The advent of the sixth-generation (6G) wireless networks, enhanced by artificial intelligence, promises ubiquitous connectivity through Low Earth Orbit (LEO) satellites. These satellites are capable of collecting vast amounts of geographically diverse and real-time data, which can be immensely valuable for training intelligent models. However, limited inter-satellite communication and data privacy constraints hinder data collection on a single server for training. Therefore, we propose SemSpaceFL, a novel hierarchical federated learning (HFL) framework for LEO satellite networks, with integrated semantic communication capabilities. Our framework introduces a two-tier aggregation architecture where satellite models are first aggregated at regional gateways before final consolidation at a cloud server, which explicitly accounts for satellite mobility patterns and energy constraints. The key innovation lies in our novel aggregation approach, which dynamically adjusts the contribution of each satellite based on its trajectory and association with different gateways, which ensures stable model convergence despite the highly dynamic nature of LEO constellations. To further enhance communication efficiency, we incorporate semantic encoding-decoding techniques trained through the proposed HFL framework, which enables intelligent data compression while maintaining signal integrity. Our experimental results demonstrate that the proposed aggregation strategy achieves superior performance and faster convergence compared to existing benchmarks, while effectively managing the challenges of satellite mobility and energy limitations in dynamic LEO networks.

Deep Joint Source-Channel Coding (Deep-JSCC) has emerged as a promising semantic communication approach for wireless image transmission by jointly optimizing source and channel coding using deep learning techniques. However, traditional Deep-JSCC architectures employ fixed encoder-decoder structures, limiting their adaptability to varying device capabilities, real-time performance optimization, power constraints and channel conditions. To address these limitations, we propose DD-JSCC: Dynamic Deep Joint Source-Channel Coding for Semantic Communications, a novel encoder-decoder architecture designed for semantic communication systems. Unlike traditional Deep-JSCC models, DD-JSCC is flexible for dynamically adjusting its layer structures in real-time based on transmitter and receiver capabilities, power constraints, compression ratios, and current channel conditions. This adaptability is achieved through a hierarchical layer activation mechanism combined with implicit regularization via sequential randomized training, effectively reducing combinatorial complexity, preventing overfitting, and ensuring consistent feature representations across varying configurations. Simulation results demonstrate that DDJSCC enhances the performance of image reconstruction in semantic communications, achieving up to 2 dB improvement in Peak Signal-to-Noise Ratio (PSNR) over fixed Deep-JSCC architectures, while reducing training costs by over 40%. The proposed unified framework eliminates the need for multiple specialized models, significantly reducing training complexity and deployment overhead.

Low Earth orbit (LEO) satellites are capable of gathering abundant Earth observation data (EOD) to enable different Internet of Things (IoT) applications. However, to accomplish an effective EOD processing mechanism, it is imperative to investigate: 1) the challenge of processing the observed data without transmitting those large-size data to the ground because the connection between the satellites and the ground stations is intermittent, and 2) the challenge of processing the non-independent and identically distributed (non-IID) satellite data. In this paper, to cope with those challenges, we propose an orbit-based spectral clustering-assisted clustered federated self-knowledge distillation (OSC-FSKD) approach for each orbit of an LEO satellite constellation, which retains the advantage of FL that the observed data does not need to be sent to the ground. Specifically, we introduce normalized Laplacian-based spectral clustering (NLSC) into federated learning (FL) to create clustered FL in each round to address the challenge resulting from non-IID data. Particularly, NLSC is adopted to dynamically group clients into several clusters based on cosine similarities calculated by model updates. In addition, self-knowledge distillation is utilized to construct each local client, where the most recent updated local model is used to guide current local model training. Experiments demonstrate that the observation accuracy obtained by the proposed method is separately$1. 01\times, 2.15\times, 1.10\times$, and$1.03\times$higher than that of pFedSD, FedProx, FedAU, and FedALA approaches using the SAT4 dataset. The proposed method also shows superiority when using other datasets.

