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.
Abstract
Efficient task offloading in UAV-assisted heterogeneous mobile edge computing (MEC) networks is increasingly challenged by the co-existence of operationally distinct workload scenarios—including high-demand bursts, resource-constrained periods, and balanced operational states—each demanding fundamentally different assignment strategies. In such networks, mobile executor nodes (e.g., UAVs or vehicle-mounted edge servers) must be dispatched to the vicinity of geographically distributed tasks, making assignment decisions jointly dependent on node mobility, the quality of sensing data, and dynamic resource availability. Conventional approaches based on combinatorial optimization with fixed parameters or greedy heuristics fail to adapt to these varying conditions, leading to resource depletion under sequential workloads or underutilization under high-demand bursts. To address these limitations, this paper proposes 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. At the state-representation level, a heterogeneous bipartite graph is constructed over mobile executor nodes and tasks, with type-specific projection layers encoding the semantic features of each node type and three-dimensional edge features—comprising task success probability, normalized service distance, and link quality—integrated via edge-gated message passing. At the decision level, the meta-controller perceives the current workload scenario through a seven-dimensional situational state vector fused with the graph embedding, selects an appropriate offloading strategy from a learned discrete action space, and drives the MILP solver to perform task-chain assignment under the selected configuration. Experiments on 60 fixed evaluation episodes spanning three representative workload scenarios demonstrate that SAGE achieves an overall reward improvement of 15.9% over the best fixed-strategy baseline, reduces the resource depletion rate to 16.7%, and maintains a high-priority task completion rate of 84.7%. Particularly under resource-constrained conditions, SAGE reduces the reward deficit by 72.3% relative to the best fixed strategy (from −0.531 to −0.147), demonstrating strong scene-adaptive decision-making capability.
The proliferation of heterogeneous compute-intensive services, such as large language models (LLMs), metaverse, cloud virtual reality (VR), and digital twins, poses unprecedented challenges to computing power-based optical transport networks (OTNs). These emerging applications require fine-grained bandwidth provisioning coupled with intelligent compute node selection, creating a natural contradiction with the static and rigid OTN pipeline architecture. While fine-grain OTN (fgOTN) enables dynamic orchestration through a multi-tier mapping hierarchy: fgOTN timeslots to Optical Data Units (ODUk) to wavelengths, the resulting massive action space and long-latency global state collection severely limit real-time decision-making. This paper proposes a Graph-Embedded En-Route Reinforcement Learning (GEERL) framework that efficiently encodes network topology into compact graph representations by exploiting topological correlations between structure and traffic patterns, enabling fast per-hop decisions without centralized planning overhead. By performing hierarchical per-hop resource allocation, GEERL achieves autonomous network orchestration with significantly reduced latency. Simulation results on the NSFNET and GERMANY50 topologies demonstrate that GEERL reduces average task completion delay by up to 48% and blocking probability by up to 78% compared with centralized Global-DQN planning approaches, while maintaining comparable resource utilization. The proposed en-route decision mechanism significantly reduces the estimated local decision latency compared with centralized schemes, supporting low-latency online orchestration under varying offered-load conditions.
Tiankuo Yu, Hui Yang, Q. Yao et al.· IEEE Open Journal of the Com...· 0 citations
In today’s world, with the emergence of IoT devices and critical latency applications, there has been an increased demand for intelligent resource management in diverse computing environments [5][10]. Collaborative computing is the integration of cloud and edge computing, while the issue of how to schedule each task for execution is still an open problem. Traditional heuristics like Round Robin and greedy latency reduction are incapable of adapting to the stochastic and non-stationary characteristics of practical workloads [4][14]. In this paper, an intelligent task scheduling mechanism based on Double Deep Q-Network (DDQN) reinforcement learning [2] has been proposed. The agent observes a four-dimensional state encoding task characteristics and selects binary offloading decisions, guided by a shaped reward signal encoding multiple performance objectives. Experimental evaluation on a heterogeneous synthetic benchmark demonstrates that the proposed DDQN scheduler reduces SLA violations by approximately 85% relative to Round Robin and 72% relative to the greedy baseline, while achieving superior energy efficiency. These results confirm that deep reinforcement learning [1][17][18] provides a principled foundation for adaptive resource management in next-generation edge-cloud systems.
Vishakha Makode, Taresh Ayaspure· Journal of Advances in Devel...· 0 citations
A two-timescale multi-layer deep reinforcement learning framework with a latent action space (2T-MDRL-LA) to jointly optimize service placement, user association, computational delegation, task offloading, and user transmit power and achieves near-optimal performance compared to branch-and-bound solutions.
V. Son, Van-Dinh Nguyen, Ngoc Hung Nguyen et al.· 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, Yuntao Wang, Jianhai Zheng· IEEE Transactions on Network...· 0 citations
The rapid growth of real-time and computation-intensive applications, such as face recognition, virtual reality, 3D
gaming, augmented reality, and intelligent transportation systems, has significantly increased the demand for efficient data
processing and low-latency services. However, mobile devices are constrained by limited computational capabilities and
battery capacity, making them unsuitable for executing heavy workloads locally. Mobile Edge Computing (MEC) has
emerged as a promising paradigm to offload computation tasks to nearby edge servers, thereby reducing latency and
improving service quality. Despite its advantages, task offloading in MEC environments remains challenging due to the
distributed nature of edge resources, energy constraints of end devices, and dynamic net- work conditions. Existing solutions
based on heuristic methods, genetic algorithms, NOMA-based techniques, and mobility-aware services often suffer from
high latency, excessive energy consumption, and task migration overhead. To address these limitations, this paper
investigates a reinforcement learning-based computation offloading strategy using an improved Deep Deterministic Policy
Gradient (IDDPG) algorithm. The proposed IDDPG approach enables decentralized decision-making by learning optimal
offloading policies from local observations, effectively balancing local execution and task offloading. By minimizing
computation costs, power consumption, and latency, the proposed method outperforms greedy offloading strategies and
demonstrates improved efficiency in dynamic MEC environments.
S. Alam, Sami Ud Din, Imtiaz Ali Shah et al.· International Journal of Inn...· 0 citations