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.

Quantum computing is a promising technology that has the potential to revolutionize many areas of science and technology, including communication. In this review, we discuss the current state of quantum computing in communication and its potential applications in various areas such as network optimization, signal processing, and machine learning for communication. First, the basic principle of quantum computing, quantum physics systems, and quantum algorithms are analyzed. Then, based on the classification of quantum algorithms, several important basic quantum algorithms, quantum optimization algorithms, and quantum machine learning algorithms are discussed in detail. Finally, the basic ideas and feasibility of introducing quantum algorithms into communications are emphatically analyzed, which provides a reference to address computational bottlenecks in communication networks.

In recent years, deep learning-based semantic communications have shown great potential to enhance the performance of communication systems. This has led to the belief that semantic communications represent a breakthrough beyond the Shannon paradigm and will play an essential role in future communications. To narrow the gap between current research and future vision, after an overview of semantic communications, this article presents and discusses ten fundamental and critical challenges in today's semantic communication field. These challenges are divided into theory foundation, system design, and practical implementation. Challenges related to the theory foundation including semantic capacity, entropy, and rate-distortion are discussed first. Then, the system design challenges encompassing architecture, knowledge base, joint semantic-channel coding, tailored transmission scheme, and impairment are posed. The last two challenges associated with the practical implementation lie in cross-layer optimization for networks and standardization. For each challenge, efforts to date and thoughtful insights are provided.

Network architectures assisted by Generative Artificial Intelligence (GAI) are envisioned as foundational elements of sixth-generation (6G) communication system. To deliver ubiquitous intelligent services and meet diverse service requirements, 6G network architecture should offer personalized services to various mobile devices. Federated learning (FL) with personalized local training, as a privacy-preserving machine learning (ML) approach, can be applied to address these challenges. In this paper, we propose a meta-learning-based personalized FL (PFL) method that improves both communication and computation efficiency by utilizing over-the-air computations. Its "pretraining-and-fine-tuning" principle makes it particularly suitable for enabling edge nodes to access personalized GAI services while preserving local privacy. Experiment results demonstrate the outperformance and efficacy of the proposed algorithm, and notably indicate enhanced communication efficiency without compromising accuracy.

In this paper, we examine an illegal wireless communication network consisting of an illegal user receiving illegal signals from an illegal station and propose an active reconfigurable intelligent surface (ARIS)-assisted multi-antenna jamming (MAJ) scheme denoted by ARIS-MAJ to interfere with the illegal signal transmission. In order to strike a balance between the jamming performance and the energy consumption, we consider a so-called jamming energy efficiency (JEE) which is defined as the ratio of achievable rate reduced by the jamming system to the corresponding power consumption. We formulate an optimization problem to maximize the JEE for the proposed ARIS-MAJ scheme by jointly optimizing the jammer's beamforming vector and ARIS's reflecting coefficients under the constraint that the jamming power received at the illegal user is lower than the illegal user's detection threshold. To address the non-convex optimization problem, we propose the Dinkelbach-based alternating optimization (AO) algorithm by applying the semidefinite relaxation (SDR) algorithm with Gaussian randomization method. Numerical results validate that the proposed ARIS-MAJ scheme outperforms the passive reconfigurable intelligent surface (PRIS)-assisted multi-antenna jamming (PRIS-MAJ) scheme and the conventional multi-antenna jamming scheme without RIS (NRIS-MAJ) in terms of the JEE.

With the rapid development of cloud computing, edge computing, and smart devices, computing power resources indicate a trend of ubiquitous deployment. The traditional network architecture cannot efficiently leverage these distributed computing power resources due to computing power island effect. To overcome these problems and improve network efficiency, a new network computing paradigm is proposed, i.e., Computing Power Network (CPN). Computing power network can connect ubiquitous and heterogenous computing power resources through networking to realize computing power scheduling flexibly. In this survey, we make an exhaustive review on the state-of-the-art research efforts on computing power network. We first give an overview of computing power network, including definition, architecture, and advantages. Next, a comprehensive elaboration of issues on computing power modeling, information awareness and announcement, resource allocation, network forwarding, computing power transaction platform and resource orchestration platform is presented. The computing power network testbed is built and evaluated. The applications and use cases in computing power network are discussed. Then, the key enabling technologies for computing power network are introduced. Finally, open challenges and future research directions are presented as well.

Low earth orbit (LEO) satellites with wide coverage can carry the mobile edge computing (MEC) servers with powerful computing capabilities to form the LEO satellite edge computing system, providing computing services for the global ground users. In this paper, the computation offloading problem and resource allocation problem are formulated as a mixed integer nonlinear program (MINLP) problem. This paper proposes a computation offloading algorithm based on deep deterministic policy gradient (DDPG) to obtain the user offloading decisions and user uplink transmission power. This paper uses the convex optimization algorithm based on Lagrange multiplier method to obtain the optimal MEC server resource allocation scheme. In addition, the expression of suboptimal user local CPU cycles is derived by relaxation method. Simulation results show that the proposed algorithm can achieve excellent convergence effect, and the proposed algorithm significantly reduces the system utility values at considerable time cost compared with other algorithms.

