Domain-guided soft actor-critic for network slicing in cell-free massive MIMO systems
Author Identifier (ORCID)
Abstract
Cell-free massive multiple-input multiple-output (mMIMO), which eliminates cell edge effects and enhances coverage and resource utilization, is suited for industrial Internet of things (IIoT) applications. In user-centric cell-free mMIMO-based IIoT networks, joint optimization of network slicing and access point (AP) selection is crucial for meeting diverse quality-of-service (QoS) requirements. However, the joint optimization is challenging due to the coupling of resource allocation decisions and typically imperfect channel state information. In this paper, we formulate the joint AP selection and network slicing problem as a constrained Markov decision process (CMDP) with a hybrid action space, and propose a deep reinforcement learning (RL) algorithm, domain-guided hybrid soft actor-critic for CMDP (DG-HSA2C), to maximize the long-Term proportional fairness in UE transmission rates while ensuring their QoS across slices. DG-HSA2C integrates CMDP-based RL into a hybrid action space by extending the Lagrangian multiplier method. To mitigate reward hacking, our algorithm incrementally predicts future states and incorporates a domain-Adaptation mechanism, enhancing fairness in resource allocation and balancing performance across slices. Simulations verify our algorithm's effectiveness in achieving rate fairness among UEs and mitigating reward hacking under the balance of QoS and rewards.
Keywords
cell-free massive MIMO, constrained Markov decision process, deep reinforcement learning, network slicing
Document Type
Journal Article
Date of Publication
1-1-2026
E-ISSN
15580857
ISSN
00906778
Volume
74
Publication Title
IEEE Transactions on Communications
Publisher
IEEE
School
School of Engineering
RAS ID
101823
Funding Information
National Natural Science Foundation Program of China (NSFC) (Grant Number: U21B2029 and 62531019), Zhejiang Provincial Natural Science Foundation of China (Grant Number: LR23F010006 and LQN25F010001), Pioneer and Leading Goose R&D Program of Zhejiang (Grant Number: 2026LDC01013(JT), Fundamental Research Funds for the Provincial Universities of Zhejiang (Grant Number: 2024YW39), National Research Foundation, Singapore and Infocomm Media Development Authority under its Communications and Connectivity Bridging Funding Initiative, China Scholarship Council.
Copyright
subscription content
First Page
11486
Last Page
11503
Recommended Citation
Li, N., Song, M., Shan, H., Ni, W., Wang, Y., Li, X., Quek, T. Q. S., & Jamalipour, A. (2026). Domain-guided soft actor-critic for network slicing in cell-free massive MIMO systems. IEEE Transactions on Communications, 74, 11486–11503. https://doi.org/10.1109/TCOMM.2026.3712554