The large-scale expansion of the Internet of Things (IoT), coupled with its integration into application scenarios like smart transportation, remote healthcare, and intelligent agriculture, has led to surging demands for enhanced computational capabilities to process massive real-time data. These demands pose significant challenges to meet the quality of service (QoS) requirements. In order to address these issues, this paper proposes a cloud-edge-end collaborative computing power network (CPN) architecture based on Terahertz (THz) communication and assisted by reconfigurable intelligent surface unmanned aerial vehicle (RIS-UAV). Here, CPN enables flexible resource collaboration for task offloading; THz communication supports large-volume data transmission, while RIS-UAV mitigates THz's limitations of small coverage and blockage sensitivity. To unify control of the computation resource and transmission resource allocation, we introduce the Resource-Allocation Multi-Agent Soft Actor-Critic (RA-MASAC) approach, which is a multi-agent reinforcement learning-based algorithm for joint optimization of resource allocation. Simulation results demonstrate that the proposed method outperforms the existing baselines significantly.

The emergence of Sixth Generation (6G) mobile communication technologies, along with the burgeoning proliferation of Internet of Things (IoT) devices, has significantly increased the requirements for computing resources. This growing demand places considerable pressure on the computing capacity. To address diverse and intensive application requirements, the integration of satellite and terrestrial networks is a key focus in the 6G vision. Within this context, the combination of a geostationary orbit (GEO) satellite and a low Earth orbit (LEO) satellite constellation is a crucial facilitator of IoT applications, addresses their computational demands while offering global coverage, low latency, seamless scalability, and strong reliability. However, several challenges arise in such networks: 1) LEO satellites are battery-powered and resource-constrained; 2) the number of LEO computing nodes is large and distributed; and 3) the network environment is highly dynamic and complex. To address these issues, a collaborative architecture for an LEO satellite constellation and a GEO satellite (CALG) is proposed. Based on the CALG, an energy-balancing strategy is designed to identify the optimal orbital plane for task offloading as well as an efficient routing path among satellites. The task offloading and routing selection are modeled by a Markov Decision Process, with a Proximal Policy Optimization (PPO) algorithm from deep reinforcement learning is applied to optimize decision-making in a dynamic environment. Experimental results demonstrate that the energy-balancing strategy based on PPO meets system performance requirements and outperforms baseline strategies.

The integrated geostationary Earth orbit (GEO)-multibeam and low Earth orbit (LEO)-uncrewed aerial vehicle (UAV) network has emerged as a promising paradigm to enhance the coverage and capacity of terrestrial networks. However, due to the high dynamics of the network, handover becomes a critical yet challenging problem. In this paper, we model the handover problem as a decentralized Markov decision process (DEC-MDP), aiming to maximize throughput while minimizing energy consumption and handover cost. A multi-agent dueling double deep Q-network (MAD3QN) algorithm is then designed to solve it, where the centralized training with decentralized execution (CTDE) method is utilized to share intelligent information, and an offline training approach is adopted to support practical deployment. Simulation experiments with real-world satellite deployments demonstrate that MAD3QN effectively converges and significantly outperforms the existing baselines.

The integrated geostationary Earth orbit (GEO)-multibeam and low Earth orbit (LEO)-uncrewed aerial vehicle (UAV) network has emerged as a promising paradigm to enhance the coverage and capacity of terrestrial networks. However, due to the high dynamics of the network and the heterogeneous service demands of user equipments (UEs), joint handoff control and resource block (RB) allocation becomes a critical yet challenging problem. To address this issue, we propose a two-stage dynamic optimization framework, aiming to maximize throughput while minimizing energy consumption and handoff cost. Specifically, the original problem is decomposed into two subproblems: handoff control and RB allocation with fixed handoff decisions. Multi-agent dueling double deep Q-network (MAD3QN) is designed for handoff control, where the centralized training with decentralized execution (CTDE) method is utilized to share intelligent information, and an offline training approach is adopted to support practical deployment. Matching theory (MT) is then applied to determine RB allocation by finding a stable matching between RBs and UEs. Simulation experiments with real-world satellite deployments demonstrate that the proposed algorithm combining MAD3QN and MT effectively converges and significantly outperforms the existing baselines.

Amid the explosive growth of latency-aware and computation-sensitive services, mobile edge computing (MEC) assisted by aerial networks, such as high-altitude platforms (HAPs) and low-altitude unmanned aerial vehicles (UAVs), has emerged as an effective solution for providing computational capabilities to regions with sparse terrestrial infrastructure. Nevertheless, aerial networks are highly sensitive to energy cost and inherently constrained in hosting dense computing resources, while the exposed wireless environment renders them particularly vulnerable to attacks from malicious nodes. Consequently, it is imperative to develop effective task scheduling and computing resources management mechanisms that satisfy users quality-of-service (QoS) requirements while minimizing system cost and ensuring network reliability. In this paper, we develop a multi-cell MEC network composed of multiple UAVs and multiple HAPs, and further propose a dual-layer blockchain-enabled, federated election (FE)-based (DBFE) group relative policy optimization (GRPO) algorithm to jointly reduce the task offloading latency and system energy expenditure. In particular, blockchain techniques enhance system resilience against non-Byzantine failures, whereas the FE mechanism suppresses the influence of Byzantine behaviors. Simulation results demonstrate that, compared with existing approaches, the proposed method reduces the overall system cost by 19% and 31% under scenarios without malicious nodes and with malicious nodes, respectively.

