A Distributed NWDAF Architecture for Federated Learning in 5G

Jeon, Youbin; Jeong, Hyeonjae; Seo, Sangwon; Kim, Taeyun; Ko, Haneul; Pack, Sangheon

doi:10.1109/icce53296.2022.9730220

Cited by 19 publications

(11 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [89], a distributed NWDAF architectural approach has been presented, where leaf NWDAFs create local models and root NWDAF constructs a global model by aggregating the local models. This structure can guarantee data privacy since local models are created in NFs and can reduce network resource usage because the global model is created by collecting local models.…”

Section: A Nwdaf-aided Resource Optimizationmentioning

confidence: 99%

Leveraging Network Data Analytics Function and Machine Learning for Data Collection, Resource Optimization, Security and Privacy in 6G Networks

Gkonis,

Nomikos,

Trakadas

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The full deployment of sixth-generation (6G) networks is inextricably connected with a holistic network redesign able to deal with various emerging challenges, such as integration of heterogeneous technologies and devices, as well as support of latency and bandwidth demanding applications. In such a complex environment, resource optimization, and security and privacy enhancement can be quite demanding, due to the vast and diverse data generation endpoints and associated hardware elements. Therefore, efficient data collection mechanisms are needed that can be deployed at any network infrastructure. In this context, the network data analytics function (NWDAF) has already been defined in the fifth-generation (5G) architecture from Release 15 of 3GPP, that can perform data collection from various network functions (NFs). When combined with advanced machine learning (ML) techniques, a full-scale network optimization can be supported, according to traffic demands and service requirements. In addition, the collected data from NWDAF can be used for anomaly detection and thus, security and privacy enhancement. Therefore, the main goal of this paper is to present the current state-of-the-art on the role of the NWDAF towards data collection, resource optimization and security enhancement in next generation broadband networks. Furthermore, various key enabling technologies for data collection and threat mitigation in the 6G framework are identified and categorized, along with advanced ML approaches. Finally, a high level architectural approach is presented and discussed, based on the NWDAF, for efficient data collection and ML model training in large scale heterogeneous environments.

show abstract

Section: A Nwdaf-aided Resource Optimizationmentioning

confidence: 99%

Leveraging Network Data Analytics Function and Machine Learning for Data Collection, Resource Optimization, Security and Privacy in 6G Networks

Gkonis,

Nomikos,

Trakadas

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The code is available on GitHub. While the authors in [ 30 ] introduces a distributed NWDAF structure tailored for FL in 5G. Distributed NWDAFs are largely composed of a single root NWDAF and several leaf NWDAFs, and an interface exists among distributed NWDAFs to enable communication with each other.…”

Section: Network Data Analytics Function (Nwdaf)mentioning

confidence: 99%

Advancing C-V2X for Level 5 Autonomous Driving from the Perspective of 3GPP Standards

Khan

Malik

et al. 2023

Sensors

View full text Add to dashboard Cite

Cellular vehicle-to-everything (C-V2X) is one of the enabling vehicular communication technologies gaining momentum from the standardization bodies, industry, and researchers aiming to realize fully autonomous driving and intelligent transportation systems. The 3rd Generation Partnership Project (3GPP) standardization body has actively been developing the standards evolving from 4G-V2X to 5G-V2X providing ultra-reliable low-latency communications and higher throughput to deliver the solutions for advanced C-V2X services. In this survey, we analyze the 3GPP standard documents relevant to V2X communication to present the complete vision of 3GPP-enabled C-V2X. To better equip the readers with knowledge of the topic, we describe the underlying concepts and an overview of the evolution of 3GPP C-V2X standardization. Furthermore, we provide the details of the enabling concepts for V2X support by 3GPP. In this connection, we carry out an exhaustive study of the 3GPP standard documents and provide a logical taxonomy of C-V2X related 3GPP standard documents divided into three categories: 4G, 4G & 5G, and 5G based V2X services. We provide a detailed analysis of these categories discussing the system architecture, network support, key issues, and potential solution approaches supported by the 3GPP. We also highlight the gap and the need for intelligence in the execution of different operations to enable the use-case scenarios of Level-5 autonomous driving. We believe, the paper will equip readers to comprehend the technological standards for the delivery of different ITS services of the higher level of autonomous driving.

show abstract

“…The breakthrough of FL paradigm gave birth to its application in many fields. For standard systems, in [10], the authors proposed a tailored structure for NWDAF function based on FL paradigm w.r.t 3GPP standards: each 5G core NF has its own NWDAF function called the NWDAF leaf, collecting data from its corresponding NF and then training the ML model locally. The root NWDAF in their architecture refers to the FL server and ensures the aggregation of the local model parameters.…”

Section: B Federated Learning Applicationsmentioning

confidence: 99%

“…Constraints (10) ensures that for each node i, the only ξ that can be activated is the one corresponding to the node of the installed server. Finally, coherence between ξ and x variables is enforced by Constraints (11) 3 .…”

Section: B Problem Formulationmentioning

confidence: 99%

Function Placement and Acceleration for In-Network Federated Learning Services

Yellas

Addis

Riggio

et al. 2022

2022 18th International Conference on Network and Service Management (CNSM)

View full text Add to dashboard Cite

Edge intelligence combined with federated learning is considered as a way to distributed learning and inference tasks in a scalable way, by analyzing data close to where it is generated, unlike traditional cloud computing where data is offloaded to remote servers. In this paper, we address the placement of Artificial Intelligence Functions (AIF) making use of federated learning and hardware acceleration. We model the behavior of federated learning and related inference point to guide the placement decision, taking into consideration the specific constraint and the empirical behavior of a virtualized infrastructure anomaly detection use-case. Besides hardware acceleration, we consider the specific training time trend when distributing training over a network, by using empirical piece-wise linear distributions. We model the placement problem as a MILP and we propose a variant of the problem. Simulation results show the impact that hardware acceleration can have in the decision of the number of AIF to enable, while dividing by a relevant factor the distributed training time. We also show how our approach exacerbates the importance of monitoring an end-to-end learning system delay budget composed of link propagation delay and distributed training time in the location of AIFs.

show abstract

A Distributed NWDAF Architecture for Federated Learning in 5G

Cited by 19 publications

References 2 publications

Leveraging Network Data Analytics Function and Machine Learning for Data Collection, Resource Optimization, Security and Privacy in 6G Networks

Leveraging Network Data Analytics Function and Machine Learning for Data Collection, Resource Optimization, Security and Privacy in 6G Networks

Advancing C-V2X for Level 5 Autonomous Driving from the Perspective of 3GPP Standards

Function Placement and Acceleration for In-Network Federated Learning Services

Contact Info

Product

Resources

About