AI4C2 – 6G Network Slicing and Resource Management
Wednesday, 4 June 2025, 16:00-17:30, room 1.G
Session Chair: Katarzyna Kosek-Szott (AGH University of Krakow, PL)
Leveraging Infrastructure Monitoring for User Experience Forecasting in Container-Based 5G Core
Bruno Marques Silva and Rodrigo Moreira (Federal University of Viçosa, Brazil); Larissa F. Rodrigues Moreira (Federal University of Uberlândia, Brazil); Flavio de Oliveira Silva (University of Minho, Portugal & Federal University of Uberlândia, Brazil)
Integrating intelligence in mobile networks enhances resource management and ensures compliance with Service Level Agreements (SLAs). However, the complexity of subsystems and interactions in the network-slicing lifecycle poses challenges. Existing studies often rely on simulated datasets or monitoring systems, which face limitations in generalization, privacy, and real-time responsiveness due to data quality and complexity of the Machine Learning (ML) algorithm. Although advanced monitoring systems improve accuracy, their high computational cost necessitates low-overhead alternatives. This paper demonstrates that generic computing and network metrics in container-based 5G core can accurately reveal user experience in mobile networks, achieving a 10.5232% Mean Absolute Percentage Error (MAPE) with feature-based and sequence-based ML algorithms.
Offline and Distributional Reinforcement Learning for Radio Resource Management
Eslam Eldeeb and Hirley Alves (University of Oulu, Finland)
Reinforcement learning (RL) has proved to have a promising role in future intelligent wireless networks. Online RL has been adopted for radio resource management (RRM), taking over traditional schemes. However, due to its reliance on online interaction with the environment, its role becomes limited in practical, real-world problems where online interaction is not feasible. In addition, traditional RL stands short in front of the uncertainties and risks in real-world stochastic environments. In this manner, we propose an offline and distributional RL scheme for the RRM problem, enabling offline training using a static dataset without any interaction with the environment and considering the sources of uncertainties using the distributions of the return. Simulation results demonstrate that the proposed scheme outperforms conventional resource management models. In addition, it is the only scheme that surpasses online RL with a 10 % gain over online RL.
Towards Cloud-Native Agentic Protocol Learning for Conflict-Free 6G: a Case Study on Inter-Slice Resource Allocation
Juan Sebastian Camargo (i2CAT Foundation, Spain); Farhad Rezazadeh (Universidad Politécnica de Cataluña (UPC), Spain); Hatim Chergui (i2CAT Foundation, Spain); Muhammad Shuaib Siddiqui (Fundació i2CAT, Internet i Innovació Digital a Catalunya, Spain); Lingjia Liu (Virginia Tech, USA)
In this paper, we propose a novel cloud-native architecture for collaborative agentic network slicing. Our approach addresses the challenge of managing shared infrastructure, particularly CPU resources, across multiple network slices with heterogeneous requirements. Each network slice is controlled by a dedicated agent operating within a Dockerized environment, ensuring isolation and scalability. The agents dynamically adjust CPU allocations based on real-time traffic demands, optimizing the performance of the overall system. A key innovation of this work is the development of emergent communication among the agents. Through their interactions, the agents autonomously establish a communication protocol that enables them to coordinate more effectively, optimizing resource allocations in response to dynamic traffic demands. Based on synthetic traffic modeled on real-world conditions, accounting for varying load patterns, tests demonstrated the effectiveness of the proposed architecture in handling diverse traffic types, including eMBB, URLLC, and mMTC, by adjusting resource allocations to meet the strict requirements of each slice. Additionally, the cloud-native design enables real-time monitoring and analysis through Prometheus and Grafana, ensuring the system’s adaptability and efficiency in dynamic network environments. The agents managed to learn how to maximize the shared infrastructure with a conflict rate of less than 3%.
A Novel Framework for Proactive CNF Orchestration in 6G NTN
Alice Piemonti (Martel Innovate, Switzerland); Riccardo Campana (University of Bologna, Italy); Vito Cianchini (Martel Innovate Gmbh, Switzerland); Carla Amatetti (University of Bologna, Italy); Massimo Neri (Martel Innovate GmbH, Switzerland); Alessandro Vanelli-Coralli (University of Bologna, Italy)
The increasing complexity of 5G and beyond networks, particularly with the integration of Non-Terrestrial Networks (NTNs), demands more dynamic and intelligent approaches to Radio Access Network (RAN) optimization. This paper presents a novel framework for closed-loop NTN RAN optimization centered on proactive Containerized Network Function (CNF) orchestration. By leveraging Artificial Intelligence (AI) to anticipate virtual resource needs, the proposed framework enables efficient, real-time deployment and scaling of CNFs, significantly enhancing the resilience and adaptability of NTN systems. Our architecture leverages Machine Learning to predict crucial metrics such as CPU usage, memory, and bandwidth, and pre-allocate virtual resources, thereby reducing latency associated with reactive orchestration methods. This proactive approach ensures optimal allocation of limited NTN resources, improves network performance, and mitigates cold-start delays of containers. Through experimental analysis of AI-based forecasting models, our work proposes a proactive framework for CNF orchestration, demonstrating its potential to enable sustainable, scalable, and efficient CNF optimization tailored for 6G NTN solutions.
Online SLA Decomposition: Enabling Real-Time Adaptation to Evolving Network Systems
Cyril Shih-Huan Hsu (University of Amsterdam, The Netherlands); Danny De De Vleeschauwer (Nokia, Belgium); Chrysa Papagianni and Paola Grosso (University of Amsterdam, The Netherlands)
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 periodically 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.
