Chrysa Papagianni
YOU?
Author Swipe
View article: LLM-based Optimization Algorithm Selection for High-Performance Networks Orchestration
LLM-based Optimization Algorithm Selection for High-Performance Networks Orchestration Open
View article: SmartNet: Bridging Performance and Realism in Network Emulation with SmartNICs
SmartNet: Bridging Performance and Realism in Network Emulation with SmartNICs Open
View article: FlexUP: Breaking Up the CU-UP to Speed Up the RAN
FlexUP: Breaking Up the CU-UP to Speed Up the RAN Open
View article: The GhostTwin: Towards Live Digital Twins via SmartNIC Network Emulation
The GhostTwin: Towards Live Digital Twins via SmartNIC Network Emulation Open
View article: Reinforcement Learning-based Adaptive Path Selection for Programmable Networks
Reinforcement Learning-based Adaptive Path Selection for Programmable Networks Open
This work presents a proof-of-concept implementation of a distributed, in-network reinforcement learning (IN-RL) framework for adaptive path selection in programmable networks. By combining Stochastic Learning Automata (SLA) with real-time…
View article: P4DDG: Data-Dependent Grammars for Packet Specification and Parsing in P4
P4DDG: Data-Dependent Grammars for Packet Specification and Parsing in P4 Open
View article: Application-centric congestion control
Application-centric congestion control Open
Modern networked applications typically establish multiple connections to one or more servers to ensure that the virtual objects with which the user interacts are kept up to date. Since these connections usually share a common bottleneck, …
View article: Online SLA Decomposition: Enabling Real-Time Adaptation to Evolving Network Systems
Online SLA Decomposition: Enabling Real-Time Adaptation to Evolving Network Systems Open
When a network slice spans multiple technology domains, it is crucial for each domain to uphold the End-to-End (E2E) Service Level Agreement (SLA) associated with the slice. Consequently, the E2E SLA must be properly decomposed into partia…
View article: A Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning
A Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning Open
Cellular Vehicle-to-Everything (C-V2X) is currently at the forefront of the digital transformation of our society. By enabling vehicles to communicate with each other and with the traffic environment using cellular networks, we redefine tr…
View article: Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning
Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning Open
In the forthcoming era of 6G networks, characterized by unprecedented data rates, ultra-low latency, and extensive connectivity, effective management of Virtualized Network Functions (VNFs) is essential. VNFs are software-based counterpart…
View article: RAILS: Risk-Aware Iterated Local Search for Joint SLA Decomposition and Service Provider Management in Multi-Domain Networks
RAILS: Risk-Aware Iterated Local Search for Joint SLA Decomposition and Service Provider Management in Multi-Domain Networks Open
The emergence of the fifth generation (5G) technology has transformed mobile networks into multi-service environments, necessitating efficient network slicing to meet diverse Service Level Agreements (SLAs). SLA decomposition across multip…
View article: In-band Collection and Control of End-to-end Latency in Programmable Packet-Optical Networks
In-band Collection and Control of End-to-end Latency in Programmable Packet-Optical Networks Open
A novel programmable INT collector, acting as active controller within the data plane, is proposed to enable fast closed-loop flow latency monitoring. Experimental evaluation on P4-based hardware switches demonstrates assurance reactions w…
View article: Application-Centric Congestion Control
Application-Centric Congestion Control Open
Modern networked applications typically establish multiple connections to one or more servers to ensure that the virtual objects with which the user interacts are kept up to date. Since these connections usually share a common bottleneck, …
View article: Lightweight INT on the Tofino programmable switch
Lightweight INT on the Tofino programmable switch Open
View article: An Architectural Framework for 6G Network Digital Twins System
An Architectural Framework for 6G Network Digital Twins System Open
View article: In-network Control for Flow Steering
In-network Control for Flow Steering Open
In recent years monitoring networks with high level of accuracy is becoming crucial to meet performanceand security requirements of data flows. Concurrently, automated communication serviceassurance calls for increased network visibility a…
View article: iRED: A disaggregated P4-AQM fully implemented in programmable data plane hardware
iRED: A disaggregated P4-AQM fully implemented in programmable data plane hardware Open
Routers employ queues to temporarily hold packets when the scheduler cannot immediately process them. Congestion occurs when the arrival rate of packets exceeds the processing capacity, leading to increased queueing delay. Over time, Activ…
