SHShuyan Hu

Shuyan Hu

*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


Shuyan Hu has a total of 48 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Hierarchical Attention-Driven Multi-Agent Reinforcement Learning for Resource Allocation in Cell-Free Massive MIMO With Integrated Sensing and Communication

    by Ming Jiang, Erwu Liu, Wei Ni, Rui Wang, Shuyan Hu, Lingzhi Xia, Yuanzhe Geng, Dusit Niyato, Abbas Jamalipour

    Cell-Free massive MIMO (CF mMIMO), as a cornerstone for future wireless communication networks, can significantly enhance spectral efficiency, reduce energy consumption, and achieve seamless coverage. This paper investigates dynamic resource allocation in CF mMIMO systems provisioning integrated sensing and communication (ISAC) and involving multiple users and heterogeneous services. To address the rapidly varying channels, high complexity, task-dependent relevance and insufficient information sharing among access points (APs) arising from ISAC requirements, we propose a novel Hierarchical Attention-Driven Multi-Agent Reinforcement Learning (HADMARL) framework. A higher-layer “Commander Controller” outputs the AP-user pairing matrix, which is passed to a lowerlayer “Worker Controller” that leverages the central attention mechanism to perform fine-grained resource allocation. Simulations demonstrate that HAD-MARL achieves about a 10% improvement in system utility score compared to benchmarks, with the performance gains becoming more pronounced as the number of APs and users increases. We empirically demonstrate and visualize the effect of the central attention mechanism on the formation of efficient collaboration among APs. The source code is available at: https://github.com/Andyyy2000/HAD.git.


  • Integrated Sensing, Communication, and Computing With Max-Min Fairness

    by Chao Sun, Shuyan Hu, Wei Ni, Chunshan Liu, Xin Wang

    Integrated sensing, communication, and computation (ISC2) has been increasingly studied to support high-precision sensing and low-latency computing. Fairness in ISC2 remains unaddressed due to the non-convexity introduced by local computing, task offloading, result delivery, and sensing. This paper develops a new approach to max-min fair task computing while ensuring target sensing demands in ISC2 systems, by holistically optimizing the beamformers of the base station (BS), the transmit powers and CPU frequencies of users (UEs), and the uplink and downlink durations. To solve this non-convex problem, we develop a new algorithm that judiciously decouples the problem into manageable steps, leveraging Rayleigh quotient maximization, semidefinite relaxation (SDR), and successive convex approximation. We rigorously prove the (local) optimality of the algorithm by proving the tightness of the SDR, i.e., a rank-one solution for the dual-purpose beamforming of the BS for both communication and sensing, and the corresponding sensing-only beamforming, can always be constructed from a solution without rank constraint. Moreover, we reveal the optimal structure of the transmit powers of the BS and UEs, the CPU frequencies of the UEs, and the attainability of absolute fairness. As corroborated numerically, our algorithm substantially outperforms its alternatives in task completion and fairness.

  • Resilience and Failure Analysis in Next-Generation Communication Networks: A Contemporary Survey

    by Siguo Bi, Xin Yuan, Shuyan Hu, Kai Li, Wei Ni, Ekram Hossain, Xin Wang

    This paper provides a comprehensive exploration of network resilience in next-generation (xG) cellular communication infrastructures. It begins with an introduction to the network science framework and its relevance to modern communication systems, and then delves into the theoretical foundations of network resilience, including key concepts from graph theory, complex network analysis, and cascading failure models. A detailed examination of network failures in xG networks follows, employing graph-theoretic approaches to analyze failure propagation, identify critical nodes, and assess network vulnerabilities. The paper also outlines practical methodologies for enhancing resilience, such as adaptive topology design, failure prediction, and decentralized architectural frameworks. The paper further discusses future research directions, emphasizing emerging challenges and opportunities in network resilience. It also reviews ongoing standardization efforts aimed at integrating network science principles into communication infrastructure design. Lessons learned and open challenges are summarized that require further investigation, making it a valuable resource for researchers, engineers, and practitioners seeking to advance the resilience and adaptability of xG networks.


  • Trajectory Planning and Transmission Scheduling for UAV-Borne RIS Assisted Energy-Efficient Uplink Transmissions

    by Yanxin Ye, Shuyan Hu, Wei Ni, Xin Wang

    Mounted on an uncrewed aerial vehicle (UAV), UAV-borne reconfigurable intelligent surfaces (RISs) can enjoy flexibility with a considerable probability of line-of-sight (LoS) channels, and assist communications between terrestrial nodes. Challenges arise in designing UAV-borne RIS (U-RIS) assisted communications, such as the influence of non-LoS, dynamic RIS configuration, and energy consumption of the UAV. To tackle these challenges, we put forth a new U-RIS assisted uplink transmission framework, in which the direct links from the ground users to the corresponding ground base station are blocked. We optimize the energy efficiency of the network by collectively devising the RIS configuration, user scheduling, power allocation, and UAV trajectory, under a probabilistic LoS channel model. Through alternating optimization and successive convex approximation, an efficient approach is established. Simulations validate that our approach is able to significantly enhance energy efficiency by 78% in comparison with its benchmarks.


