arXiv subjects

Chrysa Papagianni

Publications and source records attributed to Chrysa Papagianni.

15 recordsLinked to original sources

arXiv2026

Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models

Deploying Vision-Language Models (VLMs) on edge devices remains challenging due to their substantial computational and memory demands, which exceed the capabilities of resource-constrained embedded platforms. Conversely, fully offloading inference to the cloud is often impractical in bandwidth-limited environments, where transmitting raw visual data introduces substantial latency overhead. While recent edge-cloud collaborative architectures attempt to partition VLM workloads across devices, they typically rely on transmitting fixed-size representations, lacking adaptability to dynamic network conditions and failing to fully exploit semantic redundancy. In this paper, we propose a progressive semantic communication framework for edge-cloud VLM inference, using a Meta AutoEncoder that compresses visual tokens into adaptive, progressively refinable representations, enabling plug-and-play deployment with off-the-shelf VLMs without additional fine-tuning. This design allows flexible transmission at different information levels, providing a controllable trade-off between communication cost and semantic fidelity. We implement a full end-to-end edge-cloud system comprising an embedded NXP i.MX95 platform and a GPU server, communicating over bandwidth-constrained networks. Experimental results show that, at 1 Mbps uplink, the proposed progressive scheme significantly reduces network latency compared to full-edge and full-cloud solutions, while maintaining high semantic consistency even under high compression. The implementation code will be released upon publication at https://github.com/open-ep/ProSemComVLM.

cs.LG↗

arXiv2026

Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning

In the forthcoming era of 6G networks, characterized by unprecedented data rates, ultra-low latency, and ubiquitous connectivity, effective management of Virtualized Network Functions (VNFs) is essential. VNFs are software-based counterparts of traditional hardware devices that facilitate flexible and scalable service provisioning. Service Function Chains (SFCs), structured as ordered sequences of VNFs, are pivotal in delivering complex network services. Nevertheless, splitting an SFC into multiple segments that are deployed across different network domains or infrastructure locations presents substantial challenges due to the potential heterogeneity of domain characteristic along with quality of service (QoS) constraints and limited visibility of network state. Conventional optimization methods have limited scalability, while existing data-driven approaches struggle to balance efficiency with capturing VNF inter-dependencies in SFCs. To overcome these limitations, we introduce a Transformer-empowered actor-critic framework specifically designed for sequence-aware SFC partitioning. By utilizing the self-attention mechanism, our approach effectively models complex inter-dependencies between VNFs, facilitating coordinated and parallel decision-making processes. Furthermore, to improve training stability and convergence we introduce an $ε$-LoPe exploration strategy as well as Asymptotic Return Normalization. Comprehensive simulation results demonstrate that the proposed methodology outperforms existing state-of-the-art solutions in terms of long-term service acceptance rates, resource utilization, and scalability while achieving fast inference.

cs.NI↗

arXiv2026

MapViT: A Two-Stage ViT-Based Framework for Real-Time Radio Quality Map Prediction in Dynamic Environments

Recent advancements in mobile and wireless networks are unlocking the full potential of robotic autonomy, enabling robots to take advantage of ultra-low latency, high data throughput, and ubiquitous connectivity. However, for robots to navigate and operate seamlessly, efficiently and reliably, they must have an accurate understanding of both their surrounding environment and the quality of radio signals. Achieving this in highly dynamic and ever-changing environments remains a challenging and largely unsolved problem. In this paper, we introduce MapViT, a two-stage Vision Transformer (ViT)-based framework inspired by the success of pre-train and fine-tune paradigm for Large Language Models (LLMs). MapViT is designed to predict both environmental changes and expected radio signal quality. We evaluate the framework using a set of representative Machine Learning (ML) models, analyzing their respective strengths and limitations across different scenarios. Experimental results demonstrate that the proposed two-stage pipeline enables real-time prediction, with the ViT-based implementation achieving a strong balance between accuracy and computational efficiency. This makes MapViT a promising solution for energy- and resource-constrained platforms such as mobile robots. Moreover, the geometry foundation model derived from the self-supervised pre-training stage improves data efficiency and transferability, enabling effective downstream predictions even with limited labeled data. Overall, this work lays the foundation for next-generation digital twin ecosystems, and it paves the way for a new class of ML foundation models driving multi-modal intelligence in future 6G-enabled systems.