View article: DESiRED -- Dynamic, Enhanced, and Smart iRED: A P4-AQM with Deep Reinforcement Learning and In-band Network Telemetry
DESiRED -- Dynamic, Enhanced, and Smart iRED: A P4-AQM with Deep Reinforcement Learning and In-band Network Telemetry Open
Active Queue Management (AQM) is a mechanism employed to alleviate transient congestion in network device buffers, such as routers and switches. Traditional AQM algorithms use fixed thresholds, like target delay or queue occupancy, to comp…
View article: Towards extreme network KPIs with programmability in 6G
Towards extreme network KPIs with programmability in 6G Open
Talk about DESIRE6G Architecthure given by Technical Coordinator during Workshop 5 at EuCNC2024 This workshop focuses on EU collaborative research and innovation focal points toward 6G Smart Networks and Services (SNS) and provides a good …
View article: SLA Decomposition for Network Slicing: A Deep Neural Network Approach
SLA Decomposition for Network Slicing: A Deep Neural Network Approach Open
For a network slice that spans multiple technology and/or administrative domains, these domains must ensure that the slice's End-to-End (E2E) Service Level Agreement (SLA) is met. Thus, the E2E SLA should be decomposed to partial SLAs, ass…
View article: SLA Decomposition for Network Slicing: A Deep Neural Network Approach
SLA Decomposition for Network Slicing: A Deep Neural Network Approach Open
For a network slice that spans multiple technology and/or administrative domains, these domains must ensure that the slice’s End-to-End (E2E) Service Level Agreement (SLA) is met. Thus, the E2E SLA should be decomposed to partial SLAs, ass…
View article: Deterministic and Probabilistic P4-Enabled Lightweight In-Band Network Telemetry
Deterministic and Probabilistic P4-Enabled Lightweight In-Band Network Telemetry Open
In-band network telemetry (INT), empowered by programmable dataplanes such as P4, comprises a viable ap- proach to network monitoring and telemetry analysis. However, P4-INT as well as other existing frameworks for INT yield a substantial …
View article: D6.1 Initial Communication and Dissemination Plan (CODP)
D6.1 Initial Communication and Dissemination Plan (CODP) Open
This deliverable presents the communication and dissemination plan of DESIRE6G. Under each part of the plan, we present the list of activities, as well as the targeted metrics. Standardization deserves substantial attention in this documen…
View article: A Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning
A Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning Open
Cellular Vehicle-to-Everything (C-V2X) is currently at the forefront of the digital transformation of our society. By enabling vehicles to communicate with each other and with the traffic environment using cellular networks, we redefine tr…
View article: Pervasive Monitoring and Distributed Intelligence for 6G Near Real-Time Operation
Pervasive Monitoring and Distributed Intelligence for 6G Near Real-Time Operation Open
In-band network telemetry (INT) can provide additional insight of the network status, which can be used for distributed control loop automation. However, INT yields substantial transmission overhead that negatively affects scalability and …
View article: Paradoxical activation of oncogenic signaling as a cancer treatment strategy
Paradoxical activation of oncogenic signaling as a cancer treatment strategy Open
Cancer homeostasis depends on a balance between activated oncogenic pathways driving tumorigenesis and engagement of stress-response programs that counteract the inherent toxicity of such aberrant signaling. While inhibition of oncogenic s…
View article: V2N Service Scaling with Deep Reinforcement Learning
V2N Service Scaling with Deep Reinforcement Learning Open
The fifth generation (5G) of wireless networks is set out to meet the stringent requirements of vehicular use cases. Edge computing resources can aid in this direction by moving processing closer to end-users, reducing latency. However, gi…
View article: End-to-End Intent-Based Networking
End-to-End Intent-Based Networking Open
To reap its full benefits, 5G must evolve into a scalable decentralized architecture by exploiting intelligence ubiquitously and securely across different technologies, network layers, and segments. In this article, we propose end-to-end a…
View article: SLAs Decomposition for Network Slicing: A Deep Neural Network Approach
SLAs Decomposition for Network Slicing: A Deep Neural Network Approach Open
5G is a multi-service network supporting a range of verticals with a diverse set of requirements. Network slicing enables the creation and operation of multiple logical networks over the shared network infrastructure, tailored to the requi…
View article: Dimensioning V2N Services in 5G Networks Through Forecast-Based Scaling
Dimensioning V2N Services in 5G Networks Through Forecast-Based Scaling Open
With the increasing adoption of intelligent transportation systems and the upcoming era of autonomous vehicles, vehicular services (such as remote driving, cooperative awareness, and hazard warning) will have to operate in an ever-changing…