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
A comunicação máquina a máquina (M2M) desempenha um papel fundamental na evolução da Internet das Coisas (IoT). As redes celulares são consideradas um facilitador chave para comunicações M2M, que são originalmente projetadas principalmente para comunicações entre humanos (H2H). A introdução de usuários M2M causará uma série de problemas aos usuários H2H tradicionais, ou seja, interferência entre diversos tráfegos. A alocação de recursos é uma solução eficaz para esses problemas. Neste artigo, consideramos um bloco de recursos compartilhados (RB) e alocação de energia em um cenário de coexistência H2H/M2M, onde os usuários M2M são subdivididos em tipos tolerantes e sensíveis a atrasos. Primeiro modelamos o problema de alocação de energia RB como maximização da capacidade sob restrições de Qualidade de Serviço (QoS) de diferentes tipos de tráfego. Em seguida, é introduzida uma estrutura de aprendizagem, na qual um agente complexo é construído a partir de subagentes mais simples, o que fornece a base para o esquema de implantação distribuída. Além disso, propusemos um algoritmo de alocação de energia RB autônomo baseado em Q-learning distribuído (DQ-ARPA), que permite que os gateways de rede do tipo máquina (MTCG) como agentes aprendam o ambiente sem fio e escolham a potência RB de forma autônoma para maximizar os pares M2M. capacidade, garantindo ao mesmo tempo os requisitos de QoS de serviços críticos. Os resultados da simulação indicam que, com um projeto de recompensa apropriado, nosso esquema proposto consegue reduzir o impacto dos usuários do tipo máquina tolerante a atrasos em serviços críticos em termos de limites de SINR e taxas de interrupção.
Xing WEI
Beijing Information Science and Technology University
Xuehua LI
Beijing Information Science and Technology University
Shuo CHEN
Beijing Information Science and Technology University
Na LI
the Baicells Technologies, Co., Ltd.
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
Xing WEI, Xuehua LI, Shuo CHEN, Na LI, "Reinforcement Learning for QoS-Constrained Autonomous Resource Allocation with H2H/M2M Co-Existence in Cellular Networks" in IEICE TRANSACTIONS on Communications,
vol. E105-B, no. 11, pp. 1332-1341, November 2022, doi: 10.1587/transcom.2021TMP0011.
Abstract: Machine-to-Machine (M2M) communication plays a pivotal role in the evolution of Internet of Things (IoT). Cellular networks are considered to be a key enabler for M2M communications, which are originally designed mainly for Human-to-Human (H2H) communications. The introduction of M2M users will cause a series of problems to traditional H2H users, i.e., interference between various traffic. Resource allocation is an effective solution to these problems. In this paper, we consider a shared resource block (RB) and power allocation in an H2H/M2M coexistence scenario, where M2M users are subdivided into delay-tolerant and delay-sensitive types. We first model the RB-power allocation problem as maximization of capacity under Quality-of-Service (QoS) constraints of different types of traffic. Then, a learning framework is introduced, wherein a complex agent is built from simpler subagents, which provides the basis for distributed deployment scheme. Further, we proposed distributed Q-learning based autonomous RB-power allocation algorithm (DQ-ARPA), which enables the machine type network gateways (MTCG) as agents to learn the wireless environment and choose the RB-power autonomously to maximize M2M pairs' capacity while ensuring the QoS requirements of critical services. Simulation results indicates that with an appropriate reward design, our proposed scheme succeeds in reducing the impact of delay-tolerant machine type users on critical services in terms of SINR thresholds and outage ratios.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2021TMP0011/_p
Copiar
@ARTICLE{e105-b_11_1332,
author={Xing WEI, Xuehua LI, Shuo CHEN, Na LI, },
journal={IEICE TRANSACTIONS on Communications},
title={Reinforcement Learning for QoS-Constrained Autonomous Resource Allocation with H2H/M2M Co-Existence in Cellular Networks},
year={2022},
volume={E105-B},
number={11},
pages={1332-1341},
abstract={Machine-to-Machine (M2M) communication plays a pivotal role in the evolution of Internet of Things (IoT). Cellular networks are considered to be a key enabler for M2M communications, which are originally designed mainly for Human-to-Human (H2H) communications. The introduction of M2M users will cause a series of problems to traditional H2H users, i.e., interference between various traffic. Resource allocation is an effective solution to these problems. In this paper, we consider a shared resource block (RB) and power allocation in an H2H/M2M coexistence scenario, where M2M users are subdivided into delay-tolerant and delay-sensitive types. We first model the RB-power allocation problem as maximization of capacity under Quality-of-Service (QoS) constraints of different types of traffic. Then, a learning framework is introduced, wherein a complex agent is built from simpler subagents, which provides the basis for distributed deployment scheme. Further, we proposed distributed Q-learning based autonomous RB-power allocation algorithm (DQ-ARPA), which enables the machine type network gateways (MTCG) as agents to learn the wireless environment and choose the RB-power autonomously to maximize M2M pairs' capacity while ensuring the QoS requirements of critical services. Simulation results indicates that with an appropriate reward design, our proposed scheme succeeds in reducing the impact of delay-tolerant machine type users on critical services in terms of SINR thresholds and outage ratios.},
keywords={},
doi={10.1587/transcom.2021TMP0011},
ISSN={1745-1345},
month={November},}
Copiar
TY - JOUR
TI - Reinforcement Learning for QoS-Constrained Autonomous Resource Allocation with H2H/M2M Co-Existence in Cellular Networks
T2 - IEICE TRANSACTIONS on Communications
SP - 1332
EP - 1341
AU - Xing WEI
AU - Xuehua LI
AU - Shuo CHEN
AU - Na LI
PY - 2022
DO - 10.1587/transcom.2021TMP0011
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E105-B
IS - 11
JA - IEICE TRANSACTIONS on Communications
Y1 - November 2022
AB - Machine-to-Machine (M2M) communication plays a pivotal role in the evolution of Internet of Things (IoT). Cellular networks are considered to be a key enabler for M2M communications, which are originally designed mainly for Human-to-Human (H2H) communications. The introduction of M2M users will cause a series of problems to traditional H2H users, i.e., interference between various traffic. Resource allocation is an effective solution to these problems. In this paper, we consider a shared resource block (RB) and power allocation in an H2H/M2M coexistence scenario, where M2M users are subdivided into delay-tolerant and delay-sensitive types. We first model the RB-power allocation problem as maximization of capacity under Quality-of-Service (QoS) constraints of different types of traffic. Then, a learning framework is introduced, wherein a complex agent is built from simpler subagents, which provides the basis for distributed deployment scheme. Further, we proposed distributed Q-learning based autonomous RB-power allocation algorithm (DQ-ARPA), which enables the machine type network gateways (MTCG) as agents to learn the wireless environment and choose the RB-power autonomously to maximize M2M pairs' capacity while ensuring the QoS requirements of critical services. Simulation results indicates that with an appropriate reward design, our proposed scheme succeeds in reducing the impact of delay-tolerant machine type users on critical services in terms of SINR thresholds and outage ratios.
ER -