FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6G
arXiv:2605.21418v1 Announce Type: new Abstract: In sixth-generation (6G) ultra-dense networks, aggressive frequency reuse amplifies inter-cell interference (ICI), making multi-cell orthogonal frequency-division multiple access (OFDMA) scheduling and power control strongly coupled across neighboring cells. We study distributed downlink resource management -- joint subcarrier scheduling and power allocation -- under interference coupling and long-term per-user quality-of-service (QoS) minimum-rate constraints. By using virtual-queue deficit weights to enforce long-term QoS, we develop FedCritic,
The increasing demand for ultra-dense networks in 6G and the amplified inter-cell interference necessitate advanced resource management solutions.
Efficient resource allocation directly impacts the performance and economic viability of future 6G networks, which are crucial for AI, IoT, and other advanced applications.
Distributed, AI-driven resource management through serverless federated learning offers a new paradigm for optimizing complex 6G network operations.
- · Telecommunications infrastructure providers
- · AI/ML algorithm developers
- · 6G network operators
- · Smartphone manufacturers
- · Legacy network optimization solution providers
- · Inefficient spectrum users
Improved network efficiency and higher quality of service for 6G users.
Reduced operational costs for network providers and accelerated deployment of intelligent edge devices.
Enhanced foundational layer for distributed AI and autonomous systems, potentially underpinning future 'smart' infrastructure.
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.LG