cs.NI↗

arXiv2025

Reinforcement Learning-based Adaptive Path Selection for Programmable Networks

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 telemetry data collected via In-Band Network Telemetry (INT), the proposed system enables local, data-driven forwarding decisions that adapt dynamically to congestion conditions. The system is evaluated on a Mininet-based testbed using P4-programmable BMv2 switches, demonstrating how our SLA-based mechanism converges to effective path selections and adapts to shifting network conditions at line rate.

cs.LG↗

arXiv2025

Online SLA Decomposition: Enabling Real-Time Adaptation to Evolving Network Systems

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 partial SLAs that are assigned to each domain involved. In a network slice management system with a two-level architecture, comprising an E2E service orchestrator and local domain controllers, we consider that the orchestrator has access only to historical data regarding the responses of local controllers to previous requests, and this information is used to construct a risk model for each domain. In this study, we extend our previous work by investigating the dynamic nature of real-world systems and introducing an online learning-decomposition framework to tackle the dynamicity. We propose a framework that continuously updates the risk models based on the most recent feedback. This approach leverages key components such as online gradient descent and FIFO memory buffers, which enhance the stability and robustness of the overall process. Our empirical study on an analytic model-based simulator demonstrates that the proposed framework outperforms the state-of-the-art static approach, delivering more accurate and resilient SLA decomposition under varying conditions and data limitations. Furthermore, we provide a comprehensive complexity analysis of the proposed solution.

cs.NI↗

arXiv2025

A Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning

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 transportation, improving road safety and transportation services, increasing efficiency of vehicular traffic flows, and reducing environmental impact. To effectively facilitate the provisioning of Cellular Vehicular-to-Network (C-V2N) services, we tackle the interdependent problems of service task placement and scaling of edge resources. Specifically, we formulate the joint problem and prove that it is not computationally tractable. To address its complexity we propose Deep Hybrid Policy Gradient (DHPG), a new Deep Reinforcement Learning (DRL) approach that operates in hybrid action spaces, enabling holistic decision-making and enhancing overall performance. We evaluated the performance of DHPG using simulations with a real-world C-V2N traffic dataset, comparing it to several state-of-the-art (SoA) solutions. DHPG outperforms these solutions, guaranteeing the $99^{th}$ percentile of C-V2N service delay target, while simultaneously optimizing the utilization of computing resources. Finally, time complexity analysis is conducted to verify that the proposed approach can support real-time C-V2N services.

cs.AI↗

arXiv2025

RAILS: Risk-Aware Iterated Local Search for Joint SLA Decomposition and Service Provider Management in Multi-Domain Networks

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 multiple network domains, each potentially managed by different service providers, poses a significant challenge due to limited visibility into real-time underlying domain conditions. This paper introduces Risk-Aware Iterated Local Search (RAILS), a novel risk model-driven meta-heuristic framework designed to jointly address SLA decomposition and service provider selection in multi-domain networks. By integrating online risk modeling with iterated local search principles, RAILS effectively navigates the complex optimization landscape, utilizing historical feedback from domain controllers. We formulate the joint problem as a Mixed-Integer Nonlinear Programming (MINLP) problem and prove its NP-hardness. Extensive simulations demonstrate that RAILS achieves near-optimal performance, offering an efficient, real-time solution for adaptive SLA management in modern multi-domain networks.

cs.NI↗

arXiv2024

SLA Decomposition for Network Slicing: A Deep Neural Network Approach

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, assigned to each of these domains. Assuming a two level management architecture consisting of an E2E service orchestrator and local domain controllers, we consider that the former is only aware of historical data of the local controllers' responses to previous slice requests, and captures this knowledge in a risk model per domain. In this study, we propose the use of Neural Network (NN) based risk models, using such historical data, to decompose the E2E SLA. Specifically, we introduce models that incorporate monotonicity, applicable even in cases involving small datasets. An empirical study on a synthetic multidomain dataset demonstrates the efficiency of our approach.

