Jul 2026· International Journal of Communication Systems· Vol 39· 0 citations· 31 references
TL;DR
An innovative combination of Multi‐Relational Skeleton Graph Attention Networks is proposed to cater to the challenge of understanding multiple relational behaviors in data traffic and is optimized with the Greater Cane Rat Optimization Algorithm to enhance learning efficiency and the precision of congestion control.
Abstract
The emergence of 5G and the imminent deployment of 6G networks have revolutionized wireless communication by enabling ultra‐reliable low‐latency communication, enhanced mobile broadband, and massive machine‐type communication. While these diverse applications foster increasingly complex congestion scenarios due to highly dynamic traffic patterns, diverse requirements of different services, and ultra‐dense deployments of the network, efficient congestion control has become a pressing challenge. Conventional methods cannot address the nonlinear and multi‐relational characteristics of data traffic. Therefore, with the rapid scaling of connected devices with heterogeneous service demands, bottlenecks will be experienced, which leads to packet loss, increased latency, and poor QoS. Given the above challenges, this paper introduces an advanced congestion control framework developed on top of intelligent graph‐based learning and optimization strategies. The input data is from the DeepSense 6G dataset and preprocessed using Z‐score and min–max normalization to enhance the stability and uniformity of the preprocessed data. The feature selection is further fine‐tuned through the Orchard Algorithm (OA), ensuring highly relevant feature selection. An innovative combination of Multi‐Relational Skeleton Graph Attention Networks is proposed to cater to the challenge of understanding multiple relational behaviors in data traffic. Furthermore, the performance of the integrated model is optimized with the Greater Cane Rat Optimization Algorithm to enhance learning efficiency and the precision of congestion control. Experimental analysis demonstrates an outstanding accuracy of 99.9%, ensuring the proposed approach effectively mitigates congestion in 5G/6G networks.
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 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.
Manoj Prasad Kunasegran, Wai Leong Pang, S. K. Phang· IEEE Access· 0 citations
Routing optimization in cloud-edge collaborative networks faces a fundamental conflict between global strategic planning and local real-time responsiveness, further complicated by structural heterogeneity and stochastic traffic patterns. Traditional protocols lack adaptivity, while existing Deep Reinforcement Learning (DRL) approaches based on Graph Neural Networks (GNN) struggle with limited receptive fields and over-smoothing issues in large-scale topologies. In this paper, we propose HAT-Route, a Transformer-driven hierarchical routing framework supported by the Network Digital Twin (NDT). Our contributions are threefold: 1) We establish a cloud-edge collaborative architecture operating under the Centralized Training and Decentralized Execution paradigm. This architecture balances the trade-off between global optimization and real-time inference. 2) We introduce FlowFormer, a Spatiotemporal Transformer for the NDT. FlowFormer integrates a novel Edge-Conditioned Spatial Attention (EC-SAT) mechanism to capture physical link constraints and distinguish between congestion and Head-of-Line (HOL) blocking. 3) We design HAT-Route, a hierarchical DRL agent that utilizes Graph Transformers for global policy learning in the cloud, coupled with knowledge distillation to deploy lightweight policies at the network edge. Extensive experiments demonstrate that our framework outperforms traditional protocols and GNN-based baselines in terms of QoS optimization, training stability, scalability, and generalization capability on large-scale network topologies.
Bin Dai, Yuntao Wang, Jianhai Zheng· IEEE Transactions on Network...· 0 citations
The rapid deployment of fifth-generation (5G) mobile communication systems has significantly transformed wireless connectivity by supporting ultra-high data rates, ultra-low latency, massive machine-type communications, and heterogeneous Internet of Things (IoT) applications. However, the unprecedented growth in mobile traffic, dynamic user mobility, and diversified quality-of-service requirements have introduced substantial challenges in traffic prediction, congestion management, spectrum utilization, and network resource allocation. Conventional optimization techniques often fail to adapt to the highly dynamic and nonlinear characteristics of modern 5G environments. Deep learning has emerged as an effective paradigm for intelligent traffic optimization by learning complex spatial-temporal traffic patterns from large-scale network data and enabling proactive decision-making. Advanced architectures such as Long Short-Term Memory networks, Convolutional Neural Networks, Graph Neural Networks, Autoencoders, and Deep Reinforcement Learning provide enhanced capabilities for traffic forecasting, dynamic routing, load balancing, network slicing, edge intelligence, and energy-efficient resource management. This paper investigates the integration of deep learning algorithms into 5G traffic optimization frameworks, presents a comprehensive review of recent developments, proposes an intelligent AI-driven optimization architecture, evaluates major performance metrics, and discusses implementation challenges, scalability issues, and future research directions toward autonomous next-generation mobile networks.
Kamal N, Thirupathi Sundararajulu, Ashok Kumar R et al.· International journal of com...· 0 citations
SAGE (Scene-Adaptive Graph-Enhanced offloading), a task-offloading framework that combines a heterogeneous graph neural network (HeteroGNN) with a dueling double DQN meta-controller and a mixed-integer linear programming (MILP) solver, is proposed, demonstrating strong scene-adaptive decision-making capability.
Lingtao Xue, Xuewen Dong, Xinyu Hu et al.· Electronics· 0 citations
The rapid development of Wide Area Networks (WANs) in recent years has imposed new requirements on Traffic Engineering (TE) solutions in terms of robust to frequent and dynamic traffic fluctuations, scalable to maintain computational efficiency, and working well with limited historical traffic data. However, existing TE solutions generally struggle to achieve all three requirements simultaneously. Model-based solutions often fall short in realizing both good scalability and robustness against traffic fluctuations. Although recent deep learning-based solutions achieve strong scalability and robustness for public datasets, their effectiveness heavily relies on large numbers of Traffic Matrices (TMs). In this paper, we propose Criticality-Aware Range Routing (CARR) to achieve the three requirements using two techniques. First, we propose data and model hybrid-driven approach to alleviate dependence on large-scale datasets by integrating deep reinforcement learning with existing well-established routing models. Second, we develop hierarchical collaborative multi-model optimization to achieve both robustness and scalability by properly distributing routing tasks of TE to different routing models based on their specific features. Evaluations on public datasets with real traffic traces demonstrate that CARR achieves good performance using only 96 TMs, improving the worst-case performance by 79% at the cost of 2% median-case performance, and reduces computational overhead by more than $10\times $ .