SHShengqian Han

Shengqian Han

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shengqian Han has a total of 59 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Measured Energy Consumption for AI-Based Precoding

    by Pengyu Cong, Chenyang Yang, Shengqian Han, Nan Li, Qi Sun

    This paper presents the first measurement-based study on the energy consumption of artificial intelligence (AI) algorithms for radio access networks (RAN), aiming to investigate whether the integration of AI leads to higher energy consumption than traditional non-AI algorithms. We use the multiuser precoding problem as a representative example, where AI is widely recognized for its potential in supporting the growing deployment of antennas for 6G systems. Our assessment examines three AI algorithms using the convolutional neural network (CNN), edge graph neural network (EGNN), and communication model-based graph neural network (MGNN), in comparison with two non-AI algorithms, specifically the weighted minimum mean square error (WMMSE) and regularized zero-forcing (RZF) algorithms. Through extensive measurements of energy and power consumption, we examine how efficient architecture designs of deep neural networks (DNNs) affect energy consumptions, and provide a quantitative comparison between measured results and estimates from existing power estimation models. The results indicate that the MGNN, which is the most efficient architecture among the three DNNs, consumes substantially less energy than the non-AI algorithms for large-scale systems, while the CNN consumes significantly more energy for both training and inference compared to the MGNN. Moreover, utilizing GPUs does not always lead to higher power consumption compared to CPUs, the power consumption of CPUs should be taken into account when GPUs are used, and DRAM contributes little to total power consumption. We demonstrate the shortcomings of existing utilization-based and FLOPs-based models in estimating energy consumption, calling for the development of more accurate models to facilitate green AI designs for RAN.


  • Implicit Neural Representation of Beamforming for Continuous Aperture Array Systems

    by Shiyong Chen, Jia Guo, Shengqian Han

    In this paper, a learning-based approach is proposed for optimizing downlink beamforming in multiple-input multiple output (MIMO) systems that employ continuous aperture arrays (CAPAs) at both the base station (BS) and the user. Beamforming in such systems is a spatially continuous function that maps a coordinate on the CAPA to a corresponding beamforming weight. We first propose an implicit neural representation (INR), termed BeaINR, to parameterize this function directly. Further, noting that the optimal beamforming function can be expressed as a weighted integral of the channel response function, we propose a second INR, CoefINR, to represent the weighting coefficient function, which indirectly optimizes the beamforming function. Simulation results show that the proposed INR-based methods achieve comparable or higher spectral efficiency (SE) than the considered baselines, while requiring substantially lower inference latency, Moreover, CoefINR reduces training complexity and improves frequency generalizability relative to BeaINR by leveraging the optimal beamforming structure.


  • Over-the-Air Transmission Aided Distributed Resource Block Allocation for Wideband Cell-Free Systems

    by Yang Ma, Shengqian Han

    Distributed resource allocation is a pivotal and challenging problem for cell-free systems, where a large number of access points (APs) cooperate to serve user equipments (UEs). Compared to centralized optimization that suffers from pro hibitive computational complexity and huge fronthaul overhead, distributed methods offer a desirable alternative for practical deployment. This paper studies distributed resource block (RB) allocation in cell-free orthogonal frequency-division multiplexing (OFDM) systems. We first propose a distributed sequential algorithm along with an over-the-air (OTA) transmission scheme for optimizing RB allocation, where each AP locally updates decisions using the information obtained through OTA transmissions between APs and UEs. To achieve fast convergence and reduce the OTA transmission overhead, a clustering-based variant of the sequential algorithm is developed. To alleviate the estimation error of the information acquired via OTA transmission caused by pilot contamination and noise, we further propose a distributed deep learning-based method (DDM) to jointly optimize pilot allocation and RB allocation based on the proposed distributed algorithms. Simulation results demonstrate that the proposed distributed al gorithms perform close to the centralized algorithm under perfect OTA transmission. The proposed DDM significantly outperforms existing distributed baseline methods, indicating that the DDM effectively mitigates the impact of estimation error and reduces the overhead associated with OTA transmission. Moreover, the DDMexhibits good generalizability to different numbers of APs, UEs, and RBs as well as different channel distributions.

