems, namely infrastructure networks, and adhoc networks.…”

Section: A Reference Architecturementioning

confidence: 99%

Cooperative Robotics and Machine Learning for Smart Manufacturing: Platform Design and Trends Within the Context of Industrial Internet of Things

Lins

Givigi

2021

IEEE Access

View full text Add to dashboard Cite

Internet of Things (IoT) in industrial settings now leads to the development of a new generation of systems designed to improve the operational efficiency of the new paradigm of smart manufacturing plants. Thereby, the current article introduces in detail the definitions, concepts, standards, and other important aspects related to smart manufacturing, cooperative robotics, and Machine Learning techniques (ML). The paper highlights the opportunities presented by the new paradigm and the challenges faced in effectively implementing it in the industrial context. Especially, the focus is on the challenges associated with the architectures, communications technology, and protocols that enable the integration and deployment of machine learning algorithms to improve the execution of tasks daily performed by the collaboration of human operators, machines, and robots. Finally, it also provides a systematic review of state-of-the-art research efforts for the fields aforementioned, and a designed platform for integrating collaborative robotics and machine learning established on six layers and four hierarchies of the RAMI 4.0 (Reference Architectural Model Industry 4.0) is presented.

show abstract

“…Other papers tackle specific releases of the 802.11 standard. For instance [15] enhances channel assessment capabilities in 802.11ac networks by altering the bandwidth and channel configuration using RL; while in [17], the MCS and frame size in a 802.11n network are jointly optimized with RL. Both papers rely on a period of interaction with the environment that is stable and sufficiently long to provide the optimal solution.…”

Section: Related Workmentioning

confidence: 99%

“…However changing the bandwidth in a dynamic way creates a tradeoff in transmission range and probability of interference. [15] proposes as a potential solution a careful balance between the clear channel assessment (CCA) sensitivity level, the modulation and coding scheme (MCS) and the transmit power (TxP). Therefore our DDQN agent tries to achieve the required rate by configuring these parameters for each network slice together.…”

Section: B Parameter Selectionmentioning

confidence: 99%

Deep Reinforcement Learning for Dynamic Network Slicing in IEEE 802.11 Networks

Bast

Torrea-Duran

Chiumento

et al. 2019

IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

View full text Add to dashboard Cite

Network slicing, a key enabler for future wireless networks, divides a physical network into multiple logical networks that can be dynamically created and configured. In current IEEE 802.11 (Wi-Fi) networks, the only form of network configuration is a rule-based optimization of few parameters. Future access points (APs) are expected to have self-organizational capabilities, able to deal with large configuration spaces in order to dynamically configure each slice. Deep Reinforcement Learning (DRL) can achieve promising results in highly dynamic and complex environments without the need for an operating model, by learning the optimal strategy after interacting with the environment. However, since the number of possible slice configurations is huge, achieving the optimal strategy requires an exhaustive learning period that might yield an outdated slice configuration. In this paper, we propose a fast-learning DRL model that can dynamically optimize the slice configuration of unplanned Wi-Fi networks without expert knowledge. Enhanced with an off-line learning step, the proposed approach is able to achieve the optimal slice configuration with a fast convergence, which is attractive for dynamic scenarios.

show abstract

Post-CCA and Reinforcement Learning Based Bandwidth Adaptation in 802.11ac Networks

Cited by 30 publications

References 19 publications

Alocação dinâmica de largura de banda para redes sem fio infraestruturadas

Alocação dinâmica de largura de banda para redes sem fio infraestruturadas

Cooperative Robotics and Machine Learning for Smart Manufacturing: Platform Design and Trends Within the Context of Industrial Internet of Things

Deep Reinforcement Learning for Dynamic Network Slicing in IEEE 802.11 Networks

Contact Info

Product

Resources

About