Protocol Reverse Engineering (PRE) is of great practical importance in Internet security-related fields such as intrusion detection, vulnerability mining, and protocol fuzzing. For unknown binary protocols having fixed-length fields, and the accurate identification of field boundaries has a great impact on the subsequent analysis and final performance. Hence, this paper proposes a new protocol segmentation method based on Information-theoretic statistical analysis for binary protocols by formulating the field segmentation of unsupervised binary protocols as a probabilistic inference problem and modeling its uncertainty. Specifically, we design four related constructions between entropy changes and protocol field segmentation, introduce random variables, and construct joint probability distributions with traffic sample observations. Probabilistic inference is then performed to identify the possible protocol segmentation points. Extensive trials on nine common public and industrial control protocols show that the proposed method yields higher-quality protocol segmentation results.

In recent times, various power control and clustering approaches have been proposed to enhance overall performance for cell-free massive multiple-input multiple-output (CF-mMIMO) networks. With the emergence of deep reinforcement learning (DRL), significant progress has been made in the field of network optimization as DRL holds great promise for improving network performance and efficiency. In this work, our focus delves into the intricate challenge of joint cooperation clustering and downlink power control within CF-mMIMO networks. Leveraging the potent deep deterministic policy gradient (DDPG) algorithm, our objective is to maximize the proportional fairness (PF) for user rates, thereby aiming to achieve optimal network performance and resource utilization. Moreover, we harness the concept of “divide and conquer” strategy, introducing two innovative methods termed alternating DDPG (A-DDPG) and hierarchical DDPG (H-DDPG). These approaches aim to decompose the intricate joint optimization problem into more manageable sub-problems, thereby facilitating a more efficient resolution process. Our findings unequivocally showcase the superior efficacy of our proposed DDPG approach over the baseline schemes in both clustering and downlink power control. Furthermore, the A-DDPG and H-DDPG obtain higher performance gain than DDPG with lower computational complexity.

This paper presents an algorithm named the dependency-aware offloading framework (DeAOff), which is designed to optimize the deployment of Gen-AI decoder models in mobile edge computing (MEC) environments. These models, such as decoders, pose significant challenges due to their inter-layer dependencies and high computational demands, especially under edge resource constraints. To address these challenges, we propose a two-phase optimization algorithm that first handles dependency-aware task allocation and subsequently optimizes energy consumption. By modeling the inference process using directed acyclic graphs (DAGs) and applying constraint relaxation techniques, our approach effectively reduces execution latency and energy usage. Experimental results demonstrate that our method achieves a reduction of up to 20% in task completion time and approximately 30% savings in energy consumption compared to traditional methods. These outcomes underscore our solution's robustness in managing complex sequential dependencies and dynamic MEC conditions, enhancing quality of service. Thus, our work presents a practical and efficient resource optimization strategy for deploying models in resource-constrained MEC scenarios.

Abstract: Sparse code multiple access (SCMA) is a non-orthogonal multiple access (NOMA) scheme based on joint modulation and spread spectrum coding. It is ideal for future communication networks with a massive number of nodes due to its ability to handle user overload. Introducing SCMA into visible light communication (VLC) systems can improve the data transmission capability of the system. However, designing a suitable codebook becomes a challenging problem when addressing the demands of massive connectivity scenarios. Therefore, this paper proposes a low-complexity design method for high-overload codebooks based on the minimum bit error rate (BER) criterion. Firstly, this paper constructs a new codebook with parameters based on the symmetric mother codebook structure by allocating the codeword power so that the power of each user codebook is unbalanced; then, the BER performance in the visible light communication system is optimized to obtain specific parameters; finally, the successive interference cancellation (SIC) detection algorithm is used at the receiver side. Simulation results show that the method proposed in this paper can converge quickly by utilizing a relatively small number of detection iterations. This can simultaneously reduce the complexity of design and detection, outperforming existing design methods for massive SCMA codebooks.% so as to reduce the out-of-band (OOB) radiation as much as possible. Parameters of the proposed scheme are solved under joint con-straints of constant power and unity cumulative distribution. A new receiving method is also proposed to improve the bit error rate (BER) performance of OFDM systems. Simulation results indicate the proposed scheme can achieve better OOB radiation and BER performance at same PAPR levels, compared with existing similar companding algorithms.

