Optimization Algorithms for Joint OFDM Waveform Design and RIS Configuration in 6G Networks: From Convex Relaxation to Foundation Models
arXiv:2606.31334v1 Announce Type: new 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 reinforcem
The proliferation of complex communication demands in next-generation networks like 6G necessitates advanced optimization techniques for efficiency and performance.
This highlights the ongoing computational challenges and fragmented research efforts in integrating AI-driven optimization with hardware configurations for future wireless communication, crucial for widespread AI deployment.
The explicit recognition of a lack of standardized benchmarks impedes rapid progress and comparable results across various optimization approaches for 6G, indicating a fragmented research landscape.
- · AI/ML researchers in telecom
- · 6G infrastructure providers
- · Communication equipment manufacturers
- · Fragmented research efforts
- · Systems relying on ad-hoc optimization
Increased focus on standardized benchmarking and integrated AI/ML toolchains for 6G optimization.
Faster development and deployment of more efficient and robust 6G networks, enabling new applications.
The integration of foundation models could accelerate the path towards ubiquitous, intelligent communication fabrics, supporting advanced AI agentic systems and complex compute architectures.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI