FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6G

2026-05-20 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation, Internet of Things (IoT) & Connected Devices · Depth: Expert, quick

Summary

FedCritic, a serverless federated multi-agent actor-critic framework, addresses distributed downlink resource management in sixth-generation (6G) ultra-dense networks. It tackles the challenges of inter-cell interference (ICI) and long-term per-user quality-of-service (QoS) minimum-rate constraints in multi-cell orthogonal frequency-division multiple access (OFDMA) scheduling and power control. Unlike centralized training with decentralized execution (CTDE) methods, FedCritic federates the critic through lightweight gossip-based parameter averaging over the interference graph, enabling stable value estimation without a central coordinator. Simulations in an interference-rich reuse-1 setting demonstrate that FedCritic improves mean signal-to-interference-plus-noise ratio (SINR) and cell-edge rate, increases network-wide average sum-rate and fairness, and achieves more stable training with lower coordination overhead compared to non-coordinated and CTDE baselines.

Key takeaway

For 6G Network Architects managing resource allocation in ultra-dense networks, you should consider FedCritic's serverless federated critic learning approach. This framework offers a decentralized solution to joint subcarrier scheduling and power allocation, effectively mitigating inter-cell interference and enforcing QoS. Its ability to improve SINR, cell-edge rates, and network fairness with lower coordination overhead makes it a compelling option for enhancing 6G network performance and stability.

Key insights

FedCritic is a serverless federated actor-critic framework for 6G resource allocation, using gossip-based critic averaging to manage interference.

Principles

• Aggressive frequency reuse amplifies inter-cell interference in 6G ultra-dense networks.
• Virtual-queue deficit weights can effectively enforce long-term QoS constraints.
• Federated critic learning enables stable value estimation without a central coordinator.

Method

FedCritic employs a serverless federated multi-agent actor-critic framework. It uses virtual-queue deficit weights for QoS and federates critic learning via lightweight gossip-based parameter averaging over the interference graph.

In practice

• Apply gossip-based averaging for decentralized critic learning in multi-agent systems.
• Utilize virtual-queue deficit weights for long-term QoS enforcement.
• Consider FedCritic for 6G multi-cell OFDMA resource management.

Topics

• 6G Networks
• OFDMA
• Federated Learning
• Resource Allocation
• Multi-agent Reinforcement Learning
• Interference Management

Best for: AI Scientist, Research Scientist, Machine Learning Engineer

Related on AIssential

• FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6G — FedCritic enables decentralized 6G resource allocation by federating critic learning via gossip, avoiding central coordination.
• Federated Multi Agent Deep Learning and Neural Networks for Advanced Distributed Sensing in Wireless Networks — MADL unifies decision-making and inference in tightly coupled wireless sensing, communication, and computing systems.
• A Reinforcement Learning Based Universal Sequence Design for Polar Codes — A reinforcement learning framework designs universal Polar code sequences, scaling to 2048 code lengths with performance gains.
• Optimization Algorithms for Joint OFDM Waveform Design and RIS Configuration in 6G Networks: From Convex Relaxation to Foundation Models — ML-based optimization offers significant speedups and N-invariance for 6G OFDM-RIS, despite current benchmarking challenges.
• AI-powered 6G core network reaches autonomous control with 40% efficiency gain — AI-powered 6G core networks can achieve autonomous control and significant efficiency gains, as demonstrated by a Korean research team.
• Diffusion Offline Reinforcement Learning for Fair and Energy-Efficient UAV-Assisted Wireless Networks — Diffusion-SAC combines offline RL with diffusion models for robust, data-efficient policy learning in dynamic wireless networks.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.