This work employs intelligent reflecting surface (IRS) to enhance secure and covert communication performance. We formulate an optimization problem to jointly design both the reflection beamformer at IRS and transmit power at transmitter Alice in order to optimize the achievable secrecy rate at Bob subject to a covertness constraint. We first develop a Dinkelbach-based algorithm to achieve an upper bound performance and a high-quality solution. For reducing the overhead and computational complexity of the Dinkelbach-based scheme, we further conceive a low-complexity algorithm in which analytical expression for the IRS reflection beamforming is derived at each iteration. Examination result shows that the devised low-complexity algorithm is able to achieve similar secrecy rate performance as the Dinkelbach-based algorithm. Our examination also shows that introducing an IRS into the considered system can significantly improve the secure and covert communication performance relative to the scheme without IRS.

Memory-unsafe programming languages, such as C/C++, are often used to develop system programs, rendering the programs susceptible to a variety of memory corruption attacks. Among these threats, just-in-time return-oriented programming (JIT-ROP) stands out as an advanced method for conducting code-reuse attacks, effectively circumventing code randomization safeguards. JIT-ROP leverages memory disclosure vulnerabilities to obtain reusable code fragments dynamically and assemble malicious payloads dynamically. In response to JIT-ROP attacks, several re-randomization implementations have been developed to prevent the use of disclosed code. However, existing re-randomization methods require recurrent re-randomization during program runtime according to fixed time windows or specific events such as system calls, incurring significant runtime overhead.
In this paper, we present the design and implementation of \mytool, an efficient re-randomization approach on the AArch64 platform. Unlike previous methods that necessitate frequent runtime re-randomization or reply on unreliable triggering conditions, this approach triggers the re-randomization process by detecting the code page harvest operation, which is a fundamental operation of the JIT-ROP attacks, making our method more efficient and reliable than previous approaches. We evaluate \mytool\ on benchmarks and real-world applications. The evaluation results show that our approach can effectively protect programs from JIT-ROP attacks while introducing marginal runtime overhead.

Multimedia semantic communication has been receiving increasing attention due to its significant enhancement of communication efficiency. Semantic coding, which is oriented towards extracting and encoding the key semantics of video for transmission, is a key aspect in the framework of multimedia semantic communication. In this paper, we propose a facial video semantic coding method with low bitrate based on the temporal continuity of video semantics. At the sender's end, we selectively transmit facial keypoints and deformation information, allocating distinct bitrates to different keypoints across frames. Compressive techniques involving sampling and quantization are employed to reduce the bitrate while retaining facial key semantic information. At the receiver's end, a GAN-based generative network is utilized for reconstruction, effectively mitigating block artifacts and buffering problems present in traditional codec algorithms under low bitrates. The performance of the proposed approach is validated on multiple datasets, such as VoxCeleb and TalkingHead-1kH, employing metrics such as LPIPS, DISTS, and AKD for assessment. Experimental results demonstrate significant advantages over traditional codec methods, achieving up to approximately 10-fold bitrate reduction in prolonged, stable head pose scenarios across diverse conversational video settings.

The low Earth orbit (LEO) satellite networks have outstanding advantages such as wide coverage area and not being limited by geographic environment, which can provide a broader range of communication services and has become an essential supplement to the terrestrial network. However, the dynamic changes and uneven distribution of satellite network traffic inevitably bring challenges to multipath routing. Even worse, the harsh space environment often leads to incomplete collection of network state data for routing decision-making, which further complicates this challenge. To address this problem, this paper proposes a state-incomplete intelligent dynamic multipath routing algorithm (SIDMRA) to maximize network efficiency even with incomplete state data as input. Specifically, we model the multipath routing problem as a markov decision process (MDP) and then combine the deep deterministic policy gradient (DDPG) and the $K$ shortest paths (KSP) algorithm to solve the optimal multipath routing policy. We use the temporal correlation of the satellite network state to fit the incomplete state data and then use the message passing neuron network (MPNN) for data enhancement. Simulation results show that the proposed algorithm outperforms baseline algorithms regarding average end-to-end delay and packet loss rate and performs stably under certain missing rates of state data.

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.

Intelligent Reflecting Surface (IRS), with the potential capability to reconstruct the electromagnetic propagation environment, evolves a new IRS-assisted covert communications paradigm to eliminate the negligible detection of malicious eavesdroppers by coherently beaming the scattered signals and suppressing the signals leakage. However, when multiple IRSs are involved, accurate channel estimation is still a challenge due to the extra hardware complexity and communication overhead. Besides the cross-interference caused by massive reflecting paths, it is hard to obtain the close-formed solution for the optimization of covert communications. On this basis, the paper improves a heterogeneous multi-agent deep deterministic policy gradient (MADDPG) approach for the joint active and passive beamforming (Joint A&P BF) optimization without the channel estimation, where the base station (BS) and multiple IRSs are taken as different types of agents and learn to enhance the covert spectrum efficiency (CSE) cooperatively. Thanks to the 'centralized training and distributed execution' feature of MADDPG, each agent can execute the active or passive beamforming independently based on its partial observation without referring to others. Numeral results demonstrate that the proposed deep reinforcement learning (DRL) approach could not only obtain a preferable CSE of legitimate users and a low detection of probability (LPD) of warden, but also alleviate the communication overhead and simplify the IRSs deployment.

