arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.31334cs.AI
收藏

面向6G网络的联合OFDM波形设计与RIS配置的优化算法:从凸松弛到基础模型

Optimization Algorithms for Joint OFDM Waveform Design and RIS Configuration in 6G Networks: From Convex Relaxation to Foundation Models

Istanbul Medipol University(伊斯坦布尔梅迪波尔大学)

Ahmet Kaplan

AI总结:

综述2021-2026年间78篇联合OFDM-RIS优化工作,将其分为四类范式,发现基于ML的方法在推理速度上比模型方法快2-4个数量级,并指出六个开放挑战。

摘要:

面向6G的联合OFDM-RIS优化是一个混合整数非线性规划(MINLP)问题,涵盖和速率最大化、能量效率、最大最小公平性和峰均比(PAPR)约束目标。本文调查了2021年至2026年间发表的78篇联合OFDM-RIS优化工作。目前尚无标准化基准,跨论文比较仍不可行。本综述将这些工作分为四类范式:(I)基于模型的凸松弛,(II)启发式和元启发式搜索,(III)深度强化与无监督学习,以及(IV)新兴方法,包括基础模型(FM)、基于扩散的生成式AI和量子优化。对自报告基准的文献综合表明,基于ML的方法(范式III)报告了基于模型频谱效率的95-99%,而每次推理运行时间快10^2-10^4倍(依赖于方法对;文献值为自报告,不包括ML预训练成本)。在N=16、N=64和N=128下的配套教程基准揭示了一个关键的缩放特性:基于GPU的神经网络推理(DDQN、PPO、图神经网络(GNN)、无监督DL)是N不变的,在N=16和N=128时运行时间相同,而迭代求解器(AO+SCA、PSO)呈多项式缩放。能量效率(P2)和PAPR约束(P4)基准将推迟到未来工作,使用标准化功率模型和波形生成器。综合中出现了六个开放挑战:跨范式基准缺失、实际硬件约束部署、双弥散信道的联合波形-RIS优化、多目标PAPR权衡、实时网络控制中的LLM安全性以及独立启发式方法的收益递减。我们指定了标准化基准的要求。本研究为从事6G网络中联合OFDM-RIS优化的研究人员和从业者提供了路线图。

英文摘要:

Joint OFDM-RIS optimization for 6G is a mixed-integer nonlinear programming (MINLP) problem covering sum-rate maximization, energy efficiency, max-min fairness, and peak-to-average power ratio (PAPR)-constrained objectives. Seventy-eight joint OFDM-RIS optimization works published between 2021 and 2026 are surveyed. No standardized benchmark exists, and cross-paper comparisons remain infeasible. This survey classifies these works into four paradigms: (I) model-based convex relaxation, (II) heuristic and metaheuristic search, (III) deep reinforcement and unsupervised learning, and (IV) emerging methods including foundation models (FM), diffusion-based generative AI, and quantum optimization. A literature synthesis of self-reported benchmarks shows that ML-based methods (Paradigm~III) report 95-99\% of model-based spectral efficiency at 10^2-10^4 x faster per-inference runtime (method-pair dependent; literature values are self-reported and exclude ML pre-training cost). A companion tutorial benchmark at N=16, N=64, and N=128 reveals a critical scaling property: GPU-based neural network inference (DDQN, PPO, graph neural network (GNN), unsupervised DL) is N-invariant, with identical runtime at N=16 and N=128, while iterative solvers (AO+SCA, PSO) scale polynomially. Energy efficiency (P2) and PAPR-constrained (P4) benchmarks are deferred to future work with standardized power models and waveform generators. Six open challenges emerge from the synthesis: the cross-paradigm benchmark deficit, real-world hardware-constrained deployment, joint waveform-RIS optimization for doubly-dispersive channels, multi-objective PAPR trade-offs, LLM safety in live network control, and diminishing returns of standalone heuristics. We specify requirements for a standardized benchmark. This study serves as a roadmap for researchers and practitioners working on joint OFDM-RIS optimization in 6G networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