NET1  – Cognitive network management & Quality aware networkin

Wednesday, 7 June 2023, 11:00-12:30, Room R2

Session Chair: Philipp Geuer (Ericsson Research, Germany)

6G BRAINS Topology-Aware Industry-Grade Network Slice Management and Orchestration
João Fonseca (Instituto de Telecomunicações and Universidade de Aveiro & Capgemini Enginnering, Portugal); Mohamed Khadmaoui-Bichouna (University of the West of Scotland, United Kingdom (Great Britain)); Bruno Miguel Fonseca Mendes (University of Aveiro, Portugal); Paulo Duarte and Marco Araujo (Capgemini Engineering, Portugal); Daniel Corujo (University of Aveiro & Instituto de Telecomunicações, Portugal); Ignacio Sanchez-Navarro and Antonio Matencio Escolar (University of the West of Scotland, United Kingdom (Great Britain)); Pablo Salva-Garcia (University West Of Scotland, United Kingdom (Great Britain)); Jose Maria Alcaraz Calero (University of the West of Scotland & School of Engineering and Computing, United Kingdom (Great Britain)); Qi Wang (University of the West of Scotland, United Kingdom (Great Britain))
This paper describes the integration between the Open Network Automation Platform (ONAP) and UWS Slice Manager within the European project 6G Brains. The proposed solution allows for End-To-End(E2E) Network Slicing, enabling fine-grain and optimal traffic engineering of the Network components. This work’s findings ensure an E2E connection. The solution allows external services to create slices and attach them easily. The UWS Network Slice Manager allows for detailed monitoring of the network slice’s inner components. With this information, ONAP can improve the network by creating and optimising slices on demand. The validation of the integration presents the workflow to create and attach slices. These operations enable autonomous workflows for deploying E2E Services that ensure the QoS/QoE in the network.

EdgeDS: Data Spaces Enabled Multi-Access Edge Computing
Ioannis Kalogeropoulos, Maria Eleftheria Vlontzou, Nikos Psaromanolakis, Eleni Zarogianni and Vasileios Theodorou (Intracom S.A. Telecom Solutions, Greece)
The potential of Edge Computing technologies is yet to be exploited for multi-domain, multi-party data-driven systems. One aspect that needs to be tackled for the realization of envisioned open-edge Ecosystems, is the secure and trusted exchange of data services among diverse stakeholders. In this work, we present a novel approach for integrating mechanisms for trustworthy and sovereign data exchange, into Multi-access Edge Computing (MEC) environments. To this end, we introduce an architecture that extends the ETSI MEC Architectural Framework with artifacts from the International Data Spaces Reference Architecture Model, accompanied by processes that automatically enrich Edge Computing applications with data space capabilities in an as-a-service paradigm. To validate our approach, we implement an open-source prototype solution and we conduct experiments that showcase its functionality and scalability. To our knowledge, this is one of the first concrete architectural specifications for enabling data space features in MEC systems.

Towards a 3GPP Network-Based Framework for Improving Service Assurance and Load Balancing
Cara Watermann, Philipp Geuer and Henning Wiemann (Ericsson Research, Germany); Roman Zhohov (Ericsson Research, Sweden); Alexandros Palaios (Ericsson Research, Germany)
As cellular networks evolve towards the 6th generation, new schemes are proposed in the area of Quality of Service (QoS) assurance. In recent years, predicting QoS gained some momentum as a way of satisfying specific connectivity requirements, supporting service assurance, and estimating the Quality of Experience (QoE). The QoS requirements to guarantee a certain QoE differ per use case, and hence depend on a multitude of factors, e.g., selecting an appropriate cell that can guarantee specific QoS requirements. Machine Learning (ML) is proposed as a method to improve network capabilities for QoE assurance by the use of predictive Quality of Service (pQoS). This in return can improve the offered QoS, reduce latency by selecting the most appropriate cell quickly, and improve the load-balancing at the network. The adoption of ML depends heavily on removing some of the roadblocks of applying ML in commercial networks. For example, ML-based algorithms are known to depend on a large amount of data, which might increase the usage of signaling and the battery consumption at the User Equipment (UE). We present an ML framework that can enable many of the aforementioned network capabilities, which does not require the introduction of new signaling types or proprietary data collection procedures. We showcase the benefits of the ML framework on an inter-frequency load balancing use case and discuss how ML can improve UE and network performance. Finally, we highlight the need to introduce the expected interference to the UE as an input
feature for further improving QoS prediction performance. We test the performance of the prediction framework on data coming from a test network and evaluate the effects of e.g., different prediction thresholds.

Inferring Hidden Structure in Mobile Network Performance Data with Noisy Net Promoter Scores Using a Probabilistic Graphical Model
Jaco Du Toit (Stellenbosch University, South Africa); Louwrens Labuschagne (ByteFuse, South Africa)
Understanding customer satisfaction in the context of mobile network performance is helpful when designing reliable cellular networks to retain customers and drive customer loyalty. Using Infer.NET, we propose a probabilistic graphical model that infers hidden structure in network key performance indicators using noisy customer survey responses. Our model uses realworld net promoter score survey data, network session data consisting of sites visited by respondents, and network performance data from active sessions. The model learns hidden structure in the network performance data that represent good and bad quality of experience. The discovered properties are consistent with industry-recommended signal strength and quality levels for UMTS and LTE standards. Furthermore, our methodology allows us to estimate a daily network performance for each site, which helps to identify problem areas in the network. Due to the subjective nature of survey data, our model also estimates the overall asymmetric noise associated with the surveys.

DDoS Attack Detection Using Unsupervised Federated Learning for 5G Networks and Beyond
Saeid Sheikhi and Panos Kostakos (University of Oulu, Finland)
The rapid expansion of 5G networks, coupled with the emergence of 6G technology, has highlighted the critical need for robust security measures to protect communication infrastructures. A primary security concern in 5G core networks is Distributed Denial of Service (DDoS) attacks, which target the GTP protocol. Conventional methods for detecting these attacks exhibit weaknesses and may struggle to effectively identify novel and undiscovered attacks. In this paper, we proposed a federated learning-based approach to detect DDoS attacks on the GTP protocol within a 5G core network. The suggested model leverages the collective intelligence of multiple devices to efficiently and privately identify DDoS attacks. Additionally, we have developed a 5G testbed architecture that simulates a sophisticated public network, making it ideal for evaluating AI-based security applications and testing the implementation and deployment of the proposed model. The results of our experiments demonstrate that the proposed unsupervised federated learning model effectively detects DDoS attacks on the 5G network while preserving the privacy of individual network data. This underscores the potential of federated learning in enhancing the security of 5G networks and beyond.

Go to Top