Integrated sensing and communication (ISAC) emerges as a transformative paradigm for enabling future wireless networks by jointly supporting high-rate communication and precise environmental perception. In this paper, we investigate a robust beamforming framework tailored for monostatic ISAC systems in near-field channels, where the impact of spherical wavefront effects is significant and cannot be neglected. In particular, we formulate a minimum mean squared error (MMSE)-driven beamforming optimization problem that strikes an effective balance between sensing accuracy and communication quality, while considering both power and outage constraints and explicitly accounting for channel estimation errors. To address the inherent non-convexity arising from coupled sensing-communication constraints and uncertainties due to channel errors, a semidefinite relaxation (SDR)-based algorithm leveraging sphere bounding techniques is developed to acquire a favorable suboptimal solution, with polynomial-time complexity. Furthermore, extensive simulations are conducted to rigorously validate the proposed methodology under a variety of practical conditions. Our results demonstrate that the proposed design reduces sensing mean squared error (MSE) by up to 3.8 dB and improves achievable communication rate by 33.4% over non-robust baselines under imperfect channel state information (CSI). Furthermore, compared to conventional far-field schemes, our design achieves up to 1.6 dB lower MSE and 28.0% higher rate in millimeter-wave (mmWave) scenarios, and 2.5 dB lower MSE and 31.7% rate gain in terahertz (THz) scenarios at 10 dB communication signal-to-interference-plus-noise ratio (SINR). To further underscore the practical significance of our approach, the experimental results reveal critical insights into the delicate balance between communication and sensing performance in ISAC systems under real-world conditions. Specifically, our findings emphasize the importance of robust beamforming techniques that optimize resource allocation to mitigate the adverse effects of channel estimation errors, particularly in high-frequency regimes such as mmWave and THz. These insights are vital for the design of adaptive ISAC systems, where trade-offs between sensing precision and communication reliability must be dynamically managed to meet stringent performance requirements in next-generation wireless networks.

In this paper, we contribute to the beamforming design problem with imperfect channel state information in a monostatic integrated sensing and communication (ISAC) system. We propose a robust waveform design framework tailored for monostatic ISAC systems, incorporating a channel random error vector to account for imperfections in the communication channels, and addressing clutter interference in radar sensing received waveforms. Next, we derive expressions for target estimation performance via utilizing the minimum mean squared error criterion and the Cramer-Rao bound, which serve as objective functions for our beamforming design. Additionally, we introduce signal-to-interference-plus-noise ratio outage probability constraints and power constraints, formulating two different beamforming optimization problems. Utilizing semi-definite programming techniques, we reformulate these optimization problems into convex optimization problems and resolve them via a convex toolbox. Finally, our simulation results achieves 45% sensing gain and 37% communication gain at an SINR threshold of 20 dB compared with the baseline.

Satellite-Air-Ground Integrated Networks (SAGINs) provide ubiquitous connectivity, global coverage and flexible deployment convenience for terrestrial users, which are beneficial to optimizing network resources and achieving task scheduling functions. However, the corresponding SAGIN nodes are dynamic and complex, leading to intractable multi-modal features and high network latency when graph model is used for collaborative task completion. Therefore, we establish a directed SAGIN federated graph model to minimize the total transmission latency via computation offloading and quantization methods. Specifically, we utilize the federated graph learning to process the time-varying graph nodes and sizes, and then perform deep reinforcement learning (DRL) to optimize the computation and quantization resources. Moreover, federated learning is convoked to accelerate the convergence speed. Finally, our simulation results show that the proposed method outperforms some advanced benchmarks in terms of convergence performance and transmission latency for multiple data modals.

The large number of antennas in extremely large aperture array (ELAA) systems shifts the propagation regime of signals in wireless communication systems towards near-field spherical wave propagation, from beamforming to beamfocusing. The design of the two-dimensional beam codebook that contains both the angular and distance domains is challenging. To address this issue, we propose a reconfigurable intelligent surface (RIS)-assisted near-field beam training based on a novel multi-attention algorithm, which provides a fine-grained codebook with enhanced spatial resolution. Specifically, we transform the beam selection task into a location detection process, enabling more effective beam search. Experimental results unveil that the proposed method achieves beam selection accuracy up to 97% at signal-to-noise ratio (SNR) of 20 dB, and improves 10% over the baseline method at different SNRs.

