Improving mmWave backhaul reliability: A machine-learning based approach

Ferreira, Tânia; Figueiredo, Alexandre; Raposo, Duarte; Luís, Miguel; Rito, Pedro; Sargento, Susana

doi:10.1016/j.adhoc.2022.103050

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows the adoption of a FR1 or a FR2 backhaul link and address other aspects not taken into consideration in this work, including a comparison in terms of performance, complexity, and cost. Finally, we believe that the designed platform provides a cost-effective, scalable, and easy-to-upgrade solution for enabling other 5G signals standardized by the 3GPP, as well as, novel 5G as MIMO, beamforming techniques, and deeplearning based approach [49] in mmWave frequency bands.…”

Section: Discussionmentioning

confidence: 99%

A Flexible mmWave Layer 2 Protocol Implementation for Integrated Access and Backhaul Architecture

2023

View full text Add to dashboard Cite

In this paper, we present a 3GPP-inspired hardware implementation for the out-of-band Integrated Access and Backhaul (IAB) network, which serves as a solution to both coverage extension and capacity boosting in 5G and beyond networks. By employing an Ettus x310 software-defined radio (SDR) board, Pasternack's 60 GHz Transmitter (Tx) waveguide module, and Matlab TM software, we design and develop an easy-to-use out-of-band mmWave Layer 2 protocol. The proposed protocol decodes a frequency range 1 (FR1) 5G signal as input at 3.5 GHz, which is retransmitted to the UE as a frequency range 2 (FR2) 5G signal at 60 GHz. In the implementation of the Layer 2 protocol, the least squares (LS) estimator is adopted by considering the demodulation reference signal (DM-RS) and the channel state information reference signal (CSI-RS) as pilot symbols in real-world environments. To alleviate the performance degradation in the mmWave access link, a phase noise cancellation (PNC) algorithm based on the phase tracking reference signal (PT-RS) is implemented at the UE node where a PT-RS block structure is introduced in the mmWave Layer 2 protocol transmitter stage. We review and evaluate the key performance indicators (KPIs) of the proposed Layer 2 protocol in real non-line-of-sight (NLOS) environments and a comparison between the gNode-to-UE link is carried out. Our results indicate that the performance of the proposed Layer 2 protocol is similar to the obtained with the off-the-shelf equipment demonstrating the right functionality of the developed algorithms. Experimental results evidence the superiority of the proposed Layer 2 protocol over the gNodeB-to-UE link (direct link communication) and the best performance is obtained when the PNC algorithm is considered in the IAB architecture.

show abstract

Section: Discussionmentioning

confidence: 99%

A Flexible mmWave Layer 2 Protocol Implementation for Integrated Access and Backhaul Architecture

2023

View full text Add to dashboard Cite

show abstract

“… Future use: The dataset provided allows defining the impact of both long-term and short-term obstructions on mmWave-based WiGig networks, as explored in [2] . It has also supported the development of a proactive machine learning framework [3] in an outdoor setting [ 4 ], leveraging real-life data to enhance the reliability and resilience of WiGig-based networks that are prone to blockages. This includes a link quality classifier that can differentiate normal operation from long-term and short-term blockages, as well as a deep learning forecasting model that accurately predicts relevant link metrics ahead of time.…”

Section: Value Of the Datamentioning

confidence: 99%

Experimental mmWave WiGig-based backhaul network dataset

Ferreira,

Raposo,

Figueiredo

et al. 2024

Data in Brief

Self Cite

View full text Add to dashboard Cite

“…These mmWave antennas are a part of a testbed from previous research projects, being a part of a mmWave mesh network [60], for flexibility in assembling the small cells in different locations.…”

Section: Testbed Overviewmentioning

confidence: 99%

Disaggregated Mobile Core for Edge City Services

Valente

Raposo

Rito

et al. 2023

2023 IEEE 24th International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)

View full text Add to dashboard Cite

As redes de comunicações móveis evoluíram significativamente ao longo dos anos. A evolução atual (5G) enfrenta um aumento do número de equipamentos e de aplicações com alto consumo de dados, crescendo assim a necessidade de uma densificação da rede. Para resolver este problema, e otimizar a infra-estrutura de uma rede de comunicações 5G, deverá levar-se a cargo o desenvolvimento de uma rede unificada e partilhada, para que nesta possam ser implementadas redes de múltiplos operadores. Com uma rede planeada e partilhada pelos operadores, começam a ser pensadas diferentes formas de tirar o máximo partido da arquitectura. Considerando vários serviços, como Vehicle-to-Everything (V2X) e Internet-of-Things (IoT). É aqui que surgem tópicos como Multi-Acess Edge Computing (MEC), que podem fornecer formas de maximizar a exploração de uma infra-estrutura de cidade de forma a reduzir latências e remover esforço computacional dos servidores na cloud para o edge. Esta dissertação centra-se no desenvolvimento de uma arquitectura neutra para redes 5G com Multi-acess Edge Computing (MEC), com o propósito de ser implementada numa cidade inteligente. No caso concreto desta dissertação, a arquitetura será preparada para ser implementada na cidade de Aveiro, tirando partido dos múltiplos edge nodes e serviços que já possui. A desagregação da Rede do Core (CN) é um ponto fulcral desta dissertação, criando uma forma de ter a gateway mais próxima do edge, permitindo assim que tecnologias MEC melhorem a experiência do utilizador e a performance dos serviços existentes. Foi concebida e implementada uma testbed real para simular com precisão o ambiente da cidade e comprovar a arquitetura concebida para os serviços mencionados. Os cenários de teste envolveram a comparação de um serviço instanciado na cloud e no edge, cenários de mobilidade com handover para verificar a relocalização do user plane e, por último, a garantia de Qualidade de Serviço (QoS) para serviços de maior prioridade num cenário de ocupação de toda a largura de banda. Os resultados obtidos demonstram melhorias tanto no tráfego comum do utilizador como no tráfego orientado a serviços; além disso, este trabalho também descreve e testa as capacidades do core utilizado, bem como as suas limitações, proporcionando uma base para trabalhos futuros.

show abstract

Improving mmWave backhaul reliability: A machine-learning based approach

Cited by 4 publications

References 12 publications

A Flexible mmWave Layer 2 Protocol Implementation for Integrated Access and Backhaul Architecture

A Flexible mmWave Layer 2 Protocol Implementation for Integrated Access and Backhaul Architecture

Experimental mmWave WiGig-based backhaul network dataset

Disaggregated Mobile Core for Edge City Services

Contact Info

Product

Resources

About