A QoE-aware framework for Multi-Access Edge Computing-enabled Open Radio Access Network (O-RAN) architectures, combining a graph attention network (GAT) encoder, distributed multi-agent DRL, and privacy-preserving FL, while transitioning control from Quality of Service (QoS) to QoE metrics is proposed.
Abstract
Fifth generation (5G) networks deliver multi-gigabit data rates, sub-millisecond latency, and dense connectivity through a customised service delivery paradigm built on virtualisation and network slicing (NS). However, conventional NS frameworks rely on threshold-based control and lack the context awareness needed for autonomous, user-centric decision-making. Machine learning (ML) optimization-driven methods such as deep reinforcement learning (DRL) and hybrid metaheuristic–ML approaches can close this gap by inferring user bandwidth behaviour, anticipating congestion, and enacting proactive corrective actions. This paper presents a systematic, PRISMA-based review of 2024–2026 ML-based optimization for user-centric distributed NS, screening 6,286 records to 67 core studies that are normalised through a common evidence tuple. A comprehensive critical review is then presented with role-oriented matrices spanning admission control, resource allocation and offloading, orchestration, graph learning, and federated learning (FL). From this synthesis, we derive recurring optimization formulations and identify persistent gaps, namely the absence of direct Quality of Experience (QoE) inference, privacy preservation, topology awareness, and validated deployment. To address these gaps, we propose a QoE-aware framework for Multi-Access Edge Computing (MEC)-enabled Open Radio Access Network (O-RAN) architectures, combining a graph attention network (GAT) encoder, distributed multi-agent DRL, and privacy-preserving FL, while transitioning control from Quality of Service (QoS) to QoE metrics. The proposed framework is also grounded in preliminary validation from our two prior slice admission control and load balancing studies, offering a scalable, privacy-aware, and truly user-centric path towards 5G and Beyond 5G networks.
This paper presents a comprehensive framework for artificial intelligence (AI)-enabled autonomous network slicing optimization in 6G systems and investigates the application of advanced machine learning paradigms specifically deep reinforcement learning, federated learning, and generative AI to orchestrate dynamic resource provisioning, cross-slice isolation, and proactive SLA (Service Level Agreement) enforcement.
N. P J, Jeeva Jothi· International Journal of Com...· 0 citations
The emergence of 5G and 6G advanced ecosystems demands highly adaptive resource management to orchestrate the specialised requirements of eMBB, URLLC, and mMTC network slices. In dense multi-cell environments, capturing complex spatial interdependencies and mitigating dynamic interference is paramount for maintaining Quality of Service (QoS). This paper introduces a robust GNN-DQN framework designed for Rate Splitting Multiple Access (RSMA) based networks. By representing the network topology as a graph, the framework leverages Graph Neural Networks (GNNs) to extract highdimensional spatial features and model inter-cell interference patterns. These insights enable a Deep Q-Network (DQN) agent to perform intelligent resource partitioning and dynamic power splitting of the RSMA common stream. Experimental results demonstrate that the proposed GNN-DQN framework achieves a connectivity success ratio exceeding 90% across all slices, representing an average improvement of over 60% compared to non-graph-based reinforcement learning and supervised baselines. Notably, the framework demonstrates exceptional spectral efficiency, maintaining near-total connectivity while utilising less than 10% of the normalised system bandwidth, a 4× reduction in resource overhead compared to traditional methods. Furthermore, the GNN-driven architecture ensures stable convergence during training, yielding a 1.6× higher system reward score. Our findings validate GNN-DQN as a high-performance, scalable, and resource-efficient paradigm for intelligent orchestration in 5G and 6G networks.
Aya Kh. Ahmed, Nadia Al-Aboody, Hamed S. Al-Raweshidy· International Conference on...· 0 citations
A constrained optimization model that supports different management goals through alternative objective functions (latency-aware or power-aware) while enforcing operational constraints, including node capacities, slice-specific latency bounds, and explicit limits on VNF migrations/relocations between scheduling periods is proposed.
