Spectrum prediction is considered as a key technology to assist spectrum decision. Despite the great efforts that have been put on the construction of spectrum prediction, achieving accurate spectrum prediction emphasizes the need for more advanced solutions. In this paper, we propose a new multi-channel multi-step spectrum prediction method using Transformer and stacked bidirectional LSTM (Bi-LSTM), named TSB. Specifically, we use multi-head attention and stacked Bi-LSTM to build a new Transformer based on encoder-decoder architecture. The self-attention mechanism composed of multiple layers of multi-head attention can continuously attend to all positions of the multichannel spectrum sequences. The stacked Bi-LSTM can learn these focused coding features by multi-head attention layer by layer. The advantage of this fusion mode is that it can deeply capture the long-term dependence of multichannel spectrum data. We have conducted extensive experiments on a dataset generated by a real simulation platform. The results show that the proposed algorithm performs better than the baselines.

Reconfigurable intelligent surface (RIS) is a promising candidate technology of the upcoming Sixth Generation (6G) communication system for its ability to provide unprecedented spectral and energy efficiency increment through passive beamforming. However, it is challenging to obtain instantaneous channel state information (I-CSI) for RIS, which obliges us to use statistical channel state information (S-CSI) to achieve passive beamforming. In this paper, RIS-aided multiple-input single-output (MISO) multi-user downlink communication system with correlated channels is investigated. Then, we formulate the problem of joint beamforming design at the AP and RIS to maximize the sum ergodic spectral efficiency (ESE) of all users to improve the network capacity. Since it is too hard to compute sum ESE, an ESE approximation is adopted to reformulate the problem into a more tractable form. Then, we present two joint beamforming algorithms, namely the singular value decomposition-gradient descent (SVD-GD) algorithm and the fractional programming-gradient descent (FP-GD) algorithm. Simulation results show the effectiveness of our proposed algorithms and validate that $2$-bits quantizer is enough for RIS phase shifts implementation.

Using satellites to complete spectrum monitoring tasks can effectively receive and process electromagnetic spectrum signals emitted by radiation sources. However, due to the shortage of satellite storage, computing and network resources, the inter-satellite coordination is weak, and with the massive growth of spectrum data, the traditional cloud computing mode cannot meet the requirements of electromagnetic spectrum monitoring in terms of real-time, bandwidth, and security. We apply edge computing technology and deep learning technology to the satellite. Aiming at the problems of distributed satellite management and control, we propose a space-based distributed electromagnetic spectrum monitoring intelligent connected cloud-edge collaborative architecture SpaceEdge. SpaceEdge applies edge computing and artificial intelligence technology to space-based spectrum monitoring. SpaceEdge deploys intelligent monitoring algorithms to edge nodes to form edge intelligent satellite, and uses the cloud to uniformly manage and control heterogeneous edge satellite and monitor satellite resources. In addition, SpaceEdge can also adjust edge intelligent spectrum monitoring applications as needed to achieve effective coordination of inter-satellite algorithms and data to achieve the purpose of collaborative monitoring. Finally, SpaceEdge was experimentally verified, and the results proved the feasibility of SpaceEdge and can improve the timeliness and autonomy of the distributed satellite's coordinated signal monitoring.

Named data networking (NDNs) is an idealized deployment of information-centric networking (ICN) that has attracted attention from scientists and scholars worldwide. A distributed in-network caching scheme can efficiently realize load balancing. However, such a ubiquitous caching approach may cause problems including duplicate caching and low data diversity, thus reducing the caching efficiency of NDN routers. To mitigate these caching problems and improve the NDN caching efficiency, in this paper, a hierarchical-based sequential caching (HSC) scheme is proposed. In this scheme, the NDN routers in the data transmission path are divided into various levels and data with different request frequencies are cached in distinct router levels. The aim is to cache data with high request frequencies in the router that is closest to the content requester to increase the response probability of the nearby data, improve the data caching efficiency of named data networks, shorten the response time, and reduce cache redundancy. Simulation results show that this scheme can effectively improve the cache hit rate (CHR) and reduce the average request delay (ARD) and average route hop (ARH).

