Wen Li

Wen Li

Auto-generated profile, based on publicly available information

Wen Li

College of Communications Engineering, Army Engineering University of PLA, Nanjing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 November 2019 in IEEE Access
Verified
Journal Article
Open access
SLSongyi Liu
Songyi Liu
YXYifan Xu
Yifan Xu
XCXueqiang Chen
Xueqiang Chen
XWXiming Wang
Ximing Wang
MWMeng Wang
Meng Wang
YXYuhua Xu
Yuhua Xu
This paper investigates the problem of anti-jamming communication in dynamic and intelligent jamming environment. A sequential deep reinforcement learning algorithm (SDRLA) without prior information is proposed, and raw spectrum information is used as the input of SDRLA. The proposed SDRLA algorithm mainly contains two parts: Firstly, deep learning and sliding window principle are introduced to identify jamming patterns; Secondly, reinforcement learning is carried out to make on-line channel selection based on recognized jamming patterns. In addition, channel switching cost is introduced for the purpose of formulating the trade-off relationship between throughput and overhead. Taking advantage of both deep learning and reinforcement learning, this method can realize rapid and effective anti-jamming channel selection with no need for modeling the jammer's characteristics. Simulation results show the convergence and effectiveness of the proposed SDRLA algorithm. Compared with single-mode reinforcement learning, our approach can reach better convergence performance and higher utility.

1 June 2020 in IEEE Wireless Communications Letters
Verified
Journal Article
Closed access
YLYangyang Li
Yangyang Li
YXYuhua Xu
Yuhua Xu
YXYitao Xu
Yitao Xu
XLXin Liu
Xin Liu
XWXiming Wang
Ximing Wang
AAAlagan Anpalagan
Alagan Anpalagan
In this letter, the frequency selection problem in jamming environment with large number of optional frequencies is investigated. With numerous optional actions in the wider frequency band scenario, most of existing anti-jamming methods will become ineffective, since the convergence time and computational complexity will grow exponentially with the number of actions. To cope with the above challenge, a novel hierarchical deep reinforcement learning algorithm which does not need to know the jamming patterns and channel model is proposed. The proposed algorithm divides the frequency selection problem in the broadband into two steps via two subnetworks: Firstly, the frequency band is selected by the band selection network, and then the specific frequency is selected in this frequency band by the frequency selection network. Simulation results show that the proposed algorithm avoids multiple different jammings effectively and achieves satisfactory throughput with less calculation.

18 May 2021 in IEEE Wireless Communications Letters
Verified
Journal Article
Closed access
HHHao Han
Hao Han
XWXiming Wang
Ximing Wang
FGFanglin Gu
Fanglin Gu
WLWen Li
Wen Li
YCYuan Cai
Yuan Cai
YXYuhua Xu
Yuhua Xu
This letter studies the problem of anti-jamming spectrum access in dynamic and unknown environments with incomplete spectrum sensing information. Most existing studies were based on the assumption that users have perfect spectrum information, thus they worked poorly with incomplete sensing information. To overcome the shortcoming, we present a robust intelligent anti-jamming spectrum access scheme which includes spectrum sensing, completion, learning and access. To complete the missing spectrum data, we design a generative adversarial network (GAN) based spectrum completion network. Based on deep reinforcement learning (DRL), a channel selection network is introduced to choose effective anti-jamming channel access policy. Simulation results show that the proposed approach is able to avoid complex jamming attacks effectively and outperforms conventional DRL-based approach with incomplete spectrum information.

23 August 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YLYangyang Li
Yangyang Li
YXYuhua Xu
Yuhua Xu
GLGuoxin Li
Guoxin Li
YGYuping Gong
Yuping Gong
XLXin Liu
Xin Liu
WLWen Li
Wen Li
The primary objective of anti-jamming techniques is to ensure that the transmitted data arrives at the intended receiver without being disturbed or jammed with by any jamming signal or other hostile activities to ensuring the security of the communication system. Deep reinforcement learning (DRL) has been extensively utilized in solving the dynamic spectrum anti-jamming problem. However, most of existing DRL-based algorithms require lots of training time, which fails to adapt the fast-channging jamming environment. Our objective is to find a practical and fast-convergence anti-jamming learning solution. To achieve this, we redesign the DRL algorithm in the following two ways. First, we split the cycle of reinforcement learning into two parts: applying process and training process. Second, we use soft labels instead of rewards which bring more information. We further theoretically show that the information gain can help our proposed algorithm converge faster. Moreover, we also show that our labeled DRL algorithm is better than the idealized DRL-based scheme which can obtain the same information as the soft labels. Simulation results demonstrate that compared with existing DRL-based algorithms, our proposed algorithm reduces the number of iterations by up to 90%.

4 November 2021 in IEEE Wireless Communications Letters
Verified
Journal Article
Closed access
HHHao Han
Hao Han
YXYifan Xu
Yifan Xu
ZJZhu Jin
Zhu Jin
WLWen Li
Wen Li
XCXueqiang Chen
Xueqiang Chen
YXYuhua Xu
Yuhua Xu
This letter studies the problem of deep reinforcement learning (DRL)-based dynamic spectrum anti-jamming access in overlay cognitive radio networks. To prevent secondary user (SU) from interfering with primary user (PU) and being jammed by jammer, we propose a PU-friendly dynamic spectrum anti-jamming access scheme. First, a generative adversarial network (GAN)-based virtual environment is proposed to simulate spectrum environment. Then, a DRL-based channel decision network (CDN) is trained to learn the optimal spectrum access policy in the virtual environment. Finally, SU accesses spectrum environment under the guidance of the trained CDN. Simulation results show that the proposed scheme is able to elude both PU signals and jamming completely and converges much faster than the scheme that trains the CDN in spectrum environment from scratch.

4 January 2022 in IEEE Wireless Communications Letters
Verified
Journal Article
Closed access
HHHao Han
Hao Han
WLWen Li
Wen Li
ZFZhibin Feng
Zhibin Feng
GFGui Fang
Gui Fang
YXYifan Xu
Yifan Xu
YXYuhua Xu
Yuhua Xu
In this letter, we study the problem of jamming pattern recognition (JPR) when some patterns have no training samples. Existing works were designed for recognition of known jamming patterns only, hence they failed to deal with unknown jamming patterns. To address this challenge, a zero-shot learning (ZSL) based JPR scheme is proposed. Firstly, a supervised training process is introduced to learn the latent feature representation of known jamming patterns. Then, an unsupervised classification approach is proposed to recognize different jamming patterns. Finally, both known and unknown jamming patterns are classified in latent feature space. Simulation results show that the proposed scheme achieves excellent performance when dealing with the open-set JPR tasks.