Non-orthogonal multiple access (NOMA) enables multiple users to share the same frequency band, and simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) provides 360-degree full-space coverage, optimizing both transmission and reflection for improved network performance and dynamic control of the indoor environment. However, deploying STAR-RIS indoors presents challenges in interference mitigation, power consumption, and real-time configuration. In this work, a novel network architecture utilizing multiple access points (APs), STAR-RISs, and NOMA is proposed for indoor communication. To address these, we formulate an optimization problem involving user assignment, access point (AP) beamforming, and STAR-RIS phase control. A decomposition approach is used to solve the complex problem efficiently, employing a many-to-one matching algorithm for user-AP assignment and K-means clustering for resource management. Additionally, multi-agent deep reinforcement learning (MADRL) is leveraged to optimize the control of the STAR-RIS. Within the proposed MADRL framework, a novel approach is introduced in which each decision variable acts as an independent agent, enabling collaborative learning and decision making. The MADRL framework is enhanced by incorporating convex approximation (CA), which accelerates policy learning through suboptimal solutions from successive convex approximation (SCA), leading to faster adaptation and convergence. Simulations demonstrate significant improvements in network utility compared to baseline approaches.

Multi-access edge computing (MEC)-enabled integrated space-air-ground (SAG) networks have drawn much attention recently, as they can provide communication and computing services to wireless devices in areas that lack terrestrial base stations (TBSs). Leveraging the ample bandwidth in the terahertz (THz) spectrum, in this paper, we propose MEC-enabled integrated SAG networks with collaboration among unmanned aerial vehicles (UAVs). We then formulate the problem of minimizing the energy consumption of devices and UAVs in the proposed MEC-enabled integrated SAG networks by optimizing tasks offloading decisions, THz sub-bands assignment, transmit power control, and UAVs deployment. The formulated problem is a mixed-integer nonlinear programming (MILP) problem with a non-convex structure, which is challenging to solve. We thus propose a block coordinate descent (BCD) approach to decompose the problem into four sub-problems: 1) device task offloading decision problem, 2) THz sub-band assignment and power control problem, 3) UAV deployment problem, and 4) UAV task offloading decision problem. We then propose to use a matching game, concave-convex procedure (CCP) method, successive convex approximation (SCA), and block successive upper-bound minimization (BSUM) approaches for solving the individual subproblems. Finally, extensive simulations are performed to demonstrate the effectiveness of our proposed algorithm.

The 6G wireless communication networks need an intelligent networking system to meet the ever-increasing de-mands of various applications and mobile devices to ensure power savings, energy efficiency (EE), high integration of devices, and mass connection. To achieve these aims, an artificial intelligence (AI)-based holographic MIMO (HMIMO)-aided cell-free (CF) network is suggested to allocate desired power for beamforming by activating the required number of grids from the serving HMIMOs for serving the users. An optimization problem is developed to ensure effective power allocation that maximizes the EE of the system. A Transformer-based AI framework is proposed to solve the formulated NP-hard problem that distributes desired power for serving the users by activating the required number of grids from the required number of serving HMIMOs in the CF network. Finally, simulation results represent that the proposed power allocation framework outperforms the gated recurrent unit and long short-term memory-based mechanisms, achieving a combined power savings of 12.5% and 4.06%, and a combined EE improvement of 14.68% and 8.93%, correspondingly. Therefore, our suggested AI-based framework guarantees effective power allocation for beamforming to serve the users.

Urban air Mobility (UAM) has been conceived as a new form of transportation. UAM ultimately aims to operate unmanned, so it needs to select its trajectory and periodically send its status to the base station (BS). As an status indicator, the age of information (AoI) signifies the freshness of the information, and it is crucial for applications like real-time control systems. In this article, we address two main challenges: optimizing the UAM’s trajectory and updating the AoI between the UAM and the BS. We formulate an algorithm to maximize the energy efficiency of each UAM’s trajectory and jointly minimize the AoI cycle. As a complicated and non-convex problem, we approach proximal policy optimization (PPO) as our solution in this paper. Experiment results show that our proposed method outperformed the direct trajectory baseline in similar energy efficiency but achieved 46% increased efficiency in average AoI.