Reconfigurable intelligent surface (RIS) has proven to be promising for future wireless communication. Due to its ability to manipulate electromagnetic (EM) waves, RIS provides a flexible and programmable way to implement intelligent wireless environments. While path loss modeling has been conducted in some prior research, an issue remaining unknown is the characteristics of multi-beam path loss for RIS. In this paper, we model, simulate and measure the multi-beam path loss in RIS-assisted broadcast communication scenarios. We propose two specific configurations of RIS and derive the path loss models, which reveal that the incident beam can be equally divided into multiple beams without power loss through rational design of the phase coding. The proposed path loss model is validated through simulation subsequently. To further verify our conclusions, we build a millimeter wave (mmWave) measurement system with a 35 GHz fabricated RIS. The measurement result corresponds well with the simulation, which shows a difference of about 3 dB in the received signal power of quad-beam compared with dual-beam, as well as dual-beam compared with single-beam, except for the impact of radiation patterns of the antennas and RIS elements.

This paper studies the problem of jamming decision-making for dynamic multiple communication links in wireless communication networks (WCNs). We propose a novel jamming channel allocation and power decision-making (JCAPD) approach based on multi-agent deep reinforcement learning (MADRL). In high-dynamic and multi-target aviation communication environments, the rapid changes in channels make it difficult for sensors to accurately capture instantaneous channel state information. This poses a challenge to make centralized jamming decisions with single-agent deep reinforcement learning (DRL) approaches. In response, we design a distributed multi-agent decision architecture (DMADA). We formulate multi-jammer resource allocation as a multi-agent Markov decision process (MDP) and propose a fingerprint-based double deep Q-Network (FBDDQN) algorithm for solving it. Each jammer functions as an agent that interacts with the environment in this framework. Through the design of a reasonable reward and training mechanism, our approach enables jammers to achieve distributed cooperation, significantly improving the jamming success rate while considering jamming power cost, and reducing the transmission rate of links. Our experimental results show the FBDDQN algorithm is superior to the baseline methods.

With the increase of wireless devices and new applications, highly dense small cell base stations (SBS) have become the main means to overcome the speed bottleneck of the radio access network (RAN). However, the highly-dense deployment of SBSs greatly increases the cost of network operation and maintenance. In this paper, a base station sleep strategy combining traffic aware and high-low frequency resource allocation is proposed. To reduce the service level agreement (SLA) default caused by base station sleep, Long Short-Term Memory (LSTM) algorithm is introduced to predict the traffic flow, based on the predict result, the SBSs sleep and frequency resource allocation are introduced to increase the energy efficiency of the network. Moreover, this paper improves the decision-making efficiency by introducing Kuhn Munkres algorithm (KM) and genetic algorithm (GA). Simulation results show that the proposed strategy can greatly reduce the energy consumption of small cells and the occurrence of SLA default rate.

A new cyclic prefix (CP)-based non-overlapping FBMC-QAM (CP-NO-FBMC-QAM) system with two prototype filters is proposed in this paper, which satisfies complex orthogonality conditions and good frequency energy confinement at the same time.We analyze its inter-carrier interference/inter-symbol interference (ICI/ISI) over multipath channels. Owing to the additional CP, the ISI of received symbols over multipath channels is eliminated in the proposed system, and the resulting improvement in the signal-to-interference ratio (SIR) performance is evaluated by theoretical analysis.Moreover, for the ICI caused by multipath propagation in received symbols, we develop a method that eliminates the ICI by frequency-domain channel estimation and equalization before the receiver filtering process.The proposed CP-NO-FBMC-QAM system and ICI cancellation method (ICICM) are validated by comparisons of implementation complexity, power spectral density (PSD), bit error rate (BER) and channel estimation performance with conventional CP-based orthogonal frequency division multiplexing (CP-OFDM) and FBMC-QAM systems.

Extremely large-scale array (XL-array) communications can significantly improve the transmission rate, spectral efficiency, and spatial resolution, and has great potential in next-generation mobile communication networks. A crucial problem in XL-array communications is to determine the boundary of applicable regions of the plane wave model (PWM) and spherical wave model (SWM). In this paper, we propose new PWM/SWM demarcations for XL-arrays from the viewpoint of channel gain and rank. Four sets of results are derived for four different array setups. First, an equi-power line is derived for a point-to-uniform linear array (ULA) scenario, where an inflection point is found at $\pm \frac{\pi}{6}$ central incident angles. Second, an equi-power surface is derived for a point-to-uniform planar array (UPA) scenario, and it is proved that $\cos^2(\phi) \cos^2(\varphi)=\frac{1}{2}$ is a dividing curve, where $\phi$ and $\varphi$ denote the elevation and azimuth angles, respectively. Third, an accurate and explicit expression of the equi-rank surface is obtained for a ULA-to-ULA scenario. Finally, an approximated expression of the equi-rank surface is obtained for a ULA-to-UPA scenario. With the obtained closed-form expressions, the equi-rank surface for any antenna structure and any angle can be well estimated. Furthermore, the effect of scatterers is also investigated, from which some insights are drawn.

