The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Os serviços de transmissão para redes locais sem fio (WLANs) estão sendo padronizados no grupo de tarefas IEEE 802.11 bc. Prevendo a futura coexistência de pontos de acesso de transmissão (APs) com APs legados densamente implantados, este artigo aborda uma reutilização espacial baseada em aprendizagem com reconhecimento apenas parcial do receptor. Este reconhecimento parcial significa que os APs de transmissão podem aproveitar poucos quadros de confirmação (ACKs) das estações receptoras (STAs). Isto tem em vista as preocupações específicas das comunicações de radiodifusão. Nas comunicações de difusão para um grande número de STAs, ocorrem implosões de ACK, a menos que algumas STAs sejam impedidas de responder com ACKs. Diante disso, a principal contribuição deste artigo é demonstrar a viabilidade de melhorar a robustez da reutilização espacial baseada em aprendizagem para interferentes ocultos apenas com o reconhecimento parcial do receptor, descartando qualquer retreinamento de APs de transmissão. A ideia central é aproveitar o aprendizado de reforço adversário robusto (RARL), onde antes de uma interferência oculta ser instalada, um AP de transmissão aprende uma política de adaptação de taxa em uma competição com um interferente proxy que fornece sinais de interferência de forma inteligente. Nesse caso, as STAs receptoras sofrem interferência e as STAs parciais fornecem um feedback que superestima o efeito da interferência, permitindo que o AP de transmissão selecione uma taxa de dados para evitar perdas de quadros em uma ampla gama de STAs receptoras. Simulações demonstram a supressão da degradação do rendimento sob a instalação repentina de uma interferência oculta, indicando a viabilidade de aquisição de robustez para a interferência oculta.
Yuto KIHIRA
https://orcid.org/0000-0003-3344-7370
Kyoto University
Yusuke KODA
https://orcid.org/0000-0003-4106-3983
University of Oulu
Koji YAMAMOTO
https://orcid.org/0000-0003-1026-319X
Kyoto University
Takayuki NISHIO
Kyoto University,Tokyo Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Yuto KIHIRA, Yusuke KODA, Koji YAMAMOTO, Takayuki NISHIO, "Adversarial Reinforcement Learning-Based Coordinated Robust Spatial Reuse in Broadcast-Overlaid WLANs" in IEICE TRANSACTIONS on Communications,
vol. E106-B, no. 2, pp. 203-212, February 2023, doi: 10.1587/transcom.2022EBP3026.
Abstract: Broadcast services for wireless local area networks (WLANs) are being standardized in the IEEE 802.11 task group bc. Envisaging the upcoming coexistence of broadcast access points (APs) with densely-deployed legacy APs, this paper addresses a learning-based spatial reuse with only partial receiver-awareness. This partial awareness means that the broadcast APs can leverage few acknowledgment frames (ACKs) from recipient stations (STAs). This is in view of the specific concerns of broadcast communications. In broadcast communications for a very large number of STAs, ACK implosions occur unless some STAs are stopped from responding with ACKs. Given this, the main contribution of this paper is to demonstrate the feasibility to improve the robustness of learning-based spatial reuse to hidden interferers only with the partial receiver-awareness while discarding any re-training of broadcast APs. The core idea is to leverage robust adversarial reinforcement learning (RARL), where before a hidden interferer is installed, a broadcast AP learns a rate adaptation policy in a competition with a proxy interferer that provides jamming signals intelligently. Therein, the recipient STAs experience interference and the partial STAs provide a feedback overestimating the effect of interference, allowing the broadcast AP to select a data rate to avoid frame losses in a broad range of recipient STAs. Simulations demonstrate the suppression of the throughput degradation under a sudden installation of a hidden interferer, indicating the feasibility of acquiring robustness to the hidden interferer.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2022EBP3026/_p
Copiar
@ARTICLE{e106-b_2_203,
author={Yuto KIHIRA, Yusuke KODA, Koji YAMAMOTO, Takayuki NISHIO, },
journal={IEICE TRANSACTIONS on Communications},
title={Adversarial Reinforcement Learning-Based Coordinated Robust Spatial Reuse in Broadcast-Overlaid WLANs},
year={2023},
volume={E106-B},
number={2},
pages={203-212},
abstract={Broadcast services for wireless local area networks (WLANs) are being standardized in the IEEE 802.11 task group bc. Envisaging the upcoming coexistence of broadcast access points (APs) with densely-deployed legacy APs, this paper addresses a learning-based spatial reuse with only partial receiver-awareness. This partial awareness means that the broadcast APs can leverage few acknowledgment frames (ACKs) from recipient stations (STAs). This is in view of the specific concerns of broadcast communications. In broadcast communications for a very large number of STAs, ACK implosions occur unless some STAs are stopped from responding with ACKs. Given this, the main contribution of this paper is to demonstrate the feasibility to improve the robustness of learning-based spatial reuse to hidden interferers only with the partial receiver-awareness while discarding any re-training of broadcast APs. The core idea is to leverage robust adversarial reinforcement learning (RARL), where before a hidden interferer is installed, a broadcast AP learns a rate adaptation policy in a competition with a proxy interferer that provides jamming signals intelligently. Therein, the recipient STAs experience interference and the partial STAs provide a feedback overestimating the effect of interference, allowing the broadcast AP to select a data rate to avoid frame losses in a broad range of recipient STAs. Simulations demonstrate the suppression of the throughput degradation under a sudden installation of a hidden interferer, indicating the feasibility of acquiring robustness to the hidden interferer.},
keywords={},
doi={10.1587/transcom.2022EBP3026},
ISSN={1745-1345},
month={February},}
Copiar
TY - JOUR
TI - Adversarial Reinforcement Learning-Based Coordinated Robust Spatial Reuse in Broadcast-Overlaid WLANs
T2 - IEICE TRANSACTIONS on Communications
SP - 203
EP - 212
AU - Yuto KIHIRA
AU - Yusuke KODA
AU - Koji YAMAMOTO
AU - Takayuki NISHIO
PY - 2023
DO - 10.1587/transcom.2022EBP3026
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 2
JA - IEICE TRANSACTIONS on Communications
Y1 - February 2023
AB - Broadcast services for wireless local area networks (WLANs) are being standardized in the IEEE 802.11 task group bc. Envisaging the upcoming coexistence of broadcast access points (APs) with densely-deployed legacy APs, this paper addresses a learning-based spatial reuse with only partial receiver-awareness. This partial awareness means that the broadcast APs can leverage few acknowledgment frames (ACKs) from recipient stations (STAs). This is in view of the specific concerns of broadcast communications. In broadcast communications for a very large number of STAs, ACK implosions occur unless some STAs are stopped from responding with ACKs. Given this, the main contribution of this paper is to demonstrate the feasibility to improve the robustness of learning-based spatial reuse to hidden interferers only with the partial receiver-awareness while discarding any re-training of broadcast APs. The core idea is to leverage robust adversarial reinforcement learning (RARL), where before a hidden interferer is installed, a broadcast AP learns a rate adaptation policy in a competition with a proxy interferer that provides jamming signals intelligently. Therein, the recipient STAs experience interference and the partial STAs provide a feedback overestimating the effect of interference, allowing the broadcast AP to select a data rate to avoid frame losses in a broad range of recipient STAs. Simulations demonstrate the suppression of the throughput degradation under a sudden installation of a hidden interferer, indicating the feasibility of acquiring robustness to the hidden interferer.
ER -