To increase the quality of the 6G / B5G network, conventional cellular networks based on terrestrial base stations are geographically and economically restricted. Meanwhile, Non-Orthogonal Multiple Access (NOMA) allows multiple users to share the same resources, which improves the spectral efficiency of the system and has the advantage of supporting a larger number of users. Additionally, by intelligently manipulating the phase and amplitude of both the reflected and transmitted signals, Simultaneously Transmitting and Reflecting RISs (STAR-RISs) can achieve improved coverage, increased spectral efficiency, and enhanced communication reliability. However, STAR-RISs must simultaneously optimize the amplitude and phase shift corresponding to reflection and transmission, which makes existing terrestrial networks more complicated and is considered a major challenge. Motivated by the above, we study the joint user pairing for NOMA and the beamforming design of Multi-STAR-RISs in an indoor environment. Then, we formulate the optimization problem with the objective of maximizing the total throughput of mobile users (MUs) by jointly optimizing the decoding order, user pairing, active beamforming, and passive beamforming. However, the formulated problem is a mixed-integer non-linear programming (MINLP). To address this challenge, we first introduce the decoding order for NOMA networks. Next, we decompose the original problem into two subproblems, namely: 1) MU pairing and 2) Beamforming optimization under the optimal decoding order. For the first subproblem, we employ correlation-based K-means clustering to solve the user pairing problem. Then, to jointly deal with beamforming vector optimizations, we propose Multi-Agent Proximal Policy Optimization (MAPPO), which can make quick decisions in the given environment owing to its low complexity. Finally, simulation results prove that our proposed MAPPO algorithm is superior to Proximal Policy Optimization (PPO) and Advanced Actor-Critic (A2C) by a maximum of 1% and 6%, respectively. Furthermore, the proposed algorithm converges 1.5 times faster than the typical PPO algorithm.

In the rapidly advancing landscape of 6G wireless communication, beamforming plays a crucial role especially with the utilization of millimeter-wave and terahertz frequency bands being pivotal for achieving ultra-high data rates. Despite their promise, these bands present a significant challenge due to the beam training overheads required for precise beamforming, particularly in high-mobility applications like intelligent transportation systems and emerging virtual reality platforms such as the metaverse. While initial deep learning models mitigates the beam training overheads, their performance is compromised due to sensitivity to environmental and lighting conditions, revealing a critical gap in robustness. To address this limitation, this paper proposed a semantic-based method specifically designed to enhance the robustness of beamforming. Utilizing the cutting-edge You Only Look Once version 8 (YOLOv8) algorithm, semantic data from RGB camera images has been extracted to significantly improve the system’s adaptability across a range of environmental conditions. Further, to complement the beam management a novel approach is proposed for the identification of target vehicle by employing K-means clustering in conjunction with the GPS data of the target vehicle. For maintaining the ultra reliable low latency communication (URLLC) a lightweight model has been used to predict the optimal beamforming index. The efficacy of our proposed model is empirically substantiated through rigorous experimental trials in real-world 6G environment, demonstrating significant improvements in average received power ranging from 6.49% to 38.27%, compared to the baselines.

Satellite systems face a significant challenge in effectively utilizing limited communication resources to meet the demands of ground network traffic, characterized by asymmetrical spatial distribution and time-varying characteristics. Moreover, the coverage range and signal transmission distance of low Earth orbit (LEO) satellites are restricted by notable propagation attenuation, molecular absorption, and space losses in sub-terahertz (THz) frequencies. This paper introduces a novel approach to maximize LEO satellite coverage by leveraging reconfigurable intelligent surface (RIS) within 6G sub-THz networks. Optimization objectives include improving end-to-end (E2E) data rate, optimizing satellite-remote user equipment (RUE) associations, data packet routing within satellite constellations, RIS phase shift, and ground base station (GBS) transmit power (i.e., active beamforming). The formulated joint optimization problem poses significant challenges because of its time-varying environment, non-convex characteristics, and NP-hard complexity. To address these challenges, we propose a block coordinate descent (BCD) algorithm that integrates balanced K-means clustering, multi-agent proximal policy optimization (MAPPO) deep reinforcement learning (DRL), and whale optimization algorithm (WOA) techniques. The performance of the proposed approach is demonstrated through comprehensive simulation results, demonstrating its superiority over existing baseline methods in the literature.