The integrated optical true time delay phased array antenna system has the advantages of high bandwidth, small size, low loss and strong anti-interference capability, etc. The high integration of the optically controlled phased array antenna system is a necessary trend for the future development of the phased array, and it is also a major focus and difficulty in the current research of integrated microwave photonics. This paper firstly introduces the basic principle and development history of optical true time delay phased array antenna system based on microwave photonics, and briefly introduces the main implementation methods and integration platform of optical true time delay. Then, the application and development prospect of optical true time delay technology in beam control of phased array antenna system are mainly presented. Finally, according to the current research progress, the possible research directions of integrated optically controlled phased array antenna systems in the future are proposed.

Covert communication guarantees the security of wireless communications via hiding the existence of the transmission.This paper focuses on the first and second order asymptotics of covert communication in the AWGN channels. The covertness is measured by the total variation distance between the channel output distributions induced with and without the transmission.We provide the exact expressions of the maximum amount of information that can be transmitted with the maximum error probability and the total variation less than any small numbers.The energy detection and the random coding are employed to prove our results.We further compare our results with those under relative entropy. The results show how many additional amounts of information can be transmitted covertly when changing the covertness constraint to total variation.

Deep learning-based Joint Source-Channel Coding (JSCC) is a crucial component in semantic communication, and recent research has made significant progress in adapting to different channels. In this paper, we propose a multi-stage progressive technique called Deep learning based Progressive Joint Source-Channel Coding (DP-JSCC). This approach partitions the source into multiple stages and transmits the signals continuously. The receiver gradually enhances the quality of image reconstruction by progressively receiving the signals, offering greater flexibility compared to existing dynamic rate transmission methods. The model adopts a lightweight architectural design, where we introduce an efficient module called the Inverted Shuffle Attention Bottleneck (ISAB) and incorporate self-attention mechanisms in the encoding and decoding process to capture signal correlations and establish long-range dependencies. Additionally, we introduce the Progressive Focus Weight Allocation (PFWA) method to improve the image reconstruction capability in progressive transmission tasks. These design enhance the expressive capacity of the model. Simulation results demonstrate that DP-JSCC can flexibly adjust the transmission rate according to requirements without the need for retraining or deployment, enabling continuous optimization of signals at different rates. Furthermore, compared to state-of-the-art JSCC methods, DP-JSCC exhibits advantages in terms of computational complexity, parameter count, and reconstruction performance.

This paper investigates a wireless powered communication network (WPCN) facilitated by an unmanned aerial vehicle (UAV) in Internet of Things (IoT) networks, where multiple IoT devices (IoTDs) gather energy from a terrestrial energy station (ES) during the wireless energy transfer (WET) stage, followed by the UAV collecting data from these powered IoTDs with the time division multiple access (TDMA) protocol in the wireless information transfer (WIT) stage. To overcome the challenges of radio propagation caused by obstructions, we incorporate a reconfigurable intelligent surface (RIS) to enhance the link quality of the ES-IoTDs and IoTDs-UAV. The primary objective is to maximize the average sum rate of all IoTDs by jointly optimizing UAV trajectory, ES transmit power, and RIS phase shifts, along with the time allocation for WET and WIT. To this end, we reformulate the optimization problem as a markov decision process (MDP) and introduce a deep reinforcement learning (DRL) approach for addressing the formulated problem, called the proximal policy optimization (PPO) based energy harvesting with trajectory design and phase shift optimization (PPO-EHTDPS) algorithm. By continuously exploring within the environment, the PPO algorithm refines its policy to optimize the UAV trajectory, the energy phase shifts, ES transmit power, and WET/WIT time allocation. Additionally, a continuous phase shift optimization algorithm is employed to determine the information phase shifts for each IoTD to maximize average sum rate. Finally, numerical results demonstrate that the proposed PPO-EHTDPS algorithm can significantly achieve higher average sum rate and show better convergence performance over the benchmark algorithms.

