کنفرانس مهندسی برق ایران

صفحه اصلی / سی و چهارمین کنفرانس بین المللی مهندسی برق

Energy-Efficient AP Selection in Downlink Cell-Free Massive MIMO Systems with QoS Guarantees using Deep Reinforcement Learning

نویسندگان :

Saba Samkhaniani¹ Abbas Mohammadi² Amir Mohammad Khoueini³ Sanaz Seyedin⁴

1- Amirkabir University of Technology (Tehran Polytechnic) 2- Amirkabir University of Technology (Tehran Polytechnic) 3- Amirkabir University of Technology (Tehran Polytechnic) 4- Amirkabir University of Technology (Tehran Polytechnic)

کلمات کلیدی :

AP Selection،Deep Reinforcement Learning،Cell-Free Massive MIMO

چکیده :

Abstract— Cell-Free Massive Multiple-Input Multiple-Output (CF-mMIMO) is a key technology for future Sixth Generation (6G) networks. In this paper, we consider the downlink CF-mMIMO system. With a large number of Access Points (APs) and User Equipments (UEs), selecting an efficient subset of APs is crucial for improving Energy Efficiency (EE). To address this challenge, we propose a Deep Reinforcement Learning (DRL) framework based on the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize AP–UE associations while guaranteeing a minimum data rate for each UE. Simulation results show that the proposed approach significantly outperforms conventional schemes such as Delta-AP and All-AP in terms of EE and provides more uniform user data rates. These results demonstrate the effectiveness of DRL-based AP selection for Energy-Efficient downlink CF-mMIMO networks.