The proliferation of intelligent transportation systems (ITS) has led to increasing demand for diverse network applications. However, conventional terrestrial access networks (TANs) are inadequate in accommodating various applications for remote ITS nodes, i.e., airplanes and ships. In contrast, satellite access networks (SANs) offer supplementary support for TANs, in terms of coverage flexibility and availability. In this study, we propose a novel approach to ITS data offloading and computation services based on SANs. We use low-Earth orbit (LEO) and cube satellites (CubeSats) as independent mobile edge computing (MEC) servers that schedule the processing of data generated by ITS nodes. To optimize offloading task selection, computing, and bandwidth resource allocation for different satellite servers, we formulate a joint delay and rental price minimization problem that is mixed-integer non-linear programming (MINLP) and NP-hard. We propose a cooperative multi-agent proximal policy optimization (Co-MAPPO) deep reinforcement learning (DRL) approach with an attention mechanism to deal with intelligent offloading decisions. We also decompose the remaining subproblem into three independent subproblems for resource allocation and use convex optimization techniques to obtain their optimal closed-form analytical solutions. We conduct extensive simulations and compare our proposed approach to baselines, resulting in performance improvements of 9.9%, 5.2%, and 4.2%, respectively.

Nowadays, unmanned aerial vehicles (UAVs)-assisted mobile-edge computing (MEC) systems have been exploited as a promising solution for providing computation services to mobile users outside of terrestrial networks. However, it remains challenging for standalone UAVs to meet the computation requirement of numerous users due to their limited computation capacity and battery lives. Therefore, we propose a collaborative scheme among UAVs to share the workload between them. Furthermore, this work is the first to consider the task topology of offloading in MEC-enabled UAVs networks while restricting their power consumption. We study the task topology, in which a task consists of a set of subtasks, and each subtask has dependencies upon other subtasks. In the real world, subtasks with dependencies must wait for their preceding subtasks to complete before being executed, and this affects the offloading strategy. Next, we formulate an optimization problem to minimize the average latency of users by jointly controlling the offloading decision for dependent tasks and allocating the communication resources of UAVs. The formulated problem is NP-hard and cannot be solved in polynomial time. Therefore, we divide the problem into two subproblems: 1) offloading decision problem and 2) communication resource allocation problem. Then, a metaheuristic method is proposed to find the suboptimal solution to the former problem, while the latter problem is solved by using convex optimization. Finally, we conduct simulation experiments to prove that our proposed offloading technique outperforms several benchmark schemes in minimizing the average latency of users for dependency tasks and achieving higher uplink transmission rates.

Fifth-generation (5G) networks use millimeter-wave (mmWave) technology to process high-speed and capacity data services. However, wireless communication losses occur due to mmWave limitations, i.e., penetration, rain attenuation, and coverage range. Furthermore, many base stations (BSs) are needed to support stable wireless communications and overcome coverage distances in rural and suburban areas. Therefore, a new wireless communication platform that supports communication services at the aerial level is required. Furthermore, this aerial platform enables line-of-sight (LoS) communications rather than non-LoS (NLoS), which is advantageous in overcoming ground-level losses. Thus, an unmanned aerial vehicle (UAV) or an unmanned aerial platform (UAP) that can be rapidly and dynamically deployed at the point of interest is considered. Despite these benefits, UAV-BSs (also known as aerial BSs) still have optimization problems to solve, i.e., resource allocation and trajectory optimization. Thus, this study considered resource-based multi-agent deep reinforcement learning (MADRL) to solve the resource allocation and trajectory optimization problems of UAV-BSs at the same time. However, our proposed optimization problem is non-convex. Thus we proposed an algorithm based on multi-agent proximal policy optimization (MAPPO) DRL. The proposed algorithm treats each agent as a resource variable to perform optimization more effectively. As a result, the proposed algorithm achieved faster convergence and higher rewards than the baselines.

Next-generation networks need to meet ubiquitous and high data-rate demand. Therefore, this paper considers the throughput and trajectory optimization of terahertz (THz)-enabled unmanned aerial vehicles (UAVs) in the sixth-generation (6G) communication networks. In the considered scenario, multiple UAVs must provide on-demand terabits per second (TB/s) services to an urban area along with existing terrestrial networks. However, THz-empowered UAVs pose some new constraints, e.g., dynamic THz-channel conditions for ground users (GUs) association and UAV trajectory optimization to fulfill GU’s throughput demands. Thus, a framework is proposed to address these challenges, where a joint UAVs-GUs association, transmit power, and the trajectory optimization problem is studied. The formulated problem is mixed-integer non-linear programming (MINLP), which is NP-hard to solve. Consequently, an iterative algorithm is proposed to solve three sub-problems iteratively, i.e., UAVs-GUs association, transmit power, and trajectory optimization. Simulation results demonstrate that the proposed algorithm increased the throughput by up to 10%, 68.9%, and 69.1% respectively compared to baseline algorithms.