R. Moreno-Vozmediano, E. Huedo, R. Montero et al.· Journal of Network and Syste...· 0 citations
Future sixth-generation (6G)-oriented networks require programmable control that can adapt routing to latency and congestion without unsafe online exploration. This study evaluates offline multi-agent deep deterministic policy gradient (MADDPG) with behavior-adjusted training rewards for latency-aware path control in software-defined networking (SDN). Each traffic pair is modeled as an agent selecting one of three retained candidate paths, while centralized critics learn coordinated decisions from topology-specific Ryu–Mininet transition datasets. Nine policies are compared using ten paired seeds on fat-tree, mesh-grid, and WAN-corridors topologies under a deployed utilization–latency weighting of 0.60/0.40, together with flow-completion, latency, congestion, architectural-comparison, sensitivity, robustness, statistical, and controller-overhead analyses. The utilization-aware path heuristic achieves the strongest overall reward ranking. MADDPG is the strongest learned policy on fat-tree, is not significantly outperformed by any evaluated policy on mesh-grid, and remains statistically tied with completion-matched policies on WAN-corridors. Behavior adjustment is topology-dependent rather than uniformly beneficial. The exported policy requires approximately 52μs per joint decision, whereas complete control-loop timing is dominated by network-statistics polling. These results support offline multi-agent SDN control as a competitive, low-overhead option when interpreted jointly with topology structure, flow completion, and strong heuristic baselines.
A. Kyzyrkanov, Y. Nurakhov, Zhenis Otarbay et al.· Technologies· 0 citations
Network slicing is an enabling technology of fifth-generation (5G) mobile networks that enables several autonomous logical networks to exist on a common physical infrastructure. One key issue of the paradigm is the admission control mechanism which slice requests are accepted to achieve the best performance of the system and still ensure quality-of-service (QoS) guarantees. In this paper, the authors provide a comparative study of the current methods of admission control and introduce a new approach, Priority-Aware Deep Q-Network with Dynamic Threshold Adaptation (PA-DQN-DTA). Our method (as opposed to the traditional methods which tie admission control to resource allocation) addresses intelligent admission decisions only. The suggested scheme uses inter-slice and intra-slice priorities via a mathematically defined admission probability functional. The outcomes of simulation in four assessment scenarios show that parameter calibration is of the essence: the balanced configuration reaches acceptance ratios of 11.812.9, and QoE in all scenarios is above 98.8%. Besides, this paper presents an in-depth analysis of parameter tuning and describes the space of tradeoffs between the acceptance ratio, the QoE preservation, and the resource usage. Concrete recommendations are made and implications to the realistic 5G deployment are discussed.
A. S. Mahore, C. N. Deshmukh· International Conference Com...· 0 citations
Real-time inter-slice resource allocation in the Radio Access Network (RAN) is a critical control function in 5G and emerging 6G networks, where the scheduler in the Distributed Unit (DU) dynamically allocates physical resources, namely Physical Resource Blocks (PRBs), to different network slices to meet their diverse Quality of Service (QoS) requirements. To address the need for faster and more flexible radio resource management, and inspired by recent efforts to extend the O-RAN architecture with a real-time controller, we investigate slice-level PRB allocation through the lens of online learning. We formulate inter-slice scheduling as a dynamic decision problem and develop a system model that captures per-slice Service Level Agreement (SLA) requirements and throughput variations over configurable time windows, without assuming future channel knowledge. Our scheduling solution is implemented as a real-time RAN control application, in line with the O-RAN proposition for dApps that are programmable and distributed software components for fine-grained control in O-RAN DUs (O-DUs) and Centralized Units (O-CUs). The proposed approach adapts inter-slice radio resource allocations based on telemetry, with low computational complexity. Experimental results show sublinear dynamic regret, up to 85% fewer SLA violations than static baselines, and submillisecond amortized control overhead. Overall, these findings highlight dynamic-benchmark online control as a practical mechanism for real-time, SLA-aware slicing in O-RAN.
Asim Zoulkarni, C. Papagianni, Georgios Iosifidis et al.· International Mediterranean...· 0 citations