The next generation mobile communication systems will experience huge transformation for multiple applications, which can provide pervasive intelligence and release more network resources for multiple terrestrial users. Moreover, digital twin (DT) technique helps each terrestrial user enable the mapping from physical world to digital space for the sake of reducing transmission latency. Thus, the integration between the terrestrial network and DT can expedite the computation offloading. Nevertheless, time-varying channel gains and dynamic UAV locations severely hinder better quality of service. In this paper, we envision a UAV-DT integrated task scheduling model to maximize the processed number of bits while minimizing the privacy protection overhead, which can further reduce the channel interference. Based on long-term task queues, we present a Lyapunov stability theory based multi-agent federated reinforcement learning (MAFRL) algorithm to optimize the CPU cycle frequency, transmission power and block size, which facilitate the integration between the communication, computation and block resources. Furthermore, we propose a blockchain-based verification mechanism to strengthen the privacy protection, and then demonstrate the performance upper bounds in terms of convergent task queues. Finally, massive simulation results show that the proposed MAFRL framework has approximately 1.7% performance gains in terms of the processed number of bits compared with state-of-the-art baseline methods.

Space-air-ground (SAG) integrated heterogenous networks can provide pervasive intelligence services for various ground users (GUs). The network can help cellular networks release network resources and alleviate congestion pressure. Moreover, one important application of the network is that digital twin (DT) can enable nearly-instant wireless connectivity and highly-reliable data mapping from physical systems to digital world in a real-time fashion. The integration of SAG and DT (SAG-DT) reduces the gap between data analysis and physical status, which can further realize robust edge intelligence services. However, the random computation task arrival, time-varying channel gains, and the lack of mutual trust among ground GUs hinder better quality of service in the promising SAG-DT network. In this paper, we envision a SAG-DT integrated blockchain model to transfer the task data to the aerial network, and then perform the computation offloading, energy harvesting and privacy protection. Moreover, we propose a Lyapunov-aided multi-agent deep federated reinforcement learning (MADFRL) algorithm framework to optimize the CPU cycle frequency, the size of block, the number of DTs, and harvested energy to minimize the execution costs and privacy overhead. Extensive performance analyses indicate that the MADFRL algorithm framework can strengthen the data privacy via blockchain verification mechanism and approaches the optimal performance on the basis of lower computation complexity. Finally, simulation results corroborate that the proposed Lyapunov-aided MADFRL algorithm is superior to advanced benchmarks in terms of execution costs, task processing quantities and privacy overhead.

Satellite-ground twin networks (SGTNs) are regarded as a promising service paradigm, which can provide mega access services and powerful computation offloading capabilities via cloud-fog automation functions. Specifically, cloud-fog automation technologies are collaboratively leveraged to enable dense connectivity, pervasive computing, and intelligent control in terrestrial industrial cyber-physical systems, whose system-level privacy security can be strengthened via blockchain based consensus protocol. Moreover, digital twin (DT) can shorten the gap between physical unities and digital space to enable instant data mapping in SGTNs environments. However, complex multi-modal network environments, such as stochastic task size, dynamic low earth orbit location, and time-varying channel gains, hinder better performance metrics in terms of energy consumption, throughput and privacy overhead. Hence, we establish a SGTN integrated cloud-fog automation model to transfer task data to low earth orbit satellites, and then execute broad communication access, powerful computation offloading, and efficient twin control. Next, we propose a Lyapunov stability theory based multi-modal federated learning (LST-MMFL) method to optimize the battery energy, the size of block, computation frequency, and the number of twin control for minimizing the total energy consumption and privacy overhead. Furthermore, we design a novel blockchain based transaction verification protocol to strengthen privacy security, derive performance upper bounds of SGTN model, and fulfill the long-term average task as well as energy queue constraints. Finally, massive simulation results show that the proposed LST-MMFL algorithm outperforms existing state-of-the-art benchmarks in line with energy consumption, available battery level, networked control and privacy protection overhead.

