2026· IEEE Transactions on Cognitive Communications and Networking· Vol 12, pp. 11552-11566· 0 citations· 35 references
Abstract
Dynamic channel allocation in wireless local area networks (WLANs) is essential for mitigating co-channel interference and satisfying time-varying traffic demands under limited spectrum resources. Beyond optimizing each network snapshot, an effective allocation scheme should preserve temporal continuity to avoid excessive channel switching. Graph neural networks (GNNs) have emerged as a promising solution by modeling topology-dependent interference relationships among access points (APs). However, most existing GNN-based schemes treat consecutive allocation steps independently and may suffer from oversmoothing, which can make interfering APs produce overly similar channel decisions. To address these issues, we propose the neighbor exclusion-based graph neural network for sequential channel allocation (NEG-SCA). The proposed framework learns allocation decisions from current traffic demand, previous allocation results, and graph-structured interference relationships. Its neighbor-exclusion aggregation reduces direct representation mixing among interfering APs, while its temporal-differential mechanism adaptively balances allocation preservation and demand-driven reallocation. Extensive simulations demonstrate that NEG-SCA achieves a favorable trade-off among interference reduction, switching-cost control, and demand satisfaction under diverse WLAN configurations.
The proliferation of UAVs operating in complex interference environments has intensified the demand for collaborative spectrum management to mitigate interference and maximize network capacity. This paper proposes a heterogeneous graph neural network (HGNN) framework for collaborative spectrum management in hierarchical UAV communication networks. The proposed architecture consists of three layers: a Terminal Transmission and Control Layer for local spectrum monitoring, a Sub-Domain Transmission and Control Layer for regional interference localization, and a Global Control Layer for network-wide spectrum optimization. Each layer incorporates multiple sensing UAVs that communicate exclusively with their own layer’s Transmission and Control UAV (T&C UAV), which aggregates and processes data from its subordinate sensing nodes and forwards the result upward through the T&C UAV chains. A hierarchical heterogeneous graph neural network with intra-layer and inter-layer message passing mechanisms was designed to capture the complex spatial–temporal dependencies in the spectrum environment under non-uniform interference conditions. The simulation results demonstrate that the proposed HGNN framework achieves steady-state utility gains of approximately 7.1% and 1.4% over the SL-GNN in 48-node and 81-node scenarios, respectively, along with corresponding Interference Suppression Ratio (ISR) improvements of 1.5 dB and 2.9 dB against the SL-GNN.
Yuan-Qiang Sun, Xueqing Zhang, Menglin Wang et al.· Drones· 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
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, Yun-Tao Wang, Jianhai Zheng· IEEE Transactions on Network...· 0 citations
Network slicing over space-division-multiplexed elastic optical networks (SDM-EONs) requires jointly managing spectrum, spatial cores, and compute resources, a coupling that many existing studies ignore by treating compute placement independently from routing and spectrum decisions. This disconnect can cause the spectrum to be allocated along a path, only for the request to fail due to insufficient compute resources along the path, or may result in compute resources being allocated without consideration for spectrum resource availability on the path between compute nodes. We propose a path-constrained reinforcement learning framework that addresses compute node selection and RMCSA, being aware of both resources, restricting the RL agent's action space to nodes along $k$-shortest paths between request endpoints. Training incorporates reward shaping to improve robustness under high load. We propose PPO-Full (Proximal Policy Optimization-Full), which jointly selects compute nodes and routing paths via a multi-dimensional action space, against distance-based heuristics, a greedy baseline, and a decoupled VONE-DRL baseline on a 24-node USNET topology under hotspot traffic conditions. Results demonstrate consistent improvements in acceptance rate over all baselines at high load, with gains becoming more pronounced as traffic intensity increases.
Divya Khanure, Riti Gour, Congzhou Li et al.· 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, Xue-Wen Dong, Xinyu Hu et al.· Electronics· 0 citations
Low Earth orbit (LEO) satellite networks exhibit rapidly changing topology and time-varying traffic hotspots, which makes hop-by-hop routing highly sensitive to local congestion and state staleness. Existing routing methods either rely on global path computation or use plain local observations, while graph-enhanced approaches often focus on generic neighborhood representation rather than direct comparison among candidate next hops. To address this issue, this paper proposes a Local Graph-Aware Routing method (LGAR) for dynamic LEO satellite networks. LGAR organizes the current node, reachable candidate neighbors, and candidate links into a local graph, and then constructs structured action representations through node encoding, relation message extraction, and attention-based context aggregation. The resulting representations are integrated into an off-policy actor-critic framework to support adaptive hop-by-hop routing decisions. Experiments under the hub-inversion setting show that LGAR achieves an average total delay of 47.64 ms and an average queueing delay of 5.81 ms while maintaining a delivery rate of 99.93%. Compared with MATMR, LGAR-NoGraph, and GRLR, LGAR reduces the average total delay by 12.38%, 12.85%, and 30.75%, respectively. Additional scenario, ablation, and scalability results further show that LGAR generalizes beyond the main setting and that its gain mainly comes from local graph modeling and relation-aware action encoding.
Wen-Xiang Zhang, Yiao Gao, Ke-Yan Bai et al.· 2026 8th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
