Deep Resource Allocation for Spectrum-Aggregated AAV Multicast Systems: A Neural Combinatorial Optimization Approach
- 8 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 5077-5091
Abstract
UAV-enabled multicast transmission is pivotal for low-altitude economy networking, but is fundamentally constrained by dynamic channel availability and fluctuations stemming from UAV mobility. Efficient integration of fragmented spectrum resources spanning multiple frequency bands for opportunistic multicast transmission not only elevates resource utilization but also broadens service scalability. Nevertheless, the fragmented spectrum exhibits strong frequency selectivity, compounded by the max-min objective inherent to multicast broadcast services (MBS) and the nonlinear channel aggregation characteristics, which collectively render the resource allocation problem an intricate max-min nonlinear combinatorial optimization problem. To tackle this challenge, this paper proposes an artificial general intelligence (AGI)-driven deep resource allocation algorithm for spectrum aggregation (SA)-enabled UAV-MBS systems, capable of accommodating diverse UE demands and flexible resources. A pointer network-based neural combinatorial optimization (NCO) solver, integrated with a self-reference reinforcement learning framework, is employed to achieve probability-driven sequential resource selection. Sensitivity analysis and stepwise decomposition are conducted to evaluate the effectiveness of the trained network, providing interpretability and deeper insights into the NCO solver. Simulation results demonstrate the proposed scheme’s superiority over baseline methods with significantly fewer explorations. Furthermore, the soft selection mechanism ensures robustness against inaccurate CQI knowledge, particularly in scenarios with overly optimistic channel conditions.Keywords
Funding Information
- National Key Research and Development Project of China (2023YFF0904603)
- National Natural Science Foundation of China (62422111)
- National Natural Science Foundation of China (62272075)
- National Natural Science Foundation of China (62431015)
- National Natural Science Foundation of China (62221005)
- Natural Science Foundation of Chongqing Municipality (CSTB2025NSCQ-LZX0050)
- Natural Science Foundation of Chongqing Municipality (CSTB2024NSCQ-JQX0013)
- Natural Science Foundation of Chongqing Municipality (CSTB2024NSCQ-QCXMX0058)
- Frontier Interdisciplinary Information Science Exploration Initiative (SCIE-ZYTS-11)
This publication has 41 references indexed in Scilit:
- An optimal calibration factor for mutual information effective SINR mapping scheme in 5G NRElectronics Letters, 2024
- Interpreting Black-Box Models: A Review on Explainable Artificial IntelligenceCognitive Computation, 2023
- 5G Link-Level Simulator for Multicast/Broadcast Services2023
- Vision, application scenarios, and key technology trends for 6G mobile communicationsScience China Information Sciences, 2022
- Cognitive radio based spectrum sharing models for multicasting in 5G cellular networks: A surveyComputer Networks, 2022
- Recent metaheuristic algorithms with genetic operators for high-dimensional knapsack instances: A comparative studyComputers & Industrial Engineering, 2022
- SNR-CQI Mapping for 5G Downlink Network2021
- Metaheuristic research: a comprehensive surveyArtificial Intelligence Review, 2018
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992
- Maximally dependent random variablesProceedings of the National Academy of Sciences, 1976