The Internet of Unmanned Aerial Vehicles (I-UAVs) is expected to execute latency-sensitive tasks, but limited by co-channel interference and malicious jamming. In the face of unknown prior environmental knowledge, defending against jamming and interference through spectrum allocation becomes challenging, especially when each UAV pair makes decisions independently. In this paper, we propose a cooperative multi-agent reinforcement learning (MARL)-based anti-jamming framework for I-UAVs, enabling UAV pairs to learn their own policies cooperatively. Specifically, we first model the problem as a model-free multi-agent Markov decision process (MAMDP) to maximize the long-term expected system throughput. Then, for improving the exploration of the optimal policy, we resort to optimizing a MARL objective function with a mutual-information (MI) regularizer between states and actions, which can dynamically assign the probability for actions frequently used by the optimal policy. Next, through sharing their current channel selections and local learning experience (their soft Q-values), the UAV pairs can learn their own policies cooperatively relying on only preceding observed information and predicting others' actions. Our simulation results show that for both sweep jamming and Markov jamming patterns, the proposed scheme outperforms the benchmarkers in terms of throughput, convergence and stability for different numbers of jammers, channels and UAV pairs.

Mobile crowdsensing (MCS) has become an effective paradigm to facilitate urban sensing. However, mobile users participating in sensing tasks will face the risk of location privacy leakage when uploading their actual sensing location data. In the application of mobile crowdsensing, most location privacy protection studies do not consider the temporal correlations between locations, so they are vulnerable to various inference attacks, and there is the problem of low data availability. In order to solve the above problems, this paper proposes a dynamic differential location privacy data publishing framework (DDLP) that protects privacy while publishing locations continuously. Firstly, the corresponding Markov transition matrices are established according to different times of historical trajectories, and then the protection location set is generated based on the current location at each timestamp. Moreover, using the exponential mechanism in differential privacy perturbs the true location by designing the utility function. Finally, experiments on the real-world trajectory dataset show that our method not only provides strong privacy guarantees, but also outperforms existing methods in terms of data availability and computational efficiency.

With the rapid development of web3.0 applications, the volume of data sharing is increasing, the inefficiency of big data file sharing and the problem of data privacy leakage are becoming more and more prominent, and the existing data sharing schemes have been difficult to meet the growing demand for data sharing, this paper aims at exploring a secure, efficient and privacy-protecting data sharing scheme under web3.0 applications. Specifically, this paper adopts interplanetary file system (IPFS) technology to realize the storage of large data files to solve the problem of blockchain storage capacity limitation, and utilizes ciphertext policy attribute-based encryption (CP-ABE) and proxy re-encryption (PRE) technology to realize secure multi-party sharing and fine-grained access control of data. This paper provides the detailed algorithm design and implementation of data sharing phases and processes, and analyzes the algorithms from the perspectives of security, privacy protection, and performance.

Symmetric encryption algorithms learned by the previous proposed end-to-end adversarial network encryption communication systems are deterministic. With the same key and same plaintext, the deterministic algorithm will lead to the same ciphertext. This means that the key in the deterministic encryption algorithm can only be used once, thus the encryption is not practical. To solve this problem, a non-deterministic symmetric encryption end-to-end communication system based on generative adversarial networks is proposed. We design a nonce-based adversarial neural network model, where a "nonce" standing for "number used only once" is passed to communication participants, and does not need to be secret. Moreover, we optimize the network structure through adding Batch Normalization (BN) to the CNNs (Convolutional Neural Networks), selecting the appropriate activation functions, and setting appropriate CNNs parameters. Results of experiments and analysis show that our system can achieve non-deterministic symmetric encryption, where Alice encrypting the same plaintext with the key twice will generate different ciphertexts, and Bob can decrypt all these different ciphertexts of the same plaintext to the correct plaintext. And our proposed system has fast convergence and the correct rate of decryption when the plaintext length is 256 or even longer.

Virtualization is an indispensable part of the cloud for the objective of deploying different virtual servers over the same physical layer. However, the increase in the number of applications executing on the repositories results in increased overload due to the adoption of cloud services. Moreover, the migration of applications on the cloud with optimized resource allocation is a herculean task even though it is employed for minimizing the dilemma of allocating resources. In this paper, a Fire Hawk Optimization enabled Deep Learning Scheme (FHOEDLS) is proposed for minimizing the overload and optimizing the resource allocation on the hybrid cloud container architecture for migrating interoperability based applications This FHOEDLS achieves the load prediction through the utilization of deep CNN-GRU-AM model for attaining resource allocation and better migration of applications. It specifically adopted the Fire Hawk Optimization Algorithm (FHOA) for optimizing the parameters that influence the factors that aid in better interoperable application migration with improved resource allocation and minimized overhead. It considered the factors of resource capacity, transmission cost, demand, and predicted load into account during the formulation of the objective function utilized for resource allocation and application migration. The cloud simulation of this FHOEDLS is achieved using a container, Virtual Machine (VM), and Physical Machine (PM). The results of this proposed FHOEDLS confirmed a better resource capability of 0.418 and a minimized load of 0.0061.

