Due to the inherently open and shared nature of the wireless channels, wireless communication networks are vulnerable to jamming attacks, and effective anti-jamming measures are of utmost importance to realize reliable communications. Game theory and reinforcement learning (RL) are powerful mathematical tools in anti-jamming field. This article investigates the anti-jamming problem from the perspective of game theory and RL. First, different anti-jamming domains and anti-jamming strategies are discussed, and technological challenges are globally analyzed from different perspectives. Second, an in-depth systematic and comprehensive survey of each kind of anti-jamming solutions (i.e., game theory and RL) is presented. To be specific, some game models are discussed for game theory based solutions, including Bayesian anti-jamming game, Stackelberg anti-jamming game, stochastic anti-jamming game, zero-sum anti-jamming game, graphical/hypergraphical anti-jamming game, etc. For RL-based anti-jamming solutions, different kinds of RL are given, including Q-learning, multi-armed bandit, deep RL and transfer RL. Third, the strengths and limitations are analyzed for each type of anti-jamming solutions. Finally, we discuss the deep integration of the game theory and RL in solving anti-jamming problems, and a few future research directions are illustrated.

In urban area, 2-D radio map is no longer sufficient for spectrum management, highlighting the growing significance of 3-D radio map. However, traditional methods for constructing 3-D radio map face challenges, including high storage requirements and computational complexity, limiting their effectiveness. To address these issues, this article introduces a systematic approach for constructing 3-D radio maps. Initially, a portion of the real-world 3-D city map is captured and discretized into grids of uniform size. Subsequently, spectrum data is collected using an unmanned-aerial-vehicle (UAV) platform. To enhance sampling efficiency, iterative path planning algorithms refine sampling locations to capture the spectrum conditions of the target space. Finally, the trajectory tensor of the entire spectrum space is constructed through adaptive embedding, and the global spectrum is compressed and reconstructed by using the enhanced tensor singular value decomposition (t-SVD) algorithm to construct the radio map of the city scenario. Comparing our algorithm with the existing methods, we analyze the influence factors of frequency-spatial compression sampling on the spectrum situation and strength recovery. Numerical results show that, compared with the existing methods, the proposed method achieves more accurate spectrum mapping.

The graph neural network (GNN) has shown outstanding performance in processing unstructured data. However, the downstream task performance of GNN strongly depends on the accuracy of data graph structural features and, as a type of deep learning (DL) model, the size of the training dataset is equally crucial to its performance. This paper is based on graph neural networks to predict and complete the target radio environment map (REM) through multiple complete REMs and sparse spectrum monitoring data in the target domain. Due to the complexity of radio wave propagation in space, it is difficult to accurately and explicitly construct the spatial graph structure of the spectral data. In response to the two above issues, we propose a multi-source domain adaptive of GNN for regression (GNN-MDAR) model, which includes two key modules: (1) graph structure alignment modules are used to capture and learn graph structure information shared by cross-domain radio propagation and extract reliable graph structure information for downstream reference signal receiving power (RSRP) prediction task; and (2) a spatial distribution matching module is used to reduce the feature distribution mismatch across spatial grids and improve the model’s ability to remain domain invariant. Based on the measured REMs dataset, the comparative results of simulation experiments show that the GNN-MDAR outperforms the other four benchmark methods in accuracy when there is less RSRP label data in the target domain.

In general, judging the use/idle state of the wireless spectrum is the foundation for cognitive radio users (secondary users, SUs) to access limited spectrum resources efficiently. Rich information can be mined by the inherent correlation of electromagnetic spectrum data from SUs in time, frequency, space, and other dimensions. Therefore, how to efficiently use the spectrum status of each SU implementation of reception multidimensional combination forecasting is the core of this paper. In this paper, we propose a deep-learning hybrid model called TensorGCN-LSTM based on the tensor data structure. The model treats SUs deployed at different spatial locations under the same frequency, and the spectrum status of SUs themselves under different frequencies in the task area as nodes and constructs two types of graph structures. Graph convolutional operations are used to sequentially extract corresponding spatial-domain and frequency-domain features from the two types of graph structures. Then, the long short-term memory (LSTM) model is used to fuse the spatial, frequency, and temporal features of the cognitive radio environment data. Finally, the prediction task of the spectrum distribution situation is accomplished through fully connected layers. Specifically, the model constructs a tensor graph based on the spatial similarity of SUs’ locations and the frequency correlation between different frequency signals received by SUs, which describes the electromagnetic wave’s dependency relationship in spatial and frequency domains. LSTM is used to capture the electromagnetic wave’s dependency relationship in the temporal domain. To evaluate the effectiveness of the model, we conducted ablation experiments on LSTM, GCN, GC-LSTM, and TensorGCN-LSTM models using simulated data. The experimental results showed that our model achieves better prediction performance in RMSE, and the correlation coefficient R² of 0.8753 also confirms the feasibility of the model.

Currently, dealing directly with in-phase and quadrature time series data using the deep learning method is widely used in signal modulation classification. However, there is a relative lack of methods that consider the complex properties of signals. Therefore, to make full use of the inherent relationship between in-phase and quadrature time series data, a complex-valued hybrid neural network (CV-PET-CSGDNN) based on the existing PET-CGDNN network is proposed in this paper, which consists of phase parameter estimation, parameter transformation, and complex-valued signal feature extraction layers. The complex-valued signal feature extraction layers are composed of complex-valued convolutional neural networks (CNN), complex-valued gate recurrent units (GRU), squeeze-and-excite (SE) blocks, and complex-valued dense neural networks (DNN). The proposed network can improve the extraction of the intrinsic relationship between in-phase and quadrature time series data with low capacity and then improve the accuracy of modulation classification. Experiments are carried out on RML2016.10a and RML2018.01a. The results show that, compared with ResNet, CLDNN, MCLDNN, PET-CGDNN, and CV-ResNet models, our proposed complex-valued neural network (CVNN) achieves the highest average accuracy of 61.50% and 62.92% for automatic modulation classification, respectively. In addition, the proposed CV-PET-CSGDNN has a significant improvement in the misjudgment situation between 64QAM, 128QAM, and 256QAM compared with PET-CGDNN on RML2018.01a.

Radio Frequency Fingerprint Identification (RFFI) utilizes non-ideal hardware features present in the signal to identify different transmitters. However, existing RFFI models have poor generalization capabilities. When a model trained on one receiver is deployed on a new receiver, the identification performance of the model degrades due to the effect of different receiver characteristics, which can cause the signal distribution to be shifted. To address this problem, we propose a crossreceiver RFFI based on domain adaptation with dynamic distribution alignment. First, deep features are extracted using the ResNet18 network and the global distribution of the features is aligned using Maximum Mean Discrepancy (MMD). Then multilevel features are extracted using a designed multiscale feature extraction module and the subdomain distribution is aligned using Local Maximum Mean Discrepancy (LMMD). Finally, a dynamic parameter is introduced to adaptively adjust the relative importance between the global and subdomain distributions. Twelve sets of cross-receiver experiments are conducted on the WiSig dataset, and the algorithm in this paper achieves an average identification rate of 92.52 domain. Meanwhile, the experimental results under different signal-to-noise ratios (SNR) also verify the algorithm has strong robust performance. It shows that the algorithm can effectively alleviate the model performance degradation problem in the cross-receiver scenarios.