FSFei Shen

Fei Shen

*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


Fei Shen has a total of 64 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • IRET: IRS-Assisted Energy-Delay Incentive-Aware Transmission for Future Interplanetary Network

    by Chengcheng Lv, Fei Shen, Feng Yan, Zhiyong Bu, Yanli Xu

    The Earth–Moon interplanetary network (IPN) is a critical infrastructure for future lunar exploration, enabling real-time data transmission between lunar sensors and Earth-based clients. However, its extreme transmission distance, limited onboard resources, and the selfish behavior of heterogeneous participants pose significant challenges in achieving energy-efficient and low-latency communication. To address these issues, in this article, a real-time Earth–Moon IPN is proposed to transmit lunar data to the Earth for processing. Due to the great distance between the Earth and the Moon, intelligent reflecting surfaces (IRSs) are deployed on the relay satellites (RSs) within the network to enhance signal strength and improve data transmission efficiency. Besides, building the Earth–Moon IPN will require substantial communication and satellite resources. To encourage Earth clients (ECs) and satellites to actively participate in data transmission, an incentive mechanism that allocates rewards based on the volume of the transmitted data is proposed and modeled as a Stackelberg game. Based on the game, the utility optimization problem of energy delay between satellites and ECs is solved. To improve the Earth–Moon transmission efficiency, an IRS-assisted energy-delay-aware transmission (IRET) algorithm is proposed. Intensive simulations show that compared to other IRS-assisted algorithms, the IRET algorithm can reduce transmit power by 0.5–3 dBW, shorten transmission delay by 20%–80%, improve EC utility by 20%–80%, and enhance satellite utility by 10%–70%. The results demonstrate that the proposed framework offers a scalable and incentive-compatible solution for future Internet of Space Things (IoST) networks.

  • PAD-STT: A Pre-Denoising Adaptive Decomposition Spatial–Temporal Transformer for Cellular Traffic Prediction

    by Geng Chen, Xiantao Du, Fei Shen, Qingtian Zeng, Yu-Dong Zhang

    Accurate prediction of cellular traffic is essential for enabling intelligent networks. However, this requires effectively capturing the dynamic variations within the traffic. Thus, we propose a Pre-Denoising Adaptive Decomposition Spatial-Temporal Transformer (PAD-STT). First, to mitigate noise interference in sequence decomposition, we apply a Savitzky–Golay filter for pre-denoising. Second, a dual-correlation mechanism is designed based on cross-correlation theory, enabling PAD-STT to perform synchronized modeling by jointly learning spatial and temporal relationships rather than in a sequential manner. Finally, we develop an adaptive decomposition to replace the original moving average, aiming to effectively capture dynamic variations. Experiments on real-world datasets demonstrate that PAD-STT outperforms representative state-of-the-art methods.


  • Dynamic Topology Control Strategy for LEO Mega-constellation Networks

    by Haojian Nie, Feng Yan, Fei Shen, Jun Zheng, Weiwei Xia, Lianfeng Shen

    With the development of mobile communications, low earth orbit (LEO) mega-constellation networks (MCNs) have become an essential part to support future 6G and Internet-of-Things (IoT). In LEO MCNs, topology control strategy play an important role in providing low latency as well as high energy efficiency, and has become a hot research topic. In this paper, we introduce dynamic cross-orbit links and investigate the dynamic topology control (DTC) problem in laser inter-satellite links (LISLs)-based MCNs. Firstly, we propose a practical dynamic link establishment model which considers several factors of cross-orbit links, such as the maximum communication distance between satellites, terminal alignment requirements and the duration of a LISL. Then, the DTC problem is formulated as an NP-hard binary integer programming problem aiming to minimize the average hop count and the number of dynamic LISLs. Furthermore, a heuristic bi-directional velocity discrete particle swarm optimization algorithm is developed to solve the above problem. Finally, simulation results show that our proposed dynamic topology control strategy can significantly decrease the average hop count and the number of LISLs compared with other baseline strategies. In particular, compared with Grid+, these metrics are reduced by roughly 42% and 13% respectively. This can provide us with some insights that using cross-orbit links in a DTC strategy can significantly improve the performance of LEO MCNs.


