@article{lopes_nahum_dreifuerst_batista_klautau_cardoso_heath jr_2022, title={Deep Reinforcement Learning-Based Scheduling for Multiband Massive MIMO}, volume={10}, ISSN={["2169-3536"]}, DOI={10.1109/ACCESS.2022.3224808}, abstractNote={Fifth-generation (5G) cellular communication systems have embraced massive multiple-input-multiple-output (MIMO) in the low- and mid-band frequencies. In a multiband system, the base station can serve different users in each band, while the user equipment can operate only in a single band simultaneously. This paper considers a massive MIMO system where channels are dynamically allocated in different frequency bands. We treat multiband massive MIMO as a scheduling and resource allocation problem and propose deep reinforcement learning (DRL) agents to perform user scheduling. The DRL agents use buffer and channel information to compose their observation space, and the agent’s reward function maximizes the transmitted throughput and minimizes the packet loss rate. We compare the proposed DRL algorithms with traditional baselines, such as maximum throughput and proportional fairness. The results show that the DRL models outperformed baselines obtaining a 20% higher network sum rate and an 84% smaller packet loss rate. Moreover, we compare different DRL algorithms focusing on training time to assess the online implementation of the DRL agents, showing that the best agent needs about 50K training steps to converge.}, journal={IEEE ACCESS}, author={Lopes, Victor Hugo L. and Nahum, Cleverson Veloso and Dreifuerst, Ryan M. and Batista, Pedro and Klautau, Aldebaro and Cardoso, Kleber Vieira and Heath Jr, Robert W.}, year={2022}, pages={125509–125525} }
 @article{dreifuerst_heath_yazdan_2022, title={Massive MIMO Beam Management in Sub-6 GHz 5G NR}, DOI={10.1109/VTC2022-Spring54318.2022.9860458}, abstractNote={Beam codebooks are a new feature of massive multiple-input multiple-output (M-MIMO) in 5G new radio (NR). Codebooks comprised of beamforming vectors are used to transmit reference signals and obtain limited channel state information (CSI) from receivers via the codeword index. This enables large arrays that cannot otherwise obtain sufficient CSI. The performance, however, is limited by the codebook design. In this paper, we show that machine learning can be used to train site-specific codebooks for initial access. We design a neural network based on an autoencoder architecture that uses a beamspace observation in combination with RF environment characteristics to improve the synchronization signal (SS) burst codebook. We test our algorithm using a flexible dataset of channels generated from QuaDRiGa. The results show that our model outperforms the industry standard (DFT beams) and approaches the optimal performance (perfect CSI and singular value decomposition (SVD)-based beamforming), using only a few bits of feedback.}, journal={2022 IEEE 95TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2022-SPRING)}, author={Dreifuerst, Ryan M. and Heath, Robert W., Jr. and Yazdan, Ali}, year={2022} }
 @article{dreifuerst_heath_2022, title={SignalNet: A Low Resolution Sinusoid Decomposition and Estimation Network}, volume={70}, ISSN={["1941-0476"]}, DOI={10.1109/TSP.2022.3201336}, abstractNote={The detection and estimation of sinusoids is a fundamental signal processing task for many applications related to sensing and communications. While algorithms have been proposed for this setting, quantization is a critical, but often ignored modeling effect. In wireless communications, estimation with low resolution data converters is relevant for reduced power consumption in wideband receivers. Similarly, low resolution sampling in imaging and spectrum sensing allows for efficient data collection. In this work, we propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples. We incorporate signal reconstruction internally as domain knowledge within the network to enhance learning and surpass traditional algorithms in mean squared error and Chamfer error. We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions. This threshold provides insight into why neural networks tend to outperform traditional methods and into the learned relationships between the input and output distributions. In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data. We use the learning threshold to explain, in the one-bit case, how our estimators learn to minimize the distributional loss, rather than learn features from the data.}, journal={IEEE TRANSACTIONS ON SIGNAL PROCESSING}, author={Dreifuerst, Ryan M. and Heath, Robert W., Jr.}, year={2022}, pages={4454–4467} }