Recently, a new worldwide race has emerged to achieve a breakthrough in designing and deploying massive ultra-dense low-Earth orbit (LEO) satellite constellation (SatCon) networks with the vision of providing everywhere Internet coverage from space. Several players have started the deployment phase with different scales. However, the implementation is in its infancy, and many investigations are needed. This work provides an overview of the state-of-the-art architectures, orbital patterns, top players, and potential applications of SatCon networks. Moreover, we discuss new open research directions and challenges for improving network performance. Finally, a case study highlights the benefits of integrating SatCon network and non-orthogonal multiple access (NOMA) technologies for improving the achievable capacity of satellite end-users.

The proportionate recursive least squares (PRLS) algorithm has shown faster convergence and better performance than both proportionate updating (PU) mechanism based least mean squares (LMS) algorithms and RLS algorithms with a sparse regularization term. In this paper, we propose a variable forgetting factor (VFF) PRLS algorithm with a sparse penalty, e.g., $l_1$-norm, for sparse identification. To reduce the computation complexity of the proposed algorithm, a fast implementation method based on dichotomous coordinate descent (DCD) algorithm is also derived. Simulation results indicate superior performance of the proposed algorithm.

In this paper, we present a novel particle filter (PF)-based direct position tracking method utilizing multiple distributed observation stations. Traditional passive tracking methods are anchored on repetitive position estimation, where the set of consecutive estimates provides the tracking trajectory, such as Two-step and direct position determination methods. However, duplicate estimates can be computationally expensive. In addition, these techniques suffer from data association problems. The PF algorithm is a tracking method that avoids these drawbacks, but the conventional PF algorithm is unable to construct a likelihood function from the received signals of multiple observatories to determine the weights of particles. Therefore, we developed an improved PF algorithm with the likelihood function modified by the projection approximation subspace tracking with deflation (PASTd) algorithm. The proposed algorithm uses the projection subspace and spectral function to replace the likelihood function of PF. Then, the weights of particles are calculated jointly by multiple likelihood functions. Finally, the tracking problem of multiple targets is solved by multiple sets of particles. Simulations demonstrate the effectiveness of the proposed method in terms of computational complexity and tracking accuracy.

Time-Sensitive Network (TSN) with deterministic transmission capability is increasingly used in many emerging fields. It mainly guarantees the Quality of Service (QoS) of applications with strict requirements on time and security. One of the core features of TSN is traffic scheduling with bounded low delay in the network. However, traffic scheduling schemes in TSN are usually synthesized offline and lack dynamism. To implement incremental scheduling of newly arrived traffic in TSN, we propose a Dynamic Response Incremental Scheduling (DR-IS) method for time-sensitive traffic and deploy it on a software-defined time-sensitive network architecture. Under the premise of meeting the traffic scheduling requirements, we adopt two modes, traffic shift and traffic exchange, to dynamically adjust the time slot injection position of the traffic in the original scheme, and determine the sending offset time of the new time-sensitive traffic to minimize the global traffic transmission jitter. The evaluation results show that DR-IS method can effectively control the large increase of traffic transmission jitter in incremental scheduling without affecting the transmission delay, thus realizing the dynamic incremental scheduling of time-sensitive traffic in TSN.

In this paper, we focus on the channel estimation for multi-user MIMO-OFDM systems in rich scattering environments. We find that channel sparsity in the delay-angle domain is severely compromised in rich scattering environments, so that most existing compressed sensing (CS) based techniques can harvest a very limited gain (if any) in reducing the channel estimation overhead. To address the problem, we propose the learning-based turbo message passing (LTMP) algorithm. Instead of exploiting the channel sparsity, LTMP is able to efficiently extract the channel feature via deep learning as well as to exploit the channel continuity in the frequency domain via block-wise linear modelling. More specifically, as a component of LTMP, we develop a multi-scale parallel dilated convolutional neural network (MPDCNN), which leverages frequency-space channel correlation in different scales for channel denoising. We evaluate the LTMP's performance in MIMO-OFDM channels using the 3rd generation partnership project (3GPP) clustered delay line (CDL) channel models. Simulation results show that the proposed channel estimation method has more than 5 dB power gain than the existing algorithms when the normalized mean-square error of the channel estimation is -20 dB. The proposed algorithm also exhibits strong robustness in various environments.