  • Phased Spatial–Temporal Targeted Networks Based on Transformer and Data Augmentation for Cellular Traffic Prediction

    by Geng Chen, Xiantao Du, Fei Shen, Qingtian Zeng, Yu-Dong Zhang

    Accurate cellular traffic prediction is crucial for the rational allocation of network resources. Existing methods generally overlook the accurate extraction and full utilization of features across different periods of cellular traffic. Thus, we propose a relatively long short-term adaptive spatial–temporal targeted extraction (RLSASTTE) network, which fully extracts long-term trends and short-term dynamics, and then maximizes their utilization. First, to extract long-term spatial–temporal features, we exploit the strength of the Transformer in capturing long-range temporal dependencies, address its limitations in spatial relationship modeling by redesigning a spatial–temporal attention mechanism (STAM), and further adopt a predecomposition strategy to emphasize seasonal component mining. Second, to capture short-term spatial–temporal features, we define a multidilation convolution to explore short-term dependencies and design a novel local strong correlation dynamic attention (LSCDA) mechanism to investigate local spatial influences, which also eliminates the limitation of fixed neighboring nodes. Finally, we innovatively employ an adaptive dual gating mechanism (ADGM) to efficiently integrate diverse features. We conducted experiments on three real-world datasets. Compared to the state-of-the-art methods, RLSASTTE achieves reductions of at least 3.1% and 3.7% in mean absolute error (MAE) and root mean square error (RMSE), respectively. In addition, we explore auxiliary training based on data augmentation, achieving additional performance improvements of 2.0%–4.5%.


  • Mitigating Priority Inversion in Non-Preemptive Rigid Gang Scheduling Beyond Work-Conserving

    by Yonghui Liang, Hui Li, Qimin Xu, Fei Shen, Shanying Zhu, Xinping Guan

    Rigid gang scheduling, which enables multiple threads of real-time tasks to execute concurrently on a fixed number of different processors, has recently gained attention. Compared to preemptive rigid gang scheduling, non-preemptive rigid gang (NPRG) scheduling improves predictability by requiring fewer context switches. However, NPRG scheduling is vulnerable to 2D-blocking, where lower-priority tasks can block a higher-priority task multiple times, leading to severe priority inversion at runtime and pessimism in schedulability analysis. The root cause is the work-conserving execution behavior, in which tasks are immediately executed whenever the required processors are idle, regardless of priority and the potential blocking of subsequent tasks. This paper focuses on the global fixed-priority NPRG scheduling and introduces the NPRG-SS scheduler. NPRG-SS leverages a selective stalling (SS) mechanism that selectively stalls lower-priority jobs whenever their execution could delay the start time of a higher-priority job in the ready queue. This non-work-conserving approach inherently mitigates multiple blocking. Additionally, we present the first schedulability analysis for NPRG scheduling with SS and propose a novel heuristic priority assignment technique, Iterative Priority Refinement (IPR). Experimental results show that NPRG-SS with IPR effectively mitigates priority inversion, accepts up to 42% more task sets than the baselines at runtime, while our proposed schedulability test accepts up to 80% more task sets than the baselines in worst-case scenarios.

  • Multi-Agent Reinforcement Learning Based Idle-Aware Task Offloading in Dynamic Vehicular Networks With Partial Information

    by Jing Zhang, Fei Shen, Feng Yan, Jie Li

    Edge computing provides low-latency computational services for task offloading in vehicular networks. However, challenges such as dynamic transmission rates, resource limitations, and information-sharing constraints impede efficient offloading. Few studies address these issues concurrently in designing dynamic offloading strategies, often resulting in sub-optimal system utility. This paper aims to achieve efficient vehicular task offloading via an idleness-aware edge server (ES) from a game theory perspective. We propose a Gated Recurrent Unit (GRU) prediction model with an attention mechanism to guide vehicles to the nearest idle ES. The offloading decision process is modeled as a stochastic game, proving the existence of a Nash equilibrium (NE). Additionally, we model it as a multi-agent partially observable Markov decision process (POMDP) to account for limited information access among vehicles. To solve the POMDP and achieve near-optimal NE, we introduce a Multi-Agent Reinforcement Learning-based Task Offloading (MATO) algorithm, combining a Differentiable Neural Computer (DNC) and an Advantageous Actor-Critic (A2C) framework. The DNC’s external memory stores structured representations of past information, enabling deeper exploration of the strategy space. Adjusting the reward representation enhances training efficiency. Experimental results driven by real-world datasets demonstrate that MATO effectively improves the computing offloading utility while increasing the convergence speed compared to existing schemes.


  • Edge Collaborative Caching Based on Incentive-Driven D3QN Combined With User Preferences in UAV-Assisted Vehicular Networks