cs.NI↗

arXiv2024

Deterministic and Probabilistic P4-Enabled Lightweight In-Band Network Telemetry

In-band network telemetry (INT), empowered by programmable dataplanes such as P4, comprises a viable approach to network monitoring and telemetry analysis. However, P4-INT as well as other existing frameworks for INT yield a substantial transmission overhead, which grows linearly with the number of hops and the number of telemetry values. To address this issue, we present a deterministic and a probabilistic technique for lightweight INT, termed as DLINT and PLINT,respectively. In particular, DLINT exercises per-flow aggregation by spreading the telemetry values across the packets of a flow. DLINT relies on switch coordination through the use of per-flow telemetry states, maintained within P4 switches. Furthermore, DLINT utilizes Bloom Filters (BF) in order to compress the state lookup tables within P4 switches. On the other hand, PLINT employs a probabilistic approach based on reservoir sampling. PLINT essentially empowers every INT node to insert telemetry values with equal probability within each packet. Our evaluation results corroborate that both proposed techniques alleviate the transmission overhead of P4-INT, while maintaining a high degree of monitoring accuracy. In addition, we perform a comparative evaluation between DLINT and PLINT. DLINT is more effective in conveying path traces to the telemetry server, whereas PLINT detects more promptly path updates exploiting its more efficient INT header space utilization

cs.NI↗

arXiv2023

iRED: A disaggregated P4-AQM fully implemented in programmable data plane hardware

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, Active Queue Management (AQM) strategies have focused on directly draining packets from queues to alleviate congestion and reduce queuing delay. On Programmable Data Plane (PDP) hardware, AQMs traditionally reside in the Egress pipeline due to the availability of queue delay information there. We argue that this approach wastes the router's resources because the dropped packet has already consumed the entire pipeline of the device. In this work, we propose ingress Random Early Detection (iRED), a more efficient approach that addresses the Egress drop problem. iRED is a disaggregated P4-AQM fully implemented in programmable data plane hardware and also supports Low Latency, Low Loss, and Scalable Throughput (L4S) framework, saving device pipeline resources by dropping packets in the Ingress block. To evaluate iRED, we conducted three experiments using a Tofino2 programmable switch: i) An in-depth analysis of state-of-the-art AQMs on PDP hardware, using 12 different network configurations varying in bandwidth, Round-Trip Time (RTT), and Maximum Transmission Unit (MTU). The results demonstrate that iRED can significantly reduce router resource consumption, with up to a 10x reduction in memory usage, 12x fewer processing cycles, and 8x less power consumption for the same traffic load; ii) A performance evaluation regarding the L4S framework. The results prove that iRED achieves fairness in bandwidth usage for different types of traffic (classic and scalable); iii) A comprehensive analysis of the QoS in a real setup of a DASH) technology. iRED demonstrated up to a 2.34x improvement in FPS and a 4.77x increase in the video player buffer fill.

cs.NI↗

arXiv2023

DESiRED -- Dynamic, Enhanced, and Smart iRED: A P4-AQM with Deep Reinforcement Learning and In-band Network Telemetry

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 compute random packet drop probabilities. A very small target delay can increase packet losses and reduce link utilization, while a large target delay may increase queueing delays while lowering drop probability. Due to dynamic network traffic characteristics, where traffic fluctuations can lead to significant queue variations, maintaining a fixed threshold AQM may not suit all applications. Consequently, we explore the question: \textit{What is the ideal threshold (target delay) for AQMs?} In this work, we introduce DESiRED (Dynamic, Enhanced, and Smart iRED), a P4-based AQM that leverages precise network feedback from In-band Network Telemetry (INT) to feed a Deep Reinforcement Learning (DRL) model. This model dynamically adjusts the target delay based on rewards that maximize application Quality of Service (QoS). We evaluate DESiRED in a realistic P4-based test environment running an MPEG-DASH service. Our findings demonstrate up to a 90x reduction in video stall and a 42x increase in high-resolution video playback quality when the target delay is adjusted dynamically by DESiRED.

