A carregar...
Projeto de investigação
Distributed Access Design for Cell-less Smart 6G Networks
Financiador
Autores
Publicações
Estimation of 5G Core and RAN End-to-End Delay through Gaussian Mixture Models
Publication . Fadhil, Diyar; Oliveira, Rodolfo; DEE - Departamento de Engenharia Electrotécnica e de Computadores; MDPI - Multidisciplinary Digital Publishing Institute
Network analytics provide a comprehensive picture of the network’s Quality of Service (QoS), including the End-to-End (E2E) delay. In this paper, we characterize the Core and the Radio Access Network (RAN) E2E delay of 5G networks with the Standalone (SA) and Non-Standalone (NSA) topologies when a single known Probability Density Function (PDF) is not suitable to model its distribution. To this end, multiple PDFs, denominated as components, are combined in a Gaussian Mixture Model (GMM) to represent the distribution of the E2E delay. The accuracy and computation time of the GMM is evaluated for a different number of components and a number of samples. The results presented in the paper are based on a dataset of E2E delay values sampled from both SA and NSA 5G networks. Finally, we show that the GMM can be adopted to estimate a high diversity of E2E delay patterns found in 5G networks and its computation time can be adequate for a large range of applications.
Survey on Context-Aware Radio Frequency-Based Sensing
Publication . Casmin, Eugene; Oliveira, Rodolfo; DEE - Departamento de Engenharia Electrotécnica e de Computadores; MDPI - Multidisciplinary Digital Publishing Institute
Radio frequency (RF) spectrum sensing is critical for applications requiring precise object and posture detection and classification. This survey aims to provide a focused review of context-aware RF-based sensing, emphasizing its principles, advancements, and challenges. It specifically examines state-of-the-art techniques such as phased array radar, synthetic aperture radar, and passive RF sensing, highlighting their methodologies, data input domains, and spatial diversity strategies. The paper evaluates feature extraction methods and machine learning approaches used for detection and classification, presenting their accuracy metrics across various applications. Additionally, it investigates the integration of RF sensing with other modalities, such as inertial sensors, to enhance context awareness and improve performance. Challenges like environmental interference, scalability, and regulatory constraints are addressed, with insights into real-world mitigation strategies. The survey concludes by identifying emerging trends, practical applications, and future directions for advancing RF sensing technologies.
A Flexible mmWave Layer 2 Protocol Implementation for Integrated Access and Backhaul Architecture
Publication . Verdecia-Pena, Randy; Oliveira, Rodolfo; Alonso, Jose I.; DEE - Departamento de Engenharia Electrotécnica e de Computadores; Institute of Electrical and Electronics Engineers (IEEE)
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 MatlabTM 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.
Nonlinear Effects in NOMA Systems Using Single Carrier Modulations
Publication . Ben Haj Belkacem, Oussama; Dinis, Rui; Ammari, Mohamed Lassaad; Faculdade de Ciências e Tecnologia (FCT); Institute of Electrical and Electronics Engineers (IEEE)
Non orthogonal multiple access (NOMA) systems are very important for future communications which allows a huge increase in capacity gains when comparing to conventional orthogonal multiple access (OMA) techniques. On the other hand, the power consumption at the access point (AP) should be as low as possible, making single-carrier (SC) schemes, such as single carrier with frequency-domain equalization (SC-FDE), particularly interesting. In this paper, we consider power-efficient NOMA systems employing SC-FDE signals and present a generalized framework to characterize the signals at the output of a nonlinear device. We develop an accurate estimation of the power spectral density (PSD) of the signal associated to each user, showing that the nonlinear distortion effects on some users can be very high. Therefore, we introduce a joint iterative receiver for distortion compensation and interference cancellation based on SC-FDE characterized by low-complexity suitable for scenarios with strong nonlinear effects. Our performance results indicate that the proposed technique is able to reduce considerably the degradation associated to a high power amplifier (HPA) modeled as a memoryless polynomial and allow complexity improvements when compared to conventional schemes, especially when operating at low input back-off (IBO).
Real-time Physical Layer Authentication on ZigBee networks
Publication . Cordeiro, Leandro Correia; Bernardo, Luís
The rapid expansion of the Internet of Things (IoT) raises significant security concerns,
especially for device authentication. This thesis focuses on Physical Layer (PHY) authenti-
cation through Radio Frequency Fingerprinting (RFF), using machine learning algorithms
implemented with Software Defined Radio (SDR).
A custom and extended GNU Radio module was developed to capture ZigBee frames
and extract the preamble. The system employed a One-Dimension Convolutional (Conv1D)
Autoencoders (AE) Neural Network (NN) with a dimension of 12 to generate features,
which were subsequently used to train a Random Forest (RF) classifier.
A prototype application was developed to implement the RFF algorithms in real-time.
The application’s graphical user interface supports the training of the RF classifier and
enables real-time classification of IEEE 802.15.4 signals. The application provides an
intuitive platform for users to train models, integrate new sensors, and perform real-time
classifications efficiently.
Results demonstrated that the system performed best in static conditions, achieving an
F1-score of 97% when the training and testing conditions were aligned at a distance of 15 cm.
However, as the distance increased, performance declined, with the F1-score dropping to
90% at 1 meter and further decreasing to 89% when movement was introduced. Tests with
different antennas and Low-Noise Amplifier (LNA)s from the same manufacturer showed
no significant impact on performance. However, changing the testing environment, which
inherently involved changing communication channels, led to a noticeable decrease in
accuracy.
In conclusion, this thesis shows that Machine Learning (ML)-based PHY layer authen-
tication is feasible and effective with aligned training and testing conditions.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
3599-PPCDT
Número da atribuição
2022.08786.PTDC