    by Geng Chen, Yuchen Han, Fei Shen, Qingtian Zeng, Yu-Dong Zhang

    Mobile Edge Cache allows CDN edge nodes to be deployed closer to users, reducing content transmission latency in Vehicular Networks (VANETs). However, how to effectively utilize the limited storage space of cache nodes is the main issue in current research. To address this problem, we propose an incentive-driven hierarchical collaborative caching algorithm based on D3QN combined with user preferences (PC-ID3QN). Firstly, we constructed a UAV-assisted vehicular content-centric network framework, designing different collaborative caching strategy for various layers based on user preferences. Secondly, we proposed a hierarchical incentive mechanism based on social priority to motivate users to participate in collaborative sharing, thereby enhancing the utilization of system caching resources. Next, we modeled the cache placement problem as a system utility maximization problem and proved its NP-hardness. Then, by adjusting the constraint conditions, we conducted theoretical analysis and transform it into a linear programming(LP) problem to obtain an offline theoretical solution. This solution was validated against the simulation optimal solution obtained using the proposed PC-ID3QN algorithm, demonstrating the effectiveness of the algorithm. Finally, we validate the proposed caching strategy using the MovieLens dataset and conduct extensive experiments to verify the applicability and superiority of our solution in improving cache utility. Compared with DDQN, Dueling DQN and DQN, our proposed ID3QN algorithm reduces the request delay by 1.03%,1.73% and 2.21%, and reduces the energy cost by 38.8%, 19.6% and 17.2%, respectively.


  • Parameter Estimation of Target With Angular Spread in the Near Field

    by Mengjiang Sun, Peng Chen, Zhenxin Cao, Fei Shen

    Near-field target parameter estimation with multiple-input multiple-output (MIMO) systems has been extensively explored in existing literature. However, most methods are primarily effective only in passive or non-coherent scenario such as point scatters. In this paper, we consider a scenario where the near-field target expands in angular domain. Echoes originating from closely proximate directions within the angular spread are highly correlated, posing a significant challenge to existing models and algorithms, which may lead to biased estimations. To address the problem, we first build a model to describe the echo from the target with angular spread based on MIMO radar with only four parameters, including central range, central direction, angular spread and spinning angle. We then derive the Cramér-Rao bound (CRB) of parameter estimation in the proposed model and analyze the effect of angular spread and spinning angle on the estimation. An expanded-direction of arrival (DOA) network is proposed to estimate the four parameters in the model. With numerical simulations, we demonstrate the robustness of the model, analyze the limitations inherent in existing algorithms, and substantiate both the effectiveness and superiority of the proposed model and network.

  • Communication and Control Co-Design for Heterogeneous Industrial IoT: A Logic-Based Stochastic Switched System Approach

    by Shuling Wang, Shanying Zhu, Cailian Chen, Fei Shen, Weihai Zhang, Xinping Guan

    With the development of Industry 4.0, mobile agents are deployed to coordinate with multi-loop control systems to perform manufacturing tasks, leading to heterogeneous Internet of Things (IoT). Due to shadow fading induced by the movement of mobile agents, the wireless channel closing the control loops is inherently unreliable, which can compromise the control system performance. This paper addresses the co-design problem of transmission scheduling and agents’ movement to ensure both control performance and energy efficiency. A generalized cyber-physical-agent framework is proposed to capture the coupling between IoT systems and a mobile agent through a state-dependent fading channel. Moreover, the movement of the mobile agent among areas exhibiting different levels of shadow effects is modeled by Markov decision process. To address such heterogeneous dynamics, the co-design problem is formulated into the optimization of a logic-based stochastic switched system by utilizing the semi-tensor product technique. Based on state mergence and H-representation methods, a tractable and effective algorithm is then proposed to design co-design policies, minimizing the average joint cost of communication and control. A parallel scheme is further developed to alleviate the computation burden of the algorithm. Theoretical guarantees are provided to ensure control system performance. Finally, simulation results are given to demonstrate effectiveness of the proposed method.


  • DOGS: Dynamic Task Offloading in Space-Air–Ground Integrated Networks With Game-Theoretic Stochastic Learning

    by Jing Zhang, Jiaxuan Zhang, Fei Shen, Feng Yan, Zhiyong Bu

    The space-air–ground integrated network (SAGIN) integrates satellites, unmanned aerial vehicles (UAVs), and terrestrial remote clouds to provide seamless network access and high-volume computing services for remote Internet of Things (IoT) devices, thus alleviating geographic and resource constraints. Existing methods typically focus on the network dynamics while overlooking the comprehensive consideration of device dynamics, namely, the time-varying task performance weights, task sizes, and task processing demands. Moreover, the centralized learning-based offloading schemes often lead to substantial signaling overhead. To bridge these gaps, this article proposes a distributed dynamic task offloading mechanism with game-theoretic multiagent stochastic learning (MASL). Technically, a stochastic game is formulated with each device as a player minimizing its weighted sum cost of latency and energy. We prove the existence of Nash equilibrium (NE) for our proposed game and propose a multiagent entropy-enhanced stochastic learning (MESL) algorithm in a fully distributed manner with no information exchange among IoT devices. By introducing the entropy of decision probability for each device, MESL increases decision dimensions, accelerates convergence, and facilitates optimal strategy achievement. Experimental results show that the MESL algorithm significantly reduces the overall cost and greatly enhances the convergence speed in dynamic SAGIN environments compared to existing algorithms.