Automatic modulation classification (AMC) technology is one of the cutting-edge technologies in cognitive radio communications. AMC based on deep learning has recently attracted much attention due to its superior performances in classification accuracy and robustness. In this paper, we propose a novel, high resolution and multi-scale feature fusion convolutional neural network model with a squeeze-excitation block, referred to as HRSENet, to classify different kinds of modulation signals. The proposed model establishes a parallel computing mechanism of multi-resolution feature maps through the multi-layer convolution operation, which effectively reduces the information loss caused by down-sampling convolution. Moreover, through dense skip-connecting at the same resolution and up-sampling or down-sampling connection at different resolutions, the low resolution representation of the deep feature maps and the high resolution representation of the shallow feature maps are simultaneously extracted and fully integrated, which is benificial to mine signal multi-level features. Finally, the feature squeeze and excitation module embedded in the decoder is used to adjust the response weights between channels, further improving classification accuracy of proposed model. The proposed HRSENet significantly outperforms existing methods in terms of classification accuracy on the public dataset "Over the Air" in signal-to-noise (SNR) ranging from-2dB to 20dB. The classification accuracy in the proposed model achieves 85.36% and 97.30% at 4dB and 10dB, respectively, with the improvement by 9.71% and 5.82% compared to LWNet. Furthermore, the model also has a moderate computation complexity compared with several state-of-the-art methods.

The development of communication networks is currently undergoing a period of transformation. This paper illustrates this transformation from the growth rate of communication users, network bandwidth, and service revenue. We also analyze the shift in the focus of network technology development from aspects such as information sources, mobile terminals, wireless channels, core networks, edge clouds, data perception, and artificial intelligence. Finally, we briefly outline the new paradigm for network research and development (R&D) in the intelligent era.

Federated semi-supervised learning (FSSL) faces two major challenges: the scarcity of labeled data across clients and the non-independent and identically distributed (Non-IID) nature of data among clients. To address these issues, we propose diffusion model-based data synthesis aided FSSL (DDSA-FSSL), a novel approach that leverages diffusion model (DM) to generate synthetic data, thereby bridging the gap between heterogeneous local data distributions and the global data distribution. In the proposed DDSA-FSSL, each client addresses the scarcity of labeled data by utilizing a federated learning-trained classifier to perform pseudo labeling for unlabeled data. The DM is then collaboratively trained using both labeled and precision-optimized pseudo-labeled data, enabling clients to generate synthetic samples for classes that are absent in their labeled datasets. As a result, the disparity between local and global distributions is reduced and clients can create enriched synthetic datasets that better align with the global data distribution. Extensive experiments on various datasets and Non-IID scenarios demonstrate the effectiveness of DDSA-FSSL, achieving significant performance improvements, such as increasing accuracy from 38.46% to 52.14% on CIFAR-10 datasets with 10% labeled data.

In this paper, a novel wideband 8-element multiple-input and multiple-output (MIMO) antenna based on Booker’s relation is proposed for the fifth generation (5G) handset applications. The 8 antenna elements are arranged symmetrically along the two longer vertical side-edge frames of the handset. Each antenna element is composed of a monopole and a slot radiation structure, in which wideband characteristic covering 3140-5620MHz can be obtained. Note that the L-shaped monopole and the slot can be deemed as complementary counterparts approximatively. Furthermore, the \textit{Z}-parameter of the proposed wideband antenna element is equivalent to the shunt impedance of monopole as well as slot radiator. Based on Booker’s relation, the wideband input impedance characteristic is therein achieved compared with conventional wideband technique such as multi-resonance. Four L-shaped stubs as well as two slots etched on the ground plane are utilized to achieve acceptable isolation performance better than 13 dB, with total efficiency higher than 60\% and envelope correlation coefficients (ECCs) lower than 0.1. The proposed antenna scheme can be a good candidate for 5G handset applications with the advantages of wideband, simple structure, high efficiency, and acceptable isolation performance. Also, the scheme might be a rewarding attempt to promote the Booker’s relation in the application of 5G terminal MIMO antenna designs.

