More Like this

1. A Deep Reinforcement Learning-Based Resource Scheduler for Massive MIMO Networks

   An, Qing; Segarra, Santiago; Dick, Chris; Sabharwal, Ashutosh; Doost-Mohammady, Rahman (September 2023, IEEE transactions on machine learning in communications and networking)

   The large number of antennas in massive MIMO systems allows the base station to communicate with multiple users at the same time and frequency resource with multi-user beamforming. However, highly correlated user channels could drastically impede the spectral efficiency that multi-user beamforming can achieve. As such, it is critical for the base station to schedule a suitable group of users in each time and frequency resource block to achieve maximum spectral efficiency while adhering to fairness constraints among the users. In this paper, we consider the resource scheduling problem for massive MIMO systems with its optimal solution known to be NP-hard. Inspired by recent achievements in deep reinforcement learning (DRL) to solve problems with large action sets, we propose \name{}, a dynamic scheduler for massive MIMO based on the state-of-the-art Soft Actor-Critic (SAC) DRL model and the K-Nearest Neighbors (KNN) algorithm. Through comprehensive simulations using realistic massive MIMO channel models as well as real-world datasets from channel measurement experiments, we demonstrate the effectiveness of our proposed model in various channel conditions. Our results show that our proposed model performs very close to the optimal proportionally fair (Opt-PF) scheduler in terms of spectral efficiency and fairness with more than one order of magnitude lower computational complexity in medium network sizes where Opt-PF is computationally feasible. Our results also show the feasibility and high performance of our proposed scheduler in networks with a large number of users and resource blocks. 

   more » « less
2. A Deep Reinforcement Learning-Based Resource Scheduler for Massive MIMO Networks

   Qing An; Santiago Segarra; Chris Dick; Ashutosh Sabharwal; Rahman Doost-Mohammady (September 2023, IEEE transactions on machine learning in communications and networking)

   The large number of antennas in massive MIMO systems allows the base station to communicate with multiple users at the same time and frequency resource with multi-user beamforming. However, highly correlated user channels could drastically impede the spectral efficiency that multi-user beamforming can achieve. As such, it is critical for the base station to schedule a suitable group of users in each time and frequency resource block to achieve maximum spectral efficiency while adhering to fairness constraints among the users. In this paper, we consider the resource scheduling problem for massive MIMO systems with its optimal solution known to be NP-hard. Inspired by recent achievements in deep reinforcement learning (DRL) to solve problems with large action sets, we propose SMART, a dynamic scheduler for massive MIMO based on the state-of-the-art Soft Actor-Critic (SAC) DRL model and the K-Nearest Neighbors (KNN) algorithm. Through comprehensive simulations using realistic massive MIMO channel models as well as real-world datasets from channel measurement experiments, we demonstrate the effectiveness of our proposed model in various channel conditions. Our results show that our proposed model performs very close to the optimal proportionally fair (Opt-PF) scheduler in terms of spectral efficiency and fairness with more than one order of magnitude lower computational complexity in medium network sizes where Opt-PF is computationally feasible. Our results also show the feasibility and high performance of our proposed scheduler in networks with a large number of users and resource blocks. 

   more » « less
3. Doubly 1-Bit Quantized Massive MIMO

   https://doi.org/10.1109/IEEECONF59524.2023.10476782  

   Atzeni, Italo; Tölli, Antti; Nguyen, Duy_H N; Swindlehurst, A Lee (October 2023, IEEE)

   Enabling communications in the (sub-)THz band will call for massive multiple-input multiple-output (MIMO) arrays at either the transmit- or receive-side, or at both. To scale down the complexity and power consumption when operating across massive frequency and antenna dimensions, a sacrifice in the resolution of the digital-to-analog/analog-to-digital converters (DACs/ADCs) will be inevitable. In this paper, we analyze the extreme scenario where both the transmit- and receive-side are equipped with fully digital massive MIMO arrays and 1-bit DACs/ADCs, which leads to a system with minimum radio-frequency complexity, cost, and power consumption. Building upon the Bussgang decomposition, we derive a tractable approximation of the mean squared error (MSE) between the transmitted data symbols and their soft estimates. Numerical results show that, despite its simplicity, a doubly 1-bit quantized massive MIMO system with very large antenna arrays can deliver an impressive performance in terms of MSE and symbol error rate. 

   more » « less
4. Design Trade-offs for Decentralized Baseband Processing in Massive MU-MIMO Systems

   https://doi.org/10.1109/IEEECONF44664.2019.9048727  

   Li, Kaipeng; McNaney, James; Tarver, Chance; Castaneda, Oscar; Jeon, Charles; Cavallaro, Joseph R.; Studer, Christoph (November 2019, 2019 IEEE 53rd Asilomar Conference on Signals, Systems and Computers)

   null (Ed.)

   Massive multi-user (MU) multiple-input multiple-output (MIMO) provides high spectral efficiency by means of spatial multiplexing and fine-grained beamforming. However, conventional base-station (BS) architectures for systems with hundreds of antennas that rely on centralized baseband processing inevitably suffer from (i) excessive interconnect data rates between radio-frequency circuitry and processing fabrics, and (ii) prohibitive complexity at the centralized baseband processor. Recently, decentralized baseband processing (DBP) architectures and algorithms have been proposed, which mitigate the interconnect bandwidth and complexity bottlenecks. This paper systematically explores the design trade-offs between error-rate performance, computational complexity, and data transfer latency of DBP architectures under different system configurations and channel conditions. Considering architecture, algorithm, and numerical precision aspects, we provide practical guidelines to select the DBP architecture and algorithm that are able to realize the full benefits of massive MU-MIMO in the uplink and downlink. 

   more » « less
5. Energy efficient downlink massive MIMO: Is 1-bit quantization a solution ?

   https://doi.org/10.1109/ISWCS.2019.8877256  

   Marcastel, Alexandre; Fijalkow, Inbar; Swindlehurst, Lee (August 2019, Proc. 16th International Symposium on Wireless Communication Systems (ISWCS))

   Massive MIMO aims to build wireless base stations with hundreds of coherently operating antennas serving tens of single antenna users in order to improve both the transmission capacity by a factor 10-50 and the energy-efficiency trade-off by up to a thousand times. Pre-coding at the base station has been proposed to efficiently implement digital beamforming. It implies a high signal dynamic range and therefore a power backoff resulting in less energy-efficiency. One-bit quantized Zero-Forcing precoding has been proposed to efficiently handle the RF front-end when the array is implemented with so many antennas. In this paper, we analyze the energy-efficiency of the quantized Zero-Forcing precoded systems for a large number of users and a massive MIMO base station. 

   more » « less