As the Internet of Things (IoT) continues to develop rapidly, the exponential proliferation of devices and the sharp growth of sensed data volumes are exerting unprecedented demands on networks to achieve extensive coverage, low delay, and high reliability. Traditional terrestrial communication networks find it difficult to meet these demands in remote and special areas, which prompts satellite communication to become a key supplement. Among them, low Earth Orbit (LEO) satellites offer the advantages of low delay and superior real-time capabilities, while Geostationary Orbit (GEO) satellites offer wide coverage and stable links. Thus, the joint service of GEO and LEO has gradually become a trend. Nevertheless, a number of challenges in existing studies deserve further consideration: 1) numerous tasks are sensitive to delay; 2) tasks struggle with dynamic network environments; 3) limited computing resources are hard to allocate reasonably. Therefore, we introduce a Three-Tier Integrated Computing Network (TICN) framework in this paper to provide reliable communication and computing support for IoT, which is jointly composed of base station, LEO satellites, and GEO satellite to serve as computing sites (CSs). Given that the optimization goal involves minimizing delay and energy consumption, task offloading is modeled as a Markov decision process (MDP). As one of the multi-agent reinforcement learning (MARL) algorithms designed for coordinating multiple agents, QMixing (QMIX) is adopted to solve the optimization problem. The simulation results show that the proposed scheme provides robust performance in diverse conditions.

The rapid expansion of computation-intensive applications renders current mobile edge computing (MEC) frame works inadequate for delivering high-quality computing services in environments with sparse network infrastructure. Air-based stations, represented by low-altitude unmanned aerial vehicles (UAVs) and high-altitude platforms (HAPs), are considered a promising solution to this problem due to their flexible deployment, unconstrained by geographical conditions, and relatively low cost. However, UAV-based communication systems are highly sensitive to energy consumption, and HAPs face challenges in establishing stable connections with power-constrained devices while meeting their requirements for computation. To solve these limitations, we design a multi-UAV and HAP collaborative offloading framework innovatively, which takes both system energy cost and task processing delay into consideration, with their weighted consumption defined as the optimization objective. Since it is a mixed integer nonlinear programming (MINLP) problem, which is complicated to address by mathematical approaches, we reformulate it as a Markov decision process (MDP) and use a joint approach based on double deep Q network (DDQN)- proximal policy optimization (PPO) to assign task of f loading methods and ratios, respectively. According to simulation results, the suggested approach ensures the timeliness of task processing while efficiently reducing the weighted consumption under varying number of users, task arrival densities, and task complexities.

The rapid proliferation of the Internet of Things (IoT) has driven the emergence of intelligent applications characterized by complex task dependencies and heterogeneous quality of service (QoS) requirements. Efficient coordination of edge-cloud resources to satisfy diverse QoS demands of hybrid applications remains a challenging problem. In this paper, we formulate the task scheduling and offloading problem in edge-cloud networks as a multi-constraint, multi-objective combinatorial optimization problem through a two-dimensional decision model that jointly determines task prioritization and server selection. To support adaptive decision-making in dynamic environments, the problem is further modeled as a multi-objective Markov decision process (MOMDP). Based on this formulation, we propose a graph neural network-enhanced multi-objective reinforcement learning (GEMORL) framework that integrates a graph neural network (GNN) with multi-objective reinforcement learning (MORL). The GNN hierarchically extracts task-level, application-level, and global-level representations from task-related and latency-related attributes of applications, providing expressive state embeddings for policy learning. A multi-objective policy gradient (MOPG) algorithm is employed to train an independent policy network for each objective, and a deterministic policy is derived via a scalarization method. Extensive simulations demonstrate that GEMORL achieves superior trade-offs among conflicting objectives and consistently outperforms state-of-the-art baseline schemes across diverse network scenarios.

This letter proposes a novel pinching antenna systems (PASS) enabled non-orthogonal multiple access (NOMA) multi-access edge computing (MEC) framework. An optimization problem is formulated to minimize the maximum task delay by optimizing offloading ratios, transmit powers, and pinching antenna (PA) positions, subject to constraints on maximum transmit power, user energy budgets, and minimum PA separation to mitigate coupling effects. To address the non-convex problem, a bisection search-based alternating optimization (AO) algorithm is developed, where each subproblem is iteratively solved for a given task delay. Numerical simulations demonstrate that the proposed framework significantly reduces the task delay compared to benchmark schemes.

