AI@EDGE Scientific Publications
Line rate botnet detection with SmartNIC-embedded feature extraction
Botnets pose a significant threat in network security, exacerbated by the massive adoption of vulnerable Internet-of-Things (IoT) devices. In response to that, great research effort has taken place to propose intrusion detection solutions to the botnet menace. As most techniques focus on …
Data Pipeline System Designs for In-network Learning
This paper introduces the design of a data pipeline system (DPS) integrated with artificial intelligence (AIF) functions to support continuous AI learning and operations for network automation in 5G/6G systems. …
DVFasS: Leveraging DVFS for FaaS Workflows
DVFaaS , a per-core DVFS framework that utilizes control systems theory to assign just-enough frequency for the purpose of addressing the QoS requirements on serverless workflows comprising unseen functions. DVFaaS exploits the intermittent nature of serverless workflows, which enables …
Enabling Intelligence Inclusiveness in Edge to Cloud Continuum: Challenges and Opportunities
Edge to Cloud Continuum is a concept that integrates cloud computing and cellular networks that has been gaining popularity due to its potential to provide a seamless user experience and address the challenges of managing complex multi-domain networks involving massive IoT devices. …
A network architecture for scalable end-to-end management of reusable AI-based applications
Artificial intelligence (AI) is a key enabler for future 6G networks. Currently, related architecture works propose AI-based applications and network services that are dedicated to specific tasks (e.g., improving the performance of RAN with AI). These proposed architectures offer …
Distributed Learning for Application Placement at the Edge Minimizing Active Nodes
The main goal of application placement in Multi-Access Edge Computing (MEC) is to map their requirements to the infrastructure for desired Service Level Agreement (SLA). In highly distributed infrastructures in beyond 5G and 6G networks, …
Compression of Signal Activation from Split Deep Neural Network
The use of artificial neural networks for the purpose of image classification, together with the advancement in computational capabilities of edge devices, plays an important role in the new emerging 5G use case scenarios. However, …
DeepGANTT: A Scalable Deep Learning Scheduler for Backscatter Networks
Novel backscatter communication techniques enable battery-free sensor tags to interoperate with unmodified standard IoT devices, extending a sensor network’s capabilities in a scalable manner. Without requiring additional dedicated infrastructure, the battery-free tags harvest energy from the environment, while the IoT devices provide them with the unmodulated carrier they need to communicate. A schedule …
Edge Intelligence in 5G and Beyond Aeronautical Network with LEO Satellite Backhaul
The vision of ubiquitous network connectivity to fuel uninterrupted services to any user has materialized with the Fifth-Generation (5G) of mobile technology and will probably find maturity on the way to developing 6G. To reach this goal, 5G technology and its evolution (B5G), as well as Multi-access Edge Computing (MEC), alongside Machine Learning (ML) will play pivotal roles. …
Roundabouts: Traffic Simulations of Connected and Automated Vehicles—A State of the Art
The paper deals with traffic simulation within roundabouts when both “connected and automated vehicles” (CAVs) and human-driven cars are present. The aim is to present the past, current and future research on CAVs running into roundabouts within the Cooperative, Connected and Automated Mobility (CCAM) framework. …
Traffic simulation with human in the loop: roundabout scenario in a driving simulator
Traffic simulators are powerful tools for the simulation of vehicle interactions in many traffic conditions, but they employ approximated driver models, so the reliability of the acquired information is limited. To overcome such limitations, this paper presents a co-simulation between a widely diffused open source traffic simulator and a high end driving simulator. …
Roundabout Traffic: Simulation With Automated Vehicles, Ai, 5g, Edge Computing and Human in the Loop
The aim of the paper is to assess how the traffic of roundabouts could be organized in the future. A mixed traffic is supposed to occur, featuring both fully automated vehicle and vehicles driven by humans. The case study is a part of a comprehensive research funded by European Commission, focusing on how improving the 5G network by Artificial Intelligence (AI) and edge computing. …
Quantitative and Qualitative Evaluation of Reinforcement Learning Policies for Autonomous Vehicles
Optimizing traffic dynamics in an evolving transportation landscape is crucial, particularly in scenarios where autonomous vehicles (AVs) with varying levels of autonomy coexist with human driven cars. This paper presents a novel approach to optimizing choices of AVs using Proximal Policy Optimization (PPO), a reinforcement learning algorithm. We learned …
An intelligent scheduling for 5G user plane function placement and chaining reconfiguration
Services and use cases in 5G and beyond networks are characterized by strict requirements such as ultra-low latency, increased capacity, and high user mobility. Moreover, these networks must be capable of satisfying these ambitious demands as well as anticipating and adapting to dynamically changing conditions in a quick and feasible manner. This study deals with …