To address the contradiction between the explosive growth of wireless data and the limited spectrum resources, semantic communication has been emerging as a promising communication paradigm. In this paper, we thus design a speech semantic coded communication system, referred to as Deep-STS (i.e., Deep-learning based Speech To Speech), for the low-bandwidth speech communication. Specifically, we first deeply compress the speech data through extracting the textual information from the speech based on the conformer encoder and connectionist temporal classification decoder at the transmitter side of Deep-STS system. In order to facilitate the final speech timbre recovery, we also extract the short-term timbre feature of speech signals only for the starting 2s duration by the long short-term memory network. Then, the Reed-Solomon coding and hybrid automatic repeat request protocol are applied to improve the reliability of transmitting the extracted text and timbre feature over the wireless channel. Third, we reconstruct the speech signal by the mel spectrogram prediction network and vocoder, when the extracted text is received along with the timbre feature at the receiver of Deep-STS system. Finally, we develop the demo system based on the USRP and GNU radio for the performance evaluation of Deep-STS. Numerical results show that the accuracy of text extraction approaches 95%, and the mel cepstral distortion between the recovered speech signal and the original one in the spectrum domain is less than 10. Furthermore, the experimental results show that the proposed Deep-STS system can reduce the total delay of speech communication by 85% on average compared to the G.723 coding at the transmission rate of 5.4 kbps. More importantly, the coding rate of the proposed Deep-STS system is extremely low, only 0.2 kbps for continuous speech communication. It is worth noting that the Deep-STS with lower coding rate can support the low-zero-power speech communication, unveiling a new era in ultra-efficient coded communications.

Physical layer security is an important method to improve the secrecy performance of wireless communication systems. In this paper, we analyze the effect of employing channel correlation to improve security performance in multiple-input multiple-output (MIMO) scenario with antenna selection (AS) scheme. We first derive the analytical expressions of average secrecy capacity (ASC) and secrecy outage probability (SOP) by the first order Marcum Q function. Then, the asymptotic expressions of ASC and SOP in two specific scenarios are further derived. The correctness of analytical and asymptotic expressions is verified by Monte Carlo simulations. The conclusions suggest that the analytical expressions of ASC and SOP are related to the product of transmitting and receiving antennas; increasing the number of antennas is beneficial to ASC and SOP. Besides, when the target rate is set at a low level, strong channel correlation is bad for ASC, but is beneficial to SOP.

The advent of the internet-of-everything era has led to the increased use of mobile edge computing. The rise of artificial intelligence has provided many possibilities for the low-latency task-offloading demands of users, but existing technologies rigidly assume that there is only one task to be offloaded in each time slot at the terminal. In practical scenarios, there are often numerous computing tasks to be executed at the terminal, leading to a cumulative delay for subsequent task offloading. Therefore, the efficient processing of multiple computing tasks on the terminal has become highly challenging. To address the low-latency offloading requirements for multiple computational tasks on terminal devices, we propose a terminal multitask parallel offloading algorithm based on deep reinforcement learning. Specifically, we first establish a mobile edge computing system model consisting of a single edge server and multiple terminal users. We then model the task offloading decision problem as a Markov decision process, and solve this problem using the Dueling Deep-Q Network algorithm to obtain the optimal offloading strategy. Experimental results demonstrate that, under the same constraints, our proposed algorithm reduces the average system latency.

The deployment of multiple intelligent reflecting surfaces (IRSs) in blockage-prone millimeter wave (mmWave) communication networks have garnered considerable attention lately. Despite the remarkably low circuit power consumption per IRS element, the aggregate energy consumption becomes substantial if all elements of an IRS are turned on given a considerable number of IRSs, resulting in lower overall energy efficiency (EE). To tackle this challenge, we propose a flexible and efficient approach that individually controls the status of each IRS element. Specifically, the network EE is maximized by jointly optimizing the associations of base stations (BSs) and user equipments (UEs), transmit beamforming, phase shifts of IRS elements, and the associations of individual IRS elements and UEs. The problem is efficiently addressed in two phases. First, the Gale-Shapley algorithm is applied for BS-UE association, followed by a block coordinate descent-based algorithm that iteratively solves the subproblems related to active beamforming, phase shifts, and element-UE associations. To reduce the tremendous dimensionality of optimization variables introduced by element-UE associations in large-scale IRS networks, we introduce an efficient algorithm to solve the associations between IRS elements and UEs. Numerical results show that the proposed elementwise control scheme improves EE by 34.24% compared to the network with IRS-all-on scheme.

The utilization of millimeter-wave frequencies and cognitive radio (CR) are promising ways to increase the spectral efficiency of wireless communication systems. However, conventional CR spectrum sensing techniques entail sampling the received signal at a Nyquist rate, and they are not viable for wideband signals due to their high cost. This paper expounds on how sub-Nyquist sampling in conjunction with deep learning can be leveraged to remove this limitation. To this end, we propose a multi-task learning (MTL) framework using convolutional neural networks for the joint inference of the underlying narrowband signal number, their modulation scheme, and their location in a wideband spectrum. We demonstrate the effectiveness of the proposed framework for real-world millimeter-wave wideband signals collected by physical devices, exhibiting a $91.7 \%$ accuracy in the joint inference task when considering up to two narrowband signals over a wideband spectrum. Ultimately, the proposed data-driven approach enables on-the-fly wideband spectrum sensing, combining accuracy, and computational efficiency, which are indispensable for CR and opportunistic networking.