Satellite-Ground Integrated Networks (SGINs) are promising network architectures that can help reduce the load on terrestrial networks, provide mega-access capabilities and intensive task offloading functions. However, traditional resource management methods are difficult to apply directly into SGINs due to their multi-layered, heterogeneous and dynamic three-dimensional characteristics. In addition, massive multi-modal and multi-task information hinders better service performance in SGINs. Therefore, we design a multi-task integrated computation offloading model to process complex multi-modal network information, such as time-varying channel gains and dynamic Low Earth Orbit (LEO) locations, which can efficiently improve data transmission rate and privacy level. Furthermore, we propose three multi-modal based learning methods, such as centralized actor-critic (C-AC) algorithm, distributed multi-agent deep deterministic policy gradient (D-MADDPG) algorithm, and quantization-based federated learning (Q-FL) algorithm for computation-intensive, latency-critical and privacy-preserving tasks, which can further optimize the local execution or LEO offloading ratio, CPU cycle frequency and transmission power. Meanwhile, we demonstrate the quantization error upper bound between the optimal solution and the quantization scheme through massive mathematical derivations. Finally, extensive simulation results show that the proposed multi-modal based learning methods have better performance gains in terms of model convergence performance, quantization metrics, data transmission rate and number of bits processed.

Satellite-ground integrated heterogeneous networks can relieve network congestion, release network resources and provide ubiquitous intelligence services for terrestrial users. Furthermore, digital twin technology can enable nearly-instant data mapping from the physical world to digital systems. The integration between satellite-ground integrated heterogeneous networks and digital twin alleviates the gap between data analyses and physical unities. However, the current challenges, such as the pricing policy, the stochastic task arrivals, the time-varying satellite locations, mutual channel interference, and resource scheduling mechanisms between the users and cloud servers, severely affect the improvement of quality of service. Hence, we establish a blockchain-aided Stackelberg game model for maximizing the pricing profits and network throughput in terms of minimizing privacy overhead, which is able to perform computation offloading, decrease channel interference, and improve privacy protection. Due to the long-term task queue in Stackelberg model, we propose a Lyapunov stability theory-based model-agnostic meta-learning aided multi-agent deep federated reinforcement learning framework to transfer the long-term task queue into the single time slot, and then optimize the central processing unit frequency, channel selection, task-offloading decision, block size, and cloud server price, which facilitate the integration of communication, computation, and block resources. Subsequently, several performance analyses show that the proposed learning framework can strengthen the privacy protection, approach the optimal time average function, and fulfill the long-term average queue size via lower computational complexity. Finally, our simulation results indicate that the proposed learning framework is superior to the existing baseline methods in terms of network throughput, channel interference, cloud server profits, and privacy overhead.

Satellite-Ground integrated networks (SGINs) are regarded as promising network architecture, which can provide global coverage, large broadband and mega access services for massive terrestrial users. Furthermore, it is beneficial to reducing network congestion, releasing network resources and achieving computation offloading functions. However, the SGIN graph structure is time-varying and highly complex, lack of fixed node orders or reference nodes, which result in dynamic multi-modal features. Hence, we consider a SGIN directed graph model to minimize the total latency while improving the model prediction accuracy, and then perform the computation offloading and quantization schemes. Specifically, we envision a spatial graph convolutional neural network framework to adapt to the dynamic SGIN graph nodes and size, and then propose a centrally deep reinforcement learning aided multi-node federated learning (CDRFL) framework to optimize the CPU cycle frequency, transmission bandwidth and the number of quantization bits to accelerate the convergence round. Extensive theoretical analyses verify the graph permutation property between SGIN graph structure and optimization problems, and demonstrate the upper bound of quantization error via massive mathematical derivation. Finally, the experimental results indicate that the proposed CDRFL framework outperforms some existing benchmarks with reference to FL convergence analysis, average latency and transmission energy consumption for all independent identically distribution (IID) and non-IID data.

