Joint Power Allocation and Phase Shift Design for Stacked Intelligent Metasurfaces-aided Cell-Free Massive MIMO Systems with MARL

2025-02-27

AI Summary

To address the energy efficiency bottleneck in cell-free massive MIMO systems, this paper pioneers the integration of stacked intelligent metasurfaces (SIMs) into the architecture and jointly optimizes access point power allocation and SIM phase responses to maximize sum spectral efficiency. We propose NVR-MAPPO, a novel multi-agent reinforcement learning algorithm that incorporates a noise-value regularization mechanism and recurrent neural network–based policies, enhancing exploration diversity and convergence robustness under a centralized training–decentralized execution framework. Compared with baseline methods, the proposed approach achieves significant gains in sum spectral efficiency across diverse user distributions and channel conditions, while simultaneously improving energy efficiency and demonstrating strong generalization and robustness. This work establishes a new paradigm for co-optimizing reconfigurable electromagnetic surfaces and wireless resource allocation.

Technology Category

• Multiagent Systems: Multiagent Learning
• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Cell-free (CF) massive multiple-input multiple-output (mMIMO) systems offer high spectral efficiency (SE) through multiple distributed access points (APs). However, the large number of antennas increases power consumption. We propose incorporating stacked intelligent metasurfaces (SIM) into CF mMIMO systems as a cost-effective, energy-efficient solution. This paper focuses on optimizing the joint power allocation of APs and the phase shift of SIMs to maximize the sum SE. To address this complex problem, we introduce a fully distributed multi-agent reinforcement learning (MARL) algorithm. Our novel algorithm, the noisy value method with a recurrent policy in multi-agent policy optimization (NVR-MAPPO), enhances performance by encouraging diverse exploration under centralized training and decentralized execution. Simulations demonstrate that NVR-MAPPO significantly improves sum SE and robustness across various scenarios.

Problem

• Optimize power allocation in CF mMIMO
• Design phase shifts for SIM integration
• Maximize spectral efficiency with MARL algorithm

Innovation

• Stacked intelligent metasurfaces integration
• Multi-agent reinforcement learning algorithm
• Centralized training decentralized execution