Applying non-orthogonal multiple access (NOMA) to the mobile edge computing (MEC) network supported by unmanned aerial vehicles (UAVs) can improve spectral efficiency and achieve massive user access on the basis of solving computing resource constraints and coverage problems. However, the UAV-enabled network has a serious risk of information leakage on account of the openness of wireless channel. This paper considers a UAV-MEC secure network based on NOMA technology, which aims to minimize the UAV energy consumption. To achieve the purpose while meeting the security and users' latency requirements, we formulate an optimization problem that jointly optimizes the UAV trajectory and the allocation of network resources. Given that the original problem is non-convex and multivariate coupled, we proposed an effective algorithm to decouple the non-convex problem into independent user relation coefficients and subproblems based on successive convex approximation (SCA) and block coordinate descent (BCD). The simulation results showcase the performance of our optimization scheme across various parameter settings and confirm its superiority over other benchmarks with respect to energy consumption.

The rapid advent in artificial intelligence and big data has revolutionized the dynamic requirement in the demands of the computing resource for executing specific tasks in the cloud environment. The process of achieving autonomic resource management is identified to be a herculean task due to its huge distributed and heterogeneous environment. Moreover, the cloud network needs to provide autonomic resource management and deliver potential services to the clients by complying with the requirements of Quality-of-Service (QoS) without impacting the Service Level Agreements (SLAs). However, the existing autonomic cloud resource managing frameworks are not capable in handling the resources of the cloud with its dynamic requirements. In this paper, Coot Bird Behavior Model-based Workload Aware Autonomic Resource Management Scheme (CBBM-WARMS) is proposed for handling the dynamic requirements of cloud resources through the estimation of workload that need to be policed by the cloud environment. This CBBM-WARMS initially adopted the algorithm of adaptive density peak clustering for workloads clustering of the cloud. Then, it utilized the fuzzy logic during the process of workload scheduling for achieving the determining the availability of cloud resources. It further used CBBM for potential Virtual Machine (VM) deployment that attributes towards the provision of optimal resources. It is proposed with the capability of achieving optimal QoS with minimized time, energy consumption, SLA cost and SLA violation. The experimental validation of the proposed CBBM-WARMS confirms minimized SLA cost of 19.21\% and reduced SLA violation rate of 18.74\%, better than the compared autonomic cloud resource managing frameworks.

The intelligent operation management of distribution services is crucial for the stability of power systems. Integrating the large language model (LLM) with 6G edge intelligence provides customized management solutions. However, the adverse effects of false data injection (FDI) attacks on the performance of LLMs cannot be overlooked. Therefore, we propose an FDI attack detection and LLM-assisted resource allocation algorithm for 6G edge intelligence-empowered distribution power grids. First, we formulate a resource allocation optimization problem. The objective is to minimize the weighted sum of the global loss function and total LLM fine-tuning delay under constraints of long-term privacy entropy and energy consumption. Then, we decouple it based on virtual queues. We utilize an LLM-assisted deep Q network (DQN) to learn the resource allocation strategy and design an FDI attack detection mechanism to ensure that fine-tuning remains on the correct path. Simulations demonstrate that the proposed algorithm has excellent performance in convergence, delay, and security.

Puncturing has been recognized as a promising technology to cope with the coexistence problem of enhanced mobile broadband (eMBB) and ultra-reliable low latency communications (URLLC) traffic. However, the steady performance of eMBB traffic while meeting the requirements of URLLC traffic with puncturing is a major challenge in some realistic scenarios. In this paper, we pay attention to the timely and energy-efficient processing for eMBB traffic in the industrial Internet of Things (IIoT), where mobile edge computing (MEC) is employed for data processing. Specifically, the performance of eMBB traffic and URLLC traffic in a MEC-based IIoT system is ensured by setting the threshold of tolerable delay and outage probability, respectively. Furthermore, considering the limited energy supply, an energy minimization problem of eMBB device is formulated under the above constraints, by jointly optimizing the resource blocks (RBs) punctured by URLLC traffic, data offloading and transmit power of eMBB device. With Markov's inequality, the problem is reformulated by transforming the probabilistic outage constraint into a deterministic constraint. Meanwhile, an iterative energy minimization algorithm (IEMA) is proposed. Simulation results demonstrate that our algorithm has a significant reduction in the energy consumption for eMBB device and achieves a better overall effect compared to several benchmarks.