The satellite-ground (SG) integrated networks are regarded as a promising network structure, which can provide ubiquitous intelligence and pervasive services for multiple ground users. Moreover, digital twin (DT) can drive real-time data mapping and wireless access from usual physical utilities to digital units. Therefore, the fusion of SG and DT can decrease the gap between real-time data analysis and physical system states, which can help boost SG-DT edge intelligence paradigms. Nevertheless, the unexpected task arrivals, time-varying channel gains, and distrust among ground devices cause the network service performance degradation. Hence, in this paper, we propose a privacy-assisted blockchain computation offloading model to shine upon original tasks to the corresponding aerial platforms, and then orchestrate the task scheduling, resource allocation, and privacy protection. Additionally, we envision a Lyapunov stability theory-based multi-agent federated reinforcement learning (LST-MAFRL) algorithm to further resolve the CPU cycle frequency, the size of each blockchain, the number of DTs, and related harvested solar energy to minimize the execution energy consumption and privacy time overhead. Finally, extensive simulation results indicate that the proposed LST-MAFRL algorithm framework outperforms some state-of-the-art benchmarks for the sake of execution energy efficiency, processed bit quantities, and privacy time overhead.

The space-air-ground (SAG) integrated networks will play a major role in the sixth generation (6G) mobile networks, which will provide global coverage, full connection and pervasive intelligence services for multiple ground Internet of Things (IoT) devices. Moreover, massive computing tasks can be either performed by local devices, or offloaded to edge servers, such as low orbit satellites, high altitude platforms (HAPs) and remote base stations. Nevertheless, the joint computation and communication resource allocation solutions are becoming challenging due to the large-scale state space, time-varying network scenarios, and limited battery capacity. In this paper, we propose a SAG-integrated three-layer heterogenous network model to maximize the sum-rate of ground IoT devices, which further enhances the deep integration of communication and computation resources. Additionally, we develop a Lyapunov-assisted multi-agent proximal policy optimization algorithm to process the task scheduling, HAP selection, battery harvesting, and CPU cycle frequency optimization. Extensive simulation results corroborate that the proposed method has superior performance gains in terms of the remaining battery capacity, energy consumption, and maximum average sum-rate compared with the state-of-the-art baselines.

With the introduction of the concept of 6G ubiquitous intelligence, a network infrastructure that can provide ubiquitous intelligence services has been expected widely. Among all the promising technologies, satellite-terrestrial Internet of Things (IoT) networks are one of the key enablers of the implementation of 6G IoT, offering multiple services for remote IoT applications, such as disaster rescue and remote area monitoring in global coverage. As the satellite-terrestrial link is vulnerable to eavesdropping which can greatly damage users' privacy, implementing information security protection for reliable communication is extremely necessary. Therefore, we introduce the security service provider to offer encryption services for remote IoT users. However, higher security configuration can lead to higher overhead for the service provider and higher prices for users. Thus, to find the optimal service price and encryption security configuration, this paper models the interaction between IoT users and the service provider as a Stackelberg game. To achieve the Nash equilibrium, we formulate the decision-making process as a Markov Decision Process. Then, we apply the ‘Wolf-PUC’ multi-agent reinforcement learning algorithm to learn the optimal security configuration and pricing strategies. Finally, the feasibility and performance of the algorithm are demonstrated with our simulation results.

The sixth generation wireless communication networks (6G) are anticipated to bring a disruptive innovation on multiple scenarios, where deep edge networks (DENs) turn into a vital network structure on vertical industrial paradigms, including the combination of communication, computing and caching (3C). In this paper, we present the DENs scene to facilitate the deep convergence of computing and communication resources. More specifically, we formulate the optimization problem in terms of energy consumption and latency in order to minimize the total agents overhead. At the same time, for the sake of executing tasks and alleviating interference among different edge networks and high-dynamic network environments, we propose a CPU cycle frequency aided multi-agent deep deterministic policy gradient (C-MADDPG) algorithm framework to optimize the task scheduling, transmission power, CPU cycle frequency and mutual interference from multiple channels to obtain the optimal overhead. Finally, extensive simulation and experimental results demonstrate that our proposed C-MADDPG algorithm has better performance gain in term of execution overhead for different network parameters.