DQN-based intelligent controller for multiple edge domains
Advanced technologies like network function virtualization (NFV) and multi-access edge computing (MEC) have been used to build flexible, highly programmable, and autonomously manageable infrastructures close to the end-users, at the edge of the network. In this vein, the use of single-board computers (SBCs) in commodity clusters has gained attention to deploy virtual network functions (VNFs) due to their low cost, low energy consumption, and easy programmability. This paper deals with …
Auto-tuning of Hyper-parameters for Detecting Network Intrusions via Meta-learning
In recent years, machine learning-based Network Intrusion Detection Systems have been widely investigated to detect network attacks. The performance of such systems is strongly affected by their configuration, i.e. the setting of the hyper-parameters, usually based on human expertise. Few efforts have been made towards …
Evaluating Versal ACAP and conventional FPGA platforms for AI inference
Xilinx Versal ACAP is the newest acceleration platform, developed by Xilinx, proposed to enhance the capabilities of the conventional FPGA ones and meet the demands of modern applications. However, only few studies concerning its benefits have been performed. To address this issue, a comparison between this platform and the MPSoC FPGA is performed by , …
Deep Reinforcement Learning for QoS-aware scheduling under resource heterogeneity Optimizing serverless video analytics
Today, video analytics are becoming extremely popular due to the increasing need for extracting valuable information from videos available in public sharing services through camera-driven streams. Typically, video analytics are organized as a set of separate tasks, each of which has different resource requirements (e.g., computational- vs. memory-intensive tasks). The serverless computing paradigm forms a very promising approach for …
A memory footprint optimization framework for Python applications targeting edge devices
The advantages of processing data at the source motivate developers to offload computations at the edges of IoT networks. However, the computational resource constraints of edge computing devices limit the opportunities for deploying applications developed in high-level languages at the edge. In contrast to C/C++, applications developed in Python and other dynamic high-level languages, often require an increased amount of memory size, due to their inherent static memory management
approach. Therefore, …
Design and Evaluation of a K8s-based System for Distributed Open-Source Cellular Networks
Virtualization in cellular networks is one of the key areas of research where technologies, infrastructure and challenges are rapidly changing as 5G system architecture demands a paradigm shift. This paper aims to study the viability and the performance of cloud-native infrastructures for hosting network functions. …
Towards Sustainable and Trustworthy 6G: Challenges, Enablers, and Architectural Design
While the 5th Generation (5G) system is being widely deployed across the globe, the information and communication technology (ICT) industry, research, standardization and consensus building for the 6th generation (6G) are already well underway with high expectations towards the merger of digital, physical, and human worlds. The main goal of this book is to introduce the upcoming 6G technologies and outline the foreseen challenges, enablers, and architectural design trends that will be instrumental in realizing a Sustainable and Trustworthy 6G system in the coming years. …
Beyond 5G/6G KPI Measurements
This white paper provides an early analysis of possible Beyond 5G/6G KPIs based on current work and perspectives from ICT-52 projects, seeking to understand the level to which existing definitions in standard documents will apply to 6G and to identify, at early stages, gaps and new candidate KPIs for being standardized for 6G systems. …
SUMO Roundabout Simulation with Human in the Loop
Traffic simulators rely on calibrated driver models in order to reproduce human behavior in different traffic scenarios. Even if quite accurate results can be obtained, the actual interaction between human being and traffic cannot be completely reproduced. In particular, …
DQN-based Intelligent Application Placement with Delay-Priority in Multi MEC Systems
In 5G Multi-access Edge Computing (MEC) is critical to bring computing and processing closer to users and enable ultra-low latency communications. When instantiating an application, selecting the MEC host that minimizes the latency but still fulfills the application’s requirements is critical …
AI@EDGE: A Secure and Reusable Artificial Intelligence Platform for Edge Computing
Artificial Intelligence (AI) has become a major innovative force and a major pillar in the fourth industrial revolution. This trend has been acknowledged by the European Commission, who has pointed out how high-performance, intelligent, and secure networks are fundamental …
FaaS and Curious: Performance implications of serverless functions on edge computing platforms