  • Toward Quantum-Native Communication Systems: State-of-the-Art, Trends, and Challenges

    by Xiaolin Zhou, Anqi Shen, Shuyan Hu, Wei Ni, Xin Wang, Ekram Hossain

    The potential synergy between quantum communications and future wireless communication systems is explored. By proposing a quantum-native or quantum-by-design philosophy, the survey examines technologies such as quantumdomain (QD) multi-input multi-output, QD non-orthogonal multiple access, quantum secure direct communication, QD resource allocation, QD routing, and QD artificial intelligence. The recent research advances in these areas are summarized. Given the behavior of photonic and particle-like Terahertz (THz) systems, a comprehensive system-oriented perspective is adopted to assess the feasibility of using quantum communications in future systems. This survey also reviews quantum optimization algorithms and quantum neural networks to explore the potential integration of quantum communication and quantum computing in future systems. Additionally, the current status of quantum sensing, quantum radar, and quantum timing is briefly reviewed in support of future applications. The associated research gaps and future directions are identified, including extending the entanglement coherence time, developing THz quantum communications devices, addressing challenges in channel estimation and tracking, and establishing the theoretical bounds and performance tradeoffs of quantum communication, computing, and sensing. This survey offers a unique perspective on the potential for quantum communications to revolutionize future systems and pave the way for even more advanced technologies.


  • Differentially Private Wireless Federated Learning With Integrated Sensing and Communication

    by Shuyan Hu, Xin Yuan, Wei Ni, Xin Wang, Ekram Hossain, H. Vincent Poor

    This paper develops a novel framework for differentially private (DP) wireless federated learning (FL) with integrated sensing and communication (ISAC). In this framework, which is referred to as DP-ISAC-FL, wireless devices sense data and upload the trained local models using ISAC technique. The local training can take place concurrently with sensing at each device. We analyze the convergence upper bound of DP-ISAC-FL and rigorously capture the impact of device selection (for model training), time allocation between sensing/training and model uploading for the selected devices, and the allocations of channels, modulations, and transmit powers. We also develop an algorithm that enforces the convergence of DP-ISAC-FL by minimizing the convergence upper bound in an OFDMA system with discrete modulations. The beamforming for sensing, device selection, and the allocations of time, subchannels, modulations, and transmit powers are jointly optimized using successive convex approximation (SCA), adapting to the channels and computing capabilities of the devices. Experiments on multilayer perceptrons (MLPs) and convolutional neural networks (CNNs) show that DP-ISAC-FL with optimal allocations can significantly improve the learning convergence and accuracy under different privacy levels, e.g., by 7% and 18%, compared with its benchmarks. This is attributed to 68% more sensing data that DP-ISAC-FL can admit for model training.


  • Proximal Policy Optimization With Adaptive Weight Adjustment for Airborne Integrated Sensing and Communication

    by Shihang Zhang, Chao Sun, Shuyan Hu, Wei Ni, Xin Wang

    Integrated sensing and communication (ISAC) technology has emerged as a potential enabler for efficient data transmission and sensing in unmanned aerial vehicle (UAV) networks. In this letter, we investigate a UAV-ISAC system, where a UAV furnishes downlink communication and simultaneous sensing for mobile ground nodes (GNs). To address this non-convex optimization problem and prevent retraining required due to dynamic environments, we design a new proximal policy optimization (PPO)-based approach that jointly optimizes the UAV trajectory and resource assignment while guaranteeing the required throughput, sensing fairness (SF) and age of information (AoI) among GNs. We integrate a new adaptive reward weight adjustment (ARWA) mechanism into the PPO framework to guide the UAV operations dynamically. Simulations corroborate that the proposed ARWA-PPO scheme can ameliorate the system throughput by 12% and increase the minimum GN throughput by 19%, compared to the existing baselines, including PPO.


  • Energy-Efficient Resource Allocation for Multi-User Semantic Communications: A Deep Reinforcement Learning Approach

    by Xiaojing Chen, Jia Xu, Wei Ni, Shuyan Hu, Zhijin Qin, Shunqing Zhang

    Effective resource allocation is critical to the efficiency of semantic communications, especially when faced with limited energy supplies and constrained communication resources. The unique requirements of semantic communications have brought new challenges to the joint optimization of energy and communication resources. This paper presents a novel deep reinforcement learning (DRL)-based algorithm to maximize the long-term average semantic energy efficiency (S-EE) for energy harvesting-powered semantic communication systems. Particularly, the Multi-discrete Proximal Policy Optimization (MPPO) is applied to determine discrete actions, including channel allocation and the number of semantic symbols, while the Deep Deterministic Policy Gradient (DDPG) is employed to learn continuous transmit powers. MPPO uses multiple heads to cope with multi-discrete actions, thereby reducing the output dimension of actions. Simulation results indicate that the proposed algorithm achieves faster convergence and enhances S-EE by 31.6%, compared to its benchmarks.