Terahertz (THz) communication has the promise of enabling ultra-high data speeds in the sixth-generation (6G) wireless networks. Meanwhile, an intelligent reflecting surface (IRS) may influence incident electromagnetic wave propagation by changing the phase shifts with passive reflecting components. It can enhance spectrum efficiency and coverage capability, and minimize blockage vulnerability caused by severe THz wave propagation attenuation and poor diffraction. Recently, unmanned aerial vehicles (UAVs) have provided the services of aerial-based multi-access edge computing (MEC) ubiquitously. Motivated by above facts, this paper considers the IRS-assisted MEC-enabled UAV system for 6G THz communications networks. To that aim, the joint optimization of UAV computation power, IRS phase shift, and THz sub-band allocation are being explored to reduce total network latency. However, the designed problem is mixed-integer non-linear programming (MINLP), which is challenging to solve in polynomial time. Therefore, an iterative algorithm based on the Hungarian algorithm and the Whale-Optimization algorithm (WOA) is proposed to address this problem. The Hungarian algorithm optimizes the sub-band allocation while WOA optimizes the IRS phase shift. Finally, simulation results show that the proposed algorithm can reduce network latency by up to 50% compared to baseline algorithms.

With the emergence of sixth-generation (6G) mobile communication technologies, intelligent gadgets are expanding. Meanwhile, due to the fast rise of marine operations for trade, research, military, oil drilling, and recreational activities, the number of maritime internet-of-things (MIoT) devices is also expanding. On-demand deployment of multiaccess edge computing (MEC) empowered unmanned aerial vehicles (UAVs) to meet the network coverage demand for MIoT devices at the seaside is presented. The MEC-UAVs are considered as reliable, cost-effective, and efficient for deployment and service provision to MIoT devices. The network profit maximization on MEC-UAV deployment and effective service allocation to MIoT devices is investigated. A combinatorial optimization problem as an integer linear programming (ILP) is formulated, which is NP-hard. To deal with a complex problem, we propose a Bender decomposition (BD) algorithm. The BD decomposes the ILP into the master problem for MEC-UAVs deployment and subproblem for MIoT device association. Finally, numerical results demonstrate that the proposed algorithm provides the polynomial-time computational complexity and achieves a near-optimal solution.

A new communications infrastructure is needed for users to experience the contents of 5G-based VR/AR in High-Speed Train (HST). Therefore, it is proposed that the Unmanned Aerial Vehicle (UAV) can be used as a communication equipment on behalf of the general Rail-side Units (RSUs) supporting the communication of the HST. To maintain reliable communications, initial deployment and trajectory considered altitude and direction of UAV are determined. Also, limited energy in UAV is an important constraint on trajectory optimization. Thus, this paper proposes initial deployment and trajectory optimization techniques for stable communication between HST and Multi-UAV with the energy constraints of UAV. This paper uses Soft Actor-Critic (SAC), one of the methods of reinforcement learning, as a way to optimize the UAV trajectory. It also uses the Support Vector Machine to carry out optimal initial deployment based on data on the maximum UAV communication distance according to the speed of HST and the energy of UAV, which is the result of trajectory optimization. As a result, this study quickly and accurately derives the optimal trajectory of Multi-Uav according to the speed of HST and the energy of UAV and also maintain stable communication by optimal initial deployment.

Due to commercialization of the 5G network, many base stations need to enhance a reliable communication quality. Thus, many studies have still worked to provide mobility and economic benefits to the VAVs-Base Station (VAVs-BS) on behalf of ground base stations. In this paper, we propose a system to find a location where multiple users can have an optimal service throughput by considering users' requirements in Multi-VAVs communication. Based on the Air-To-Ground Path Loss Model, the virtual communication environment is established and Airtime Fairness is applied for equitable channel usage time distribution according to user requirements. Thus, we apply a collaborative algorithm with modified K-means that can distribute users to each VAV and solve communication overload problems. In addition, the Proximal Policy Optimization (PPO) algorithm is applied to set an optimal location with the maximum throughput. As a result, the proposed systems allow the Multi-VAVs to be in the locations with high service throughput for users with different demands.