Federated learning (FL) has emerged as the most promising distributed machine learning training framework due to its advantages in efficiency, privacy preservation, and scalability. In the practical deployment, FL usually faces the system heterogeneity, data heterogeneity, and limited communication resources. Many works attempt to address the above challenges by client selection, but seldom consider the issues of missing classes in training samples and communication resource allocation, which leads to poor training performance. In this paper, we propose an efficient FL framework with clustering-based client selection and bandwidth allocation, called FedCCS. Specifically, FedCCS first clusters clients based on the local label distribution. By ensuring clients from each cluster participate in training, a wider range of sample classes are covered to mitigate data heterogeneity effects. Furthermore, considering system heterogeneity and limited communication resources, we develop an iterative-based joint optimization algorithm for client selection and bandwidth allocation to minimize latency. Experimental results on both simulations and real-world prototypes show that, compared to other methods, FedCCS can significantly reduce latency and improve the stability of model performance during the training process.

Abstract With the rapid development of communication technology and the increasing demand for coverage refinement in wireless communication networks, the optimization of wireless communication networks is faced with unprecedented challenges. Obtaining the signal distribution map of wireless communication networks efficiently has become a popular area of study in this field. This paper considers a distributed sensing network architecture, a radial basis function neural network is used to process electromagnetic data and optimize the parameters of the random forest model. Then, interpolation processing of incomplete electromagnetic data is achieved by the improved random forest model, based on which a signal distribution map of the wireless communication network is reconstructed. The results indicate that the proposed algorithm yields high interpolation accuracy. The average error between the real signal distribution and the reconstructed signal distribution is 2.7973 dBm when the proportion of sampled nodes is 1%, and the similarity of the reconstructed signal distribution map to the original signal distribution map is good, demonstrating certain application prospects.

Since distributed sensing, storage, and computing are the frontiers for future sixth‐generation (6G) communication systems, user terminal (UT) localization based on received signal strength (RSS) data from wireless sensor networks (WSNs) has received widespread attention because of its low energy consumption and ease of operation. Most of the existing work focused on the single‐source localization problem. However, multiple UT localization is a more realistic problem that has not been well addressed. In this paper, we proposed a novel multiple UT localization scheme. Specifically, based on the log‐normal property of spatial shadowing, the RSS is approximated as a random variable obeying a log‐normal distribution, and the objective function is derived via maximum likelihood estimation. Then, aiming to better solve the objective function, a radio map is constructed to narrow search area, and a meta‐heuristic algorithm with global search capability is adopted. Compared with the state‐of‐the‐art methods through simulation experiments, it is proved that the method proposed in this paper has the best localization performance.

Radio frequency fingerprint identification (RFFI) has become a crucial technology in physical layer authentication, and plays an important role in authenticating the identities of wireless communication devices in the Internet of Things (IoT). Although open-set recognition has been applied in RFFI tasks, these schemes still demand extensive RF signal samples. In this paper, few-shot open-set recognition is being dedicated to exploring in RFFI tasks. To surmount mentioned challenges, we propose meta-learning by gaussian prototype network (MLGPN) scheme to achieve the goal of few-shot open-set recognition. MLGPN adopts the Mahalanobis distance between the embedding feature and the gaussian prototype as its metric. With the introduction of open-set loss function, the proposed scheme shows excellent open-set recognition performance. It is worth mentioning that meta-learning not only satisfies the demands of few-shot scenarios, but also enables new devices to join and leave without the need for retraining. Experiments conducted based on real LoRa RF signals confirmed the excellent performance of our proposed scheme for few-shot open-set recognition which surpasses traditional prototypical network model by 5.3% of AUC and 6.7% of ACC under the 1-shot condition. Compared with other schemes, the proposed scheme also demonstrated significant advantages.

A radio environment map (REM) is a visualization method that display electromagnetic properties, such as received signal strength, channel gain, and power spectrum density in combination with geographic information. The map can effectively support modern Internet of Things (IoT) network planning and resource management. A novel REM construction scheme of an arbitrary height and frequency in 3-D space is studied in this article. First, a complex urban environment is considered, where the radiation sources transmit wireless signals in different frequency bands. Then, the construction is sliced into 2-D planes with various elevations to achieve precise and efficient sensing of 3-D space. For near-ground scenarios, preliminary global interpolation based on linear unbiased estimation is first performed to obtain a coarse REM, and then graph neural networks are utilized to further extract the relationships and features of the spatial nodes to improve the construction accuracy. For high-altitude scenarios, a small range of interpolation is carried out on the basis of linear unbiased estimation with the clustering center obtained by clustering the known sensing nodes as the center of the circle. Then the global construction is implemented via domain transformation processing to increase the construction speed. Finally, the 2-D REMs are stacked in sheets according to elevation to form a 3-D REM. The simulation results demonstrate the effectiveness and superiority of the proposed scheme.

radiation source localization (RSL) via received signal strength (RSS) from wireless sensor network has received much attention due to its simplicity and low energy consumption. However, localization in the presence of multiple radiation sources and in complex propagation environments, such as shadow effect is still not well addressed. In this article, we utilize the lognormal property of the shadow effect to approximate RSS as a random variable obeying a lognormal distribution, and construct a multi-RSL model based on maximum likelihood estimation. Thus the model is shadow-resilient. In order to better solve the nonconvex objective function, we construct radio map based on RSS, so as to provide key parameters of number of radiation sources, initial feasible solutions and location constraints for the localization model. Ultimately, we realize high-precision localization of radiation sources. Among them, this is the first time that sparse Gaussian process regression based on variational inference is applied to radio map construction, and the method can greatly reduce computational complexity to better meet the real demand of large area and large data. Both simulation and real-world experiments show that the proposed method can achieve the highest localization accuracy with the lowest computational complexity compared with the state-of-the-art methods. Additionally, Cramer–Rao lower bound (CRLB) is also derived in detail.

Abstract Based on the successful application of generative adversarial network (GAN) models in the field of image generation, this article introduces GANs into the field of deep learning for communication systems and surveys its application in modulation classification. To solve the difficulties in feature extraction, to address the low recognition accuracy of existing radio signal modulation‐type recognition methods, and to adapt to complex electromagnetic environments with high noise interference intensity, this article presents a modulation recognition model for high‐order digital signals. This model uses the Morlet wavelet transform to analyse time‐frequency signals, uses the excellent image generation performance of a GAN model to extract and reconstruct the features of noise‐contaminated time‐frequency images, and designs an integrated classification network architecture to classify and predict reconstructed images. The experimental results show that the algorithm model proposed in this article can significantly improve the recognition accuracy of high‐order digital modulated signals under low signal‐to‐noise ratio conditions and can achieve 90% recognition accuracy at a signal‐to‐noise ratio of 1 dB.

In this article, we propose a novel localization and channel estimation integration framework for cell-free massive multiple-input–multiple-output (MIMO) Internet of Things (IoT) systems, in which position information supports accurate channel estimation and accurate channel information can, in turn, improve positioning accuracy. Under this integration framework, we propose a two-phase fingerprint-based localization method consisting of both initial and accurate localization phases and a coarse-location-based (CLB) pilot reassignment scheme. The coarse location information for pilot reassignment is obtained in the initial localization phase of the two-phase localization method, and the fingerprint information used in the accurate localization phase is extracted through channel estimation based on the CLB scheme. Furthermore, for localization, two different fingerprint similarity criteria are proposed to meet the requirements of the different localization phases. Simulation results demonstrate that our proposed two-phase fingerprint-based localization method achieves better positioning performance than existing methods, although there is a slight increase in computational complexity compared to the initial localization. Moreover, our proposed CLB pilot reassignment scheme outperforms the conventional pilot assignment schemes in the comprehensive performance considering both channel estimation performance and complexity.

Intelligent reflecting surfaces (IRSs) have significant advantages in enhancing the coverage and reducing the deployment cost of wireless networks. This paper studies an aerial IRS- (AIRS-) enhanced cell-free massive multiple-input multiple-output- (MIMO-) based wireless sensor network (WSN) in which multiple access points (APs) serve several sensor users (SUs). Direct links between the APs and SUs are blocked due to occlusion by tall buildings. Hence, we deploy an AIRS to improve the communication quality of the SUs. Our goal is to minimize the total transmit power of all APs under a given minimum signal-to-interference-plus-noise ratio (SINR) requirement. We propose a joint iterative optimization algorithm by designing an active beamforming mechanism at each AP and a passive beamforming mechanism at the AIRS to solve this problem. Simulation results illustrate the good performance of the proposed method.

In this paper, beam-domain (BD) anti-jamming transmission in a downlink massive multiple-input multiple-output (MIMO) system is investigated. A smart jammer with multiple antennas attempts to interfere with the signal reception of users with the desired energy efficiency (EE), whereas a base station (BS) tries to minimize the transmission cost while ensuring uninterrupted communication. A Bayesian Stackelberg game between the BS and jammer, where the jammer is the follower and the BS acts as the leader, is modeled. In the follower subgame, the optimal jamming precoding with a closed-form power solution is introduced. The optimal jamming power is proportional to the transmission power in the downlink, and thus, for the BS, the strategy of suppressing malicious attacks by increasing the transmission power fails. In the leader subgame, generalized zero-forcing (ZF), whose closed-form power solution constitutes the unique Stackelberg equilibrium (SE) with that of the jammer, is found to be the optimal anti-jamming precoding for robust transmission. The results show that there always exists a precoding solution for the BS that ensures reliable transmission when the SE is obtained. A proper increase in the minimum signal-to-interference-and-noise ratio (SINR) threshold or the BD channel approximation error helps the BS save power during the resistance against the jammer. Then, a simplified power solution without the instantaneous channel state information (CSI) of jamming channels is further introduced for practical implementation. Numerical results are provided to verify the proposed solutions.

In this paper, we investigate the interactions between a base station (BS) and a full-duplex (FD) active eavesdropper in the uplink of multi-cell massive multiple-input multiple-output (MIMO) systems. Focusing on the resistance against simultaneous eavesdropping and jamming, we introduce a beam extraction method based on spatial information to eliminate pilot contamination, from which a beam-domain (BD) distributed receiving scheme is proposed to suppress the jamming mixed in users' signals. From a practical point of view, we use the perspective of a hierarchical game to analyze the interactions without the prior information of the eavesdropper. The results show that with the help of the proposed scheme, the performance of the FD-mode attack is inferior to that of passive eavesdropping. A statistical upper bound of eavesdropping is given in a closed-form, which is mainly determined by the direction and distance of the eavesdropper relative to users. Then, a joint power and combining matrix optimization algorithm is proposed to improve the secrecy capacity of the system.

In this study, the authors consider the simultaneous wireless information and power transfer (SWIPT) protocol design for the massive multiple‐input multiple‐output (MIMO) system in the beam‐domain. In this system, the base station (BS) simultaneously serves a set of half‐duplex energy‐constrained terminals that are uniformly distributed within its coverage area. Based on the beam‐domain distributions of channels, the BS can intelligently schedule terminals to mitigate the interference between terminals and improve the transmission spectral efficiency. The entire protocol can be divided into two phases. The first phase is designed for terminals energy harvesting as well as downlink training. During this phase, the BS transmits energy signals to the terminals. The terminals utilise the received energy signals for energy harvesting and downlink channel estimation. In the second phase, the BS forms the receive beamformers to receive signals transmitted by terminals. The transmit powers at the BS and the time switching ratio are optimised under the constraints of the current available energy and minimum transmission rate of terminals, so that the system can achieve the maximum sum‐rate performance. Simulation results show that compared with traditional massive MIMO SWIPT protocols, the proposed SWIPT protocol can achieve better spectral efficiency performance.