Serverless is an emerging paradigm that greatly simplifies the usage of cloud resources providing unprecedented auto-scaling, simplicity, and cost-efficiency features. Thus, more and more individuals and organizations adopt it, to increase their productivity and focus exclusively …
Towards sharing one FPGA SoC for both low-level PHY and high-level AI/ML computing at the edge
International Mediterranean Conference. on Communications and Networking (meditcom 2021), Workshop 1 on Acceleration for Edge Computing
Delay-Sensitive Wireless Content Delivery: An Interpretable Artificial Intelligence Approach
1st International Workshop on Network Programmability (NetP 2021) co-located with CNSM 2021
Auto-configuration des systèmes de détection d’intrusions grâce aux expériences passées
RESSI (Rendez-Vous de la Recherche et de l’Enseignement de la Sécurité des Systèmes d’Information)
An AI-empowered framework for cross-layer softwarized infrastructure state assessment
Network softwarization technologies challenge legacy fault management systems. Coordination and dependency among different novel software components for orchestration, switching, virtual machine and container management creates novel monitoring points, …
Robust Access Point Clustering in Edge Computing Resource Optimization
Multi-access Edge Computing (MEC) technology has emerged to overcome traditional cloud computing limitations, challenged by the new 5G services with heavy and heterogeneous requirements on both latency and bandwidth. …
A Lightweight Southbound Interface for Standalone P4-NetFPGA SmartNICs
We present a lightweight Southbound Interface (SBI) for P4→NetFPGA devices, aimed at enhancing the capability of NetFPGA Smart Network Interface Cards (SmartNICs) to work in standalone mode. …
An Open Dataset for Beyond-5G Data-driven Network Automation Experiments
In this paper, we present the 5G3E (5G End-to-End Emulation) dataset created to support 5G network automation. The dataset contains thousands of time-series, built at different sampling rates, related to the observation of multiple resources involved in 5G network operation: radio, computing and network resources. …
Anomaly Detection for 5G Softwarized Infrastructures with Federated Learning
We present how to distribute an anomaly detection framework at the state of the art, called SYRROCA (SYstem Radiography and ROot Cause Analysis), for edge computing and 5G environment, using federated learning. The goal is to leverage …
LSTM acceleration with FPGA and GPU devices for edge computing applications in B5G MEC
The advent of AI/ML in B5G and Multi-Access Edge Computing will rely on the acceleration of neural networks. The current work focuses on the acceleration of Long Short-Term Memory (LSTM) kernels playing a key role in numerous applications. We assume various LSTM sizes while targeting FPGA and GPU hardware for both embedded and server MEC purposes. …
Roadrunner: O-RAN-based Cell Selection in Beyond 5G Networks
O-RAN is currently emerging as the way to build a virtualized 5G and beyond Radio Access Network (RAN) that is based on open interfaces and off-the-shelf hardware. O-RAN consolidates the intelligence of several gNodeBs at the Near-realtime RAN Intelligent Controller (RIC) making it more programmable and aware of the mobile users’ surroundings. …
Sequence Clock: A Dynamic Resource Orchestrator for Serverless Architectures
Function-as-a-service (FaaS) represents the next frontier in the evolution of cloud computing being an emerging paradigm that removes the burden of configuration and management issues from users. This is achieved by replacing the well-established monolithic approach with …
Zero Touch Management: A Survey of Network Automation Solutions for 5G and 6G Networks
Mobile networks are facing an unprecedented demand for high-speed connectivity originating from novel mobile applications and services and, in general, from the adoption curve of mobile devices. However, coping with the service requirements imposed by current and future applications and services is very difficult since …
Function Placement and Acceleration for In-Network Federated Learning Services
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. …
Beyond 5G/6G KPIs and Target Values. A white paper from the Test, Measurement and KPIs Validation Working Group”
The main objective of this document is to present the current view of the available B5G and 6G KPIs from 5G PPP phase III projects with a focus on projects of the ICT-52 call. This view includes mapping to KPIs previously defined for 5G and evaluating how they might evolve to fit the B5G and 6G visions. …
5G PPP Architecture Working Group – View on 5G Architecture, Version 4.0
The overall goal of the Architecture Working Group (WG) within the 5G PPP Initiative is to consolidate the main technology enablers and the bleeding-edge design trends in the context of the 5G Architecture. As a result, it provides a consolidated view of the architectural efforts developed in the projects part of the 5G PPP initiative and other research efforts, including standardization. …
Machine Learning at the Mobile Edge: The Case of Dynamic Adaptive Streaming Over HTTP (DASH)
Dynamic Adaptive Streaming over HTTP (DASH) is a standard for delivering video in segments and adapting each segment’s bitrate (quality), to adjust to changing and limited network bandwidth. We study segment prefetching, informed by machine learning predictions of bitrates of client segment requests, implemented at the network edge. …