Integrated sensing and communication (ISAC) is considered an effective technique to solve spectrum congestion in the future. In this paper, we consider a hybrid reconfigurable intelligent surface (RIS)-assisted downlink ISAC system that simultaneously serves multiple single-antenna communication users and senses multiple targets. Hybrid RIS differs from fully passive RIS in that it is composed of both active and passive elements, with the active elements having the effect of amplifying the signal in addition to phase-shifting. We maximize the achievable sum rate of communication users by collaboratively improving the beamforming matrix at the dual function base station (DFBS) and the phase-shifting matrix of the hybrid RIS, subject to the transmit power constraint at the DFBS, the signal-to-interference-plus-noise-ratio (SINR) constraint of the radar echo signal and the RIS constraint are satisfied at the same time. The built-in RIS-assisted ISAC design problem model is significantly non-convex due to the fractional objective function of this optimization problem and the coupling of the optimization variables in the objective function and constraints. As a result, we provide an effective alternating optimization approach based on fractional programming (FP) with block coordinate descent (BCD) to solve the optimization variables. Results from simulations show that the hybrid RIS-assisted ISAC system outperforms the other benchmark solutions.

Codebooks have been indispensable for wireless communication standard since the first release of the Long-Term Evolution in 2009. They offer an efficient way to acquire the channel state information (CSI) for multiple antenna systems. Nowadays, a codebook is not limited to a set of pre-defined precoders, it refers to a CSI feedback framework, which is more and more sophisticated. In this paper, we review the codebooks in 5G New Radio (NR) standards. The codebook timeline and the evolution trend are shown. Each codebook is elaborated with its motivation, the corresponding feedback mechanism, and the format of the precoding matrix indicator. Some insights are given to help grasp the underlying reasons and intuitions of these codebooks. Finally, we point out some unresolved challenges of the codebooks for future evolution of the standards. In general, this paper provides a comprehensive review of the codebooks in 5G NR and aims to help researchers understand the CSI feedback schemes from a standard and industrial perspective.

In recent years, deep learning has been gradually used in communication physical layer receivers and has achieved excellent performance. In this paper, we employ deep learning to establish covert communication systems, enabling the transmission of signals through high-power signals present in the prevailing environment while maintaining covertness, and propose a convolutional neural network (CNN) based model for covert communication receivers, namely DeepCCR. This model leverages CNN to execute the signal separation and recovery tasks commonly performed by traditional receivers. It enables the direct recovery of covert information from the received signal. The simulation results show that the proposed DeepCCR exhibits significant advantages in bit error rate (BER) compared to traditional receivers in the face of noise and multipath fading. We verify the covert performance of the covert method proposed in this paper using the maximum-minimum eigenvalue ratio-based method and the frequency domain entropy-based method. The results indicate that this method has excellent covert performance. We also evaluate the mutual influence between covert signals and opportunity signals, indicating that using opportunity signals as cover can cause certain performance losses to covert signals. When the interference-to-signal power ratio (ISR) is large, the impact of covert signals on opportunity signals is minimal.

With the explosive growth of high-definition video streaming data, a substantial increase in network traffic has ensued. The emergency of mobile edge caching (MEC) can not only alleviate the burden on core network, but also significantly improve user experience. Integrating with the MEC and satellite networks, the network is empowered popular content ubiquitously and seamlessly. Addressing the research gap between multilayer satellite networks and MEC, we study the caching placement problem in this paper. Initially, we introduce a three-layer distributed network caching management architecture designed for efficient and flexible handling of large-scale networks. Considering the constraint on satellite capacity and content propagation delay, the cache placement problem is then formulated and transformed into a markov decision process (MDP), where the content coded caching mechanism is utilized to promote the efficiency of content delivery. Furthermore, a new generic metric, content delivery cost, is proposed to elaborate the performance of caching decision in large-scale networks. Then, we introduce a graph convolutional network (GCN)-based multi-agent advantage actor-critic (A2C) algorithm to optimize the caching decision. Finally, extensive simulations are conducted to evaluate the proposed algorithm in terms of content delivery cost and transferability.

Frequent extreme disasters have led to frequent large-scale power outages in recent years. To quickly restore power, it is necessary to understand the damage information of the distribution network accurately. However, the public network communication system is easily damaged after disasters, causing the operation center to lose control of the distribution network. In this paper, we considered using satellites to transmit the distribution network data and focus on the resource scheduling problem of the satellite emergency communication system for the distribution network. Specifically, this paper first formulates the satellite beam-pointing problem and the access-channel joint resource allocation problem. Then, this paper proposes the Priority-based Beam-pointing and Access-Channel joint optimization algorithm (PBAC), which uses convex optimization theory to solve the satellite beam pointing problem, and adopts the block coordinate descent method, Lagrangian dual method, and a greedy algorithm to solve the access-channel joint resource allocation problem, thereby obtaining the optimal resource scheduling scheme for the satellite network. Finally, this paper conducts comparative experiments with existing methods to verify the effectiveness of the proposed methods. The results show that the total weighted transmitted data of the proposed algorithm is increased by about 19.29$\sim$26.29% compared with other algorithms.