Leveraging Deep Reinforcement Learning for Clustered Cell-Free Networking Over User Mobility

2026-05-17

AI Summary

This work addresses the challenges of excessive channel measurement overhead, high computational complexity, and poor adaptability to dynamic changes in conventional network clustering methods under highly mobile user scenarios. To overcome these limitations, the authors propose DDPG-C²F, a deep reinforcement learning–based framework for efficient and dynamic clustering in cell-free networks. The proposed approach requires each access point to estimate only a single channel state, drastically reducing both measurement and computational costs while enabling adaptive deployment under diverse optimization objectives and constraints. Experimental results demonstrate that the method consistently outperforms existing baselines across various scenarios, significantly lowering handover overhead and maintaining stable performance even when users randomly join or leave the network, thereby enhancing system robustness and scalability.

Abstract

Clustered cell-free networking paves a new way for enabling scalable joint transmission among access points (APs) by partitioning the whole network into non-overlapping subnetworks. Previous works adopted clustering algorithms, graph partitioning methods or conventional continuous optimization theories to partition a network based on the channels between all users and all APs, resulting in huge channel measurement and computational costs. This makes these methods difficult to be implemented in practical systems since the optimal network partition could vary frequently due to user mobility. In addition, existing methods were usually designed for specific clustered cell-free networking problems with different optimization algorithms employed. In this paper, we leverage deep reinforcement learning (DRL) for clustered cell-free networking so as to rapidly adapt to user movements in dynamic environments, and propose a deep deterministic policy gradient based clustered cell-free networking (DDPG-C$^{2}$F) framework that can be adapted in various application scenarios. Moreover, in our framework, only one single channel needs to be estimated at each AP as the input of the neural network, which greatly reduces the channel measurement costs for clustered cell-free networking, and the training and inference costs of our framework. The proposed DDPG-C$^{2}$F framework is then applied to various clustered cell-free networking problems with different objectives and constraints to demonstrate its performance. Simulation results show that our framework outperforms existing baselines in all scenarios. Moreover, we show that the proposed framework can reduce the handover cost over user mobility, and is robust to dynamic scenarios with random user joining or leaving.

Problem

• clustered cell-free networking
• user mobility
• network partitioning
• channel measurement cost
• dynamic environment

Innovation

• Deep Reinforcement Learning
• Cell-Free Networking
• User Mobility
• Network Clustering
• Channel Estimation