cs.NI↗

arXiv2023

V2N Service Scaling with Deep Reinforcement Learning

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, given the stochastic nature of traffic loads and availability of physical resources, appropriate auto-scaling mechanisms need to be employed to support cost-efficient and performant services. To this end, we employ Deep Reinforcement Learning (DRL) for vertical scaling in Edge computing to support vehicular-to-network communications. We address the problem using Deep Deterministic Policy Gradient (DDPG). As DDPG is a model-free off-policy algorithm for learning continuous actions, we introduce a discretization approach to support discrete scaling actions. Thus we address scalability problems inherent to high-dimensional discrete action spaces. Employing a real-world vehicular trace data set, we show that DDPG outperforms existing solutions, reducing (at minimum) the average number of active CPUs by 23% while increasing the long-term reward by 24%.

cs.LG↗

arXiv2021

Dimensioning of V2X Services in 5G Networks through Forecast-based Scaling

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 face an ever changing and dynamic environment. Traffic flows on the roads is a critical condition for these services and, therefore, it is of paramount importance to forecast how they will evolve over time. By knowing future events (such as, traffic jams), vehicular services can be dimensioned in an on-demand fashion in order to minimize Service Level Agreements (SLAs) violations, thus reducing the chances of car accidents. This research departs from an evaluation of traditional time-series techniques with recent Machine Learning (ML)-based solutions to forecast traffic flows in the roads of Torino (Italy). Given the accuracy of the selected forecasting techniques, a forecast-based scaling algorithm is proposed and evaluated over a set of dimensioning experiments of three distinct vehicular services with strict latency requirements. Results show that the proposed scaling algorithm enables resource savings of up to a 5% at the cost of incurring in an increase of less than 0.4% of latency violations.

cs.NI↗

arXiv2020

Joint Satellite Gateway Placement and Routing for Integrated Satellite-Terrestrial Networks

With the increasing attention to the integrated satellite-terrestrial networks (ISTNs), the satellite gateway placement problem becomes of paramount importance. The resulting network performance may vary depending on the different design strategies. In this paper, a joint satellite gateway placement and routing strategy for the terrestrial network is proposed to minimize the overall cost of gateway deployment and traffic routing, while adhering to the average delay requirement for traffic demands. Although traffic routing and gateway placement can be solved independently, the dependence between the routing decisions for different demands makes it more realistic to solve an aggregated model instead. We develop a mixed-integer linear program (MILP) formulation for the problem. We relax the integrality constraints to achieve a linear program (LP) which reduces time-complexity at the expense of a sub-optimal solution. We further propose a variant of the proposed model to balance the load between the selected gateways.

cs.NI↗

arXiv2020

Joint Mobility-Aware UAV Placement and Routing in Multi-Hop UAV Relaying Systems

Unmanned Aerial Vehicles (UAVs) have been extensively utilized to provide wireless connectivity in rural and under-developed areas, enhance network capacity and provide support for peaks or unexpected surges in user demand, mainly due to their fast deployment, cost-efficiency and superior communication performance resulting from Line of Sight (LoS)-dominated wireless channels. In order to exploit the benefits of UAVs as base stations or relays in a mobile network, a major challenge is to determine the optimal UAV placement and relocation strategy with respect to the mobility and traffic patterns of the ground network nodes. Moreover, considering that the UAVs form a multi-hop aerial network, capacity and connectivity constraints have significant impacts on the end-to-end network performance. To this end, we formulate the joint UAV placement and routing problem as a Mixed Integer Linear Program (MILP) and propose an approximation that leads to a LP rounding algorithm and achieves a balance between time-complexity and optimality.

cs.NI↗