Pasar al contenido principal

BOND2: B6G NON-CELLULAR TECHNOLOGIES FOR EXTREMELY DYNAMIC 3D NETWORKS

PID2023-148214OB-C22

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE VIGO

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Improving WAF detection capabilities through machine learning algorithms in open‐source technologies

  • Otero Mosquera, Javier
  • López Bravo, Cristina
  • Tubío Figueira, Pedro
  • García de la Iglesia, Alejandro Ignacio
The number of companies offering their services online has grown enormously in recent years. Customer confidence in these web applications is, therefore, vital. However, the number of attacks on these sites has also multiplied exponentially, requiring the use of new tools to prevent and defend against them. In this scenario, web application firewalls (WAFs) are emerging as one of the main defenses against website attacks. Their goal is to block those requests that could be considered malicious. Most WAFs are based on filtering requests using regular expressions; nevertheless, this approach has many difficulties in dealing with issues such as detecting zero‐day vulnerabilities or replay attacks and requires frequent and exhaustive updates. Thanks to advances in machine learning techniques, it is now possible to simplify the update process and combine manually configured rules with learned rules. In this work, we present a solution for the open‐source WAF Shadow Daemon that incorporates a machine learning module for attack detection. The proposed solution improves the detection capability of Shadow Daemon while keeping the latency of the detection process within limits that allow for pleasant interaction with users., Xunta de Galicia | Ref. ED431C 2022/04, Agencia Estatal de Investigación | Ref. BOND2 PID2023-148214OB-C22
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Real-time SARIMA-based anomaly detection in operator networks

  • Fondo Ferreiro, Pablo
  • Rodelgo Lacruz, Miguel
  • González Castaño, Francisco Javier
  • Gil Castiñeira, Felipe Jose
  • Zamorano Pinal, Carlos
  • Candal Ventureira, David
The growing complexity of telecommunication networks increases the need for automated monitoring and detection of incidents. The increasing amount of data generated by current information and communication technologies equipment can be used to identify abnormal behavior and detect anomalies. In this paper, we propose a volume-based real-time solution for anomaly detection in operator networks. The proposal is based on a seasonal autoregressive integrated moving average (SARIMA) forecasting of time-series data, and the identification of outliers. We validate the proposed solution using real traffic traces from a nationwide operator’s network which we make publicly available. Our experimental results show that the proposed solution outperforms baseline approaches in terms of precision, being able to substantially reduce the amount of false positives, while maintaining the same level of recall., Xunta de Galicia, Spain | Ref. ED481B 2022/019, Xunta de Galicia, Spain | Ref. ED431C 2022/04, Agencia Estatal de Investigación | Ref. PID2023-148214OB-C22, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Simulating a quantum switch with concurrent demands

  • Fernández‐Herrerín Álvarez, Juan
  • González Castaño, Francisco Javier
  • Fernández Vilas, Ana
Quantum networks rely on entanglement distribution to enable secure communication and distributed quantum computation. Most analytical models address idealized, single-flow scenarios and overlook the impact of concurrent entanglement requests, limiting their applicability to realistic network conditions. This work studies the behavior of a quantum switch under simultaneous entanglement demands, motivated by the need to understand how concurrency affects link utilization, generation rate, and end-to-end fidelity. Our main contribution is a concurrency-aware switch model that jointly captures capacity and fidelity under multi-flow conditions, offering the first systematic simulation-based analysis of this problem. Results show that handling several requests at the same time improves throughput but reduces fidelity once the network is too busy. This highlights the need for scheduling and routing strategies that keep a good balance between efficiency and entanglement quality in future quantum networks., Agencia Estatal de Investigación | Ref. TED-2021-130369B-C3, Agencia Estatal de Investigación | Ref. PID2023‐148214OB‐C22
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Intelligent handover solutions for heterogeneous B5G cellular networks: proposals and full-stack evaluation

  • Rúa Estévez, José Manuel
  • Fondo Ferreiro, Pablo
  • Gil Castiñeira, Felipe Jose
  • González Castaño, Francisco Javier
Mobility management remains a key challenge in cellular networks, particularly handover management. The introduction of a wider range of frequencies and radio access technologies in 5G networks further intensifies this challenge. For example, the 5G standard considers the joint deployment of cells using new frequency bands beyond 24 GHz (frequency range 2, FR2), alongside cells operating in the sub-6 GHz bands (frequency range 1, FR1), referred to as millimeter-wave heterogeneous networks (mmWave HetNets). However, the 3GPP-defined handover algorithms do not fully leverage the network capacity of HetNets, as they originate from single-band scenarios and base their decisions on received power levels. We propose two novel strategies for handover management in HetNets and evaluate them using a new, realistic, end-to-end full-stack 5G metasimulator, which is another key contribution of this paper. One of the strategies is based on a heuristic algorithm, while the other relies on a Double Deep Q-Network (DDQN) architecture. The current main 5G full-stack simulators do not support arbitrary handover strategies, so state-of-the-art research in this field has relied on custom simulators with simplified system models. To enable realistic simulations, we propose a novel method that orchestrates multiple 5G simulations to emulate a complex 5G environment with arbitrary handover capabilities. The evaluation of the proposed strategies shows an improvement between 65% and 450% in aggregated throughput compared to the 3GPP Release 15 handover and Conditional Handover algorithm, depending on the scenario., Xunta de Galicia | Ref. ED481D 2025/007, Xunta de Galicia | Ref. ED431C 2022/04, Agencia Estatal de Investigación | Ref. PREP2023-002164, Agencia Estatal de Investigación | Ref. PID2023-148214OB-C22, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Intelligent energy-efficient GNSS-assisted and LoRa-based positioning for wildlife tracking

  • López Escobar, Juan José
  • Fondo Ferreiro, Pablo
  • González Castaño, Francisco Javier
  • Gil Castiñeira, Felipe Jose
  • Piorno González, Vicente
  • Munilla Rumbao, Ignacio
  • Gil Carrrera, Alberto
The Internet of Things (IoT), together with low power wide area network (LPWAN) technologies, have revolutionized wildlife monitoring and tracking systems. The research in this article has been motivated by the need of an adequate tracking solution based on LoRaWAN technology to study the population of the yellow-legged gull at Sálvora Island, Atlantic Islands of Galicia National Park. The main contribution is an intelligent approach that estimates the positions from LoRa signal features [received signal strength indicator (RSSI) and signal-to-noise ratio (SNR)] and trajectory information from previous positions, combined with as less frequent GNSS information as possible. By doing so, we achieve a good compromise between energy consumption, sampling rate, and application-level estimation accuracy. The results show that the approach achieves satisfactory performance for sampling frequencies according to the biological problems of interest, minimizing recharging cycles and, thus maximizing the duration of monitoring sessions. Specifically, the combination of previous GNSS positions and LoRa radio indicators within an intelligent framework can improve energy efficiency for extended periods with sporadic power-intensive GNSS position updates., Ministerio de Ciencia, Innovación y Universidades | Ref. FPU19/01284, Agencia Estatal de Investigación | Ref. PID2023-148214OB-C22, Xunta de Galicia | Ref. ED481B-2022-019, Xunta de Galicia | Ref. ED431C 2022/04, Parque Nacional de las Islas Atánticas de Galicia, Universidade de Vigo/CISUG