The propagation characteristics of wireless body area network (WBAN) under the hospital environments at 10GHz are studied for exploring the feasibility of indoor high frequency communication. Based on the extensive measured data in the hospital room and corridor scenarios, a new path loss (PL) model with the antenna angle factor (called as AAF) is proposed, where AAF is used to characterize the influence of angle change of a wearable or handheld device of the human body on the PL. Moreover, the expression of AAF is presented, which is a trigonometric functional of the angle of receiving antenna. In addition, the statistical characteristics of the time-domain root-mean-square delay spread (RMS-DS) are given under the two hospital scenarios, and a novel RMS-DS model is also presented. In the proposed model, the RMS-DS is expressed as a linear function of PL, and a normal random variable is employed to describe the deviation between the measured RMS-DS and the linear function. The validity of the proposed models is verified in the different hospital environments, and the simulation results show that the proposed models have higher accuracy and better adaptability than the existing models.

Satellite-terrestrial spectrum sharing can effectively alleviate the scarcity of spectrum resources, which is a widely concerned issue in the academic community, and thus have received great attention. In this paper, considering the delay-limited transmission mode, we investigate a hybrid satellite-terrestrial network and propose a spectrum sharing scheme to increase the spectrum efficiency by sharing spectrum resources both between various networks on the condition of interference constraints and within one network by enabling non-orthogonal multiple access. The feasibility of spectrum sharing is first analyzed, which is also the theoretical foundation of our proposed scheme. Afterwards, by employing the Shadowed-Rician fading, we evaluate its performance, while realistically taking the mutual interferences between terrestrial and satellite networks into consideration. In addition, these theoretical derivation results are used for power allocation to maximize the system throughput by tedious algebraic operations. Finally, we validate the superiority of our proposed spectrum sharing scheme and the proposed power allocation method through numerical simulation.

As the new generation of low Earth orbit (LEO) satellite communication systems begins to provide high-speed broadband access services to areas without terrestrial cellular coverage, scholars both domestically and internationally are reassessing the relationship between satellite and ground communications in regions prone to warfare and sparsely populated areas. Especially after the launch of Starlink's "Direct to Cell" service, many believe that new-generation LEO satellite communication systems may not just be a supplement to terrestrial networks in the future. Presently, the discourse surrounding satellite-terrestrial network technology predominantly centers on economic costs and user acceptance, with a noticeable gap in research that addresses green communication and sustainable development. This paper, therefore, aims to fill this void by modeling the energy consumption of LEO satellite communication systems, exemplified by Starlink, and juxtaposing it with that of terrestrial networks. Our findings indicate that the energy consumption of satellite communication systems, such as Starlink, is a staggering 32.9 times higher than that of ground base station clusters in remote regions and an astonishing 715 times greater in densely populated urban areas. Although satellite communication systems hold the promise of global coverage, their standalone construction without integration with terrestrial networks could lead to significant energy waste.

Solving the path planning problem of Autonomous Underwater Vehicles (AUVs) is crucial for reducing energy waste and improving operational efficiency. However, two main challenges hinder further development: Firstly, existing algorithms often treat this as a single-objective optimization problem, whereas in reality, it should be multi-objective, considering factors such as distance, safety, and smoothness simultaneously. Secondly, the limited availability of optimization results arises due to they are single-path, which fail to meet real-world conditions. To address these challenges, first of all, an improved AUV path planning model is proposed, in which the collisions of path and obstacles are classified more specifically. Subsequently, a novel Altruistic Nurturing Algorithm (ANA) inspired by natural altruism is introduced. In the algorithm, nurturing cost considering Pareto rank and crowd distance is introduced as guidance of evolution to avoid futile calculation, abandonment threshold is self-adaptive with descendant situation to help individuals escape from local optima and double selection strategy combining crowd and k-nearest neighbors selection helps to get a better-distributed Pareto front. Experimental results comparing ANA with existing algorithms in AUV path planning demonstrate its superiority. Finally, a user-friendly interface, the Multi-Objective AUV Path Planner, is designed to provide users with a group of paths for informed decision-making.