🤖 AI Summary
This study addresses the multi-objective mixed-integer nonlinear programming problem of jointly designing OFDM waveforms and configuring reconfigurable intelligent surfaces (RIS) for 6G. Synthesizing insights from 78 studies published between 2021 and 2026, it proposes the first cross-paradigm classification framework encompassing model-based convex relaxation, heuristic search, deep reinforcement and unsupervised learning, as well as emerging approaches integrating foundation models, diffusion-based generative AI, and quantum optimization. The work identifies a key property of neural network inference—maintaining constant latency under antenna array scaling (N = 16–128)—and establishes a standardized benchmark. Results demonstrate that machine learning methods achieve 95–99% of the spectral efficiency of model-driven approaches while accelerating inference by 10²–10⁴ times, and highlight six open challenges, including the lack of unified benchmarks, hardware-aware deployment constraints, and safety concerns regarding large models in real-time control.
📝 Abstract
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.