A novel non-orthogonal multiple access (NOMA) based low-delay service framework is proposed for fog radio access networks (F-RANs). Fog access points (FAPs) leverage NOMA for local delivery of cached content, while the cloud access point employs NOMA to simultaneously push content to FAPs and directly serve users. Based on this model, a delay minimization problem is formulated by jointly optimizing user association, cache placement, and power allocation. To address this non-convex mixed-integer nonlinear programming problem, an alternating optimization (AO) algorithm is developed, which decomposes the original problem into two subproblems, namely joint user association and cache placement, and power allocation. In particular, a low-complexity algorithm is designed to optimizing the user association and cache placement strategy using the McCormick envelope theory and Lagrangian partial relaxation. The power allocation is optimized by invoking the successive convex approximation. Simulation results reveal that: 1) the proposed AO-based algorithm effectively balances between the achieved performance and computational efficiency, and 2) the proposed NOMA-based F-RANs framework significantly outperforms orthogonal multiple access-based F-RANs systems in terms of average transmission delay in different scenarios.

Vehicle-to-Vehicle (V2V) energy trading is a feasible solution to alleviate charging anxiety and enhance the range of electric vehicles (EVs). Clustering EVs can improve the efficiency of both energy transfer and V2V communication. However, in the complex large-scale Internet of Electric Vehicles (IoEV), the security and reliability of trading and communication, as well as the impact of cluster number and strategy on trading efficiency, require further discussion. This paper proposes a V2V energy trading system that leverages blockchain sharding and dynamic clustering to securely record energy trades as transactions on the blockchain. The system forms clusters using a clustering algorithm based on the mobility information and power levels of EVs, ensuring the reachability of energy trading. These trading clusters correspond to blockchain shards, enhancing transaction throughput through sharding scalability. Deep reinforcement learning (DRL) is employed to optimize the number of clusters, clustering algorithms, and parameters of the sharded blockchain system under security and latency constraints. The results demonstrate that the proposed scheme ensures timely power replenishment for low-power vehicles, improves overall economic utility and throughput for participants, and is effectively applicable to large-scale V2V energy trading scenarios.

Due to the triple mobility of mobile users (MUs), unmanned aerial vehicle (UAV) relays, and low Earth orbit (LEO) satellites, handover becomes a critical and challenging issue for maintaining the continuity and quality of communication services in UAV-assisted LEO satellite networks. This article proposes a distributed handover decision-making process aimed at improving scalability and reducing communication overhead. The handover problem is modeled as a decentralized Markov decision process (DEC-MDP) with the objective of maximizing the total end-to-end (E2E) throughput. We design an independent proximal policy optimization-based distributed intelligent handover (IPPO-DIH) algorithm within a centralized training with decentralized execution framework to solve the DEC-MDP. To analyze the theoretical optimal E2E throughput, we eliminate the correlation between handover decisions at different time steps. A three-sided matching algorithm with theoretical convergence guarantees is designed to obtain a stable matching among MUs, UAV relays, and LEO satellites at each time step. These stable matchings are combined to provide a theoretical performance benchmark for the handover algorithms. Simulation results validate the convergence of the proposed IPPO-DIH and three-sided matching algorithms. Additionally, the total E2E throughput achieved by the IPPO-DIH algorithm approaches the theoretical performance benchmark and outperforms typical handover algorithms.

As urbanization progresses, train-to-train (T2T) communication for communication-based train control (CBTC) systems has become crucial, leading to mobile ad hoc networks (MANETs) between trains. The dynamic network topology poses challenges to the high reliability needed for safe rail transportation information. To address this, we propose a cooperative medium access control (MAC) communication scheme based on distributed time division multiple access (DTDMA) for T2T communications. This scheme uses multiple nodes in their idle time slots to cooperatively forward failed data. To ensure the reliability and effectiveness of this cooperation, we propose a cooperative MAC protocol and frame structures combined with the automatic repeat request (ARQ) mechanism for reliability and effectiveness. Additionally, we propose a cooperative node selection method, modeled as a Markov decision process (MDP), to maximize system throughput and minimize overhead. For actions with hybrid space, we use the soft actor-critic (SAC) to set a continuous threshold and select nodes discretely. Simulations show that our proposed cooperative MAC protocol and cooperative node selection method effectively enhance transmission reliability.

The management of computing resources through the computing power network (CPN) has gradually become a focal point of research. With the development of the 6th generation (6G) mobile networks, some promising technologies, such as satellite-terrestrial integrated network (STIN) and smart endogenous network driven by artificial intelligence (AI) are increasingly being applied in Industrial Internet of Things (IIoT). However, several issues in current studies are worthy of attention: