Learning Power Control Protocol for In-Factory 6G Subnetworks

2025-05-09

AI Summary

To address severe interference, high signaling overhead, and poor scalability arising from reliance on global channel state information (CSI) in ultra-dense 6G factory subnets, this paper proposes a decentralized joint signaling and power control protocol. We formulate the problem for the first time as a partially observable Markov decision process (POMDP), eliminating dependence on a central controller and on complete or real-time CSI. Leveraging a multi-agent reinforcement learning (MARL) framework, we employ the MAPPO algorithm to enable distributed, autonomous, and cooperative optimization. Experimental results demonstrate that the proposed scheme reduces signaling overhead by 8×, achieves a buffer clearing rate only 5% lower than the ideal genie-aided benchmark, and significantly improves spectral efficiency and system scalability.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Multiagent Systems: Mechanism Design
• Search and Optimization: Distributed Search

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

In-X Subnetworks are envisioned to meet the stringent demands of short-range communication in diverse 6G use cases. In the context of In-Factory scenarios, effective power control is critical to mitigating the impact of interference resulting from potentially high subnetwork density. Existing approaches to power control in this domain have predominantly emphasized the data plane, often overlooking the impact of signaling overhead. Furthermore, prior work has typically adopted a network-centric perspective, relying on the assumption of complete and up-to-date channel state information (CSI) being readily available at the central controller. This paper introduces a novel multi-agent reinforcement learning (MARL) framework designed to enable access points to autonomously learn both signaling and power control protocols in an In-Factory Subnetwork environment. By formulating the problem as a partially observable Markov decision process (POMDP) and leveraging multi-agent proximal policy optimization (MAPPO), the proposed approach achieves significant advantages. The simulation results demonstrate that the learning-based method reduces signaling overhead by a factor of 8 while maintaining a buffer flush rate that lags the ideal"Genie"approach by only 5%.

Problem

• Mitigating interference in high-density 6G In-Factory Subnetworks
• Reducing signaling overhead in power control protocols
• Enabling autonomous learning of power control without full CSI

Innovation

• Multi-agent reinforcement learning for power control
• POMDP formulation with MAPPO optimization
• Reduces signaling overhead by 8 times