  • Gradient-Driven Graph Neural Networks for Learning Digital and Hybrid Precoder

    by Lin Zhang, Shengqian Han, Chenyang Yang

    The optimization of multi-user multi-input multi-output (MU-MIMO) precoders is a widely recognized challenging problem. In this paper, we develop a gradient-driven GNN design method for the learning of fully digital and hybrid precoding policies. The proposed GNNs leverage two kinds of knowledge, namely the gradient of signal-to-interference-plus-noise ratio (SINR) to the precoders and the permutation equivariant property of the precoding policy. To demonstrate the flexibility of the proposed method for accommodating different optimization objectives and different precoding policies, we first apply the proposed method to learn the fully digital precoding policies. We study two precoder optimization problems for spectral efficiency (SE) maximization and log-SE maximization to achieve proportional fairness. We then apply the proposed method to learn the hybrid precoding policy, where the gradients to analog and digital precoders are harnessed for the design of the GNN. Simulation results show the effectiveness of the proposed methods in achieving good performance with low inference complexity, particularly for large-scale systems, and demonstrate superior generalization to the numbers of both users and antennas compared to the baseline GNNs.

  • Learning Wideband User Scheduling and Hybrid Precoding With Graph Neural Networks

    by Shengjie Liu, Chenyang Yang, Shengqian Han

    User scheduling and hybrid precoding in wideband multi-antenna systems have never been learned jointly due to the challenges arising from the massive user combinations on resource blocks (RBs) and the shared analog precoder among RBs. In this paper, we strive to jointly learn the scheduling and precoding policies with graph neural networks (GNNs), which have emerged as a powerful tool for optimizing resource allocation thanks to their potential in generalizing across problem scales. By reformulating the joint optimization problem into an equivalent functional optimization problem for the scheduling and precoding policies, we propose a GNN-based architecture consisting of two cascaded modules to learn the two policies. We discover a same-parameter same-decision (SPSD) property for wireless policies defined on sets, revealing that a GNN cannot well learn the optimal scheduling policy when users have similar channels. This motivates us to develop a sequence of GNNs to enhance the scheduler module. Furthermore, by analyzing the SPSD property, we find when linear aggregators in GNNs impede size generalization. Based on the observation, we devise a novel attention mechanism for information aggregation in the precoder module. Simulation results demonstrate that the proposed architecture achieves satisfactory spectral efficiency with short inference time and low training complexity, and is generalizable to the numbers of users, RBs, and antennas at the base station and users.


  • Quantization Design for Deep Learning-Based CSI Feedback

    by Manru Yin, Shengqian Han, Chenyang Yang

    Deep learning-based autoencoders have been employed to compress and reconstruct channel state information (CSI) in frequency-division duplex systems. Practical implementations require judicious quantization of encoder outputs for digital transmission. In this paper, we propose a novel quantization module with bit allocation among encoder outputs and develop a method for joint training the module and the autoencoder. To enhance learning performance, we design a loss function that adaptively weights the quantization loss and the logarithm of reconstruction loss. Simulation results show the performance gain of the proposed method over existing baselines.


  • Open Access

    Optimizing QoE-Privacy Tradeoff for Proactive VR Streaming

    by Xing Wei, Shengqian Han, Chenyang Yang, Chengjian Sun

    Proactive virtual reality (VR) streaming requires users to upload viewpoint-related information, raising significant privacy concerns. Existing strategies preserve privacy by introducing errors to viewpoints, which, however, compromises the quality of experience (QoE) of users. In this paper, we first delve into the analysis of the viewpoint leakage probability achieved by existing privacy-preserving approaches. We determine the optimal distribution of viewpoint errors that minimizes the viewpoint leakage probability. Our analyses show that existing approaches cannot fully eliminate viewpoint leakage. Then, we propose a novel privacy-preserving approach that introduces noise to uploaded viewpoint prediction errors, which can ensure zero viewpoint leakage probability. Given the proposed approach, the tradeoff between privacy preservation and QoE is optimized to minimize the QoE loss while satisfying the privacy requirement. Simulation results validate our analysis results and demonstrate that the proposed approach offers a promising solution for balancing privacy and QoE.

  • Open Access

    Precoder Learning by Leveraging Unitary Equivariance Property

    by Yilun Ge, Shuyao Liao, Shengqian Han, Chenyang Yang

    Incorporating mathematical properties of a wireless policy to be learned into the design of deep neural networks (DNNs) is effective for enhancing learning efficiency. Multi-user precoding policy in multi-antenna system, which is the mapping from channel matrix to precoding matrix, possesses a permutation equivariance property, which has been harnessed to design the parameter sharing structure of the weight matrix of DNNs. In this paper, we study a stronger property than permutation equivariance, namely unitary equivariance, for precoder learning. We first show that a DNN with unitary equivariance designed by further introducing parameter sharing into a permutation equivariant DNN is unable to learn the optimal precoder. We proceed to develop a novel non-linear weighting process satisfying unitary equivariance and then construct a joint unitary and permutation equivariant DNN. Simulation results demonstrate that the proposed DNN not only outperforms existing learning methods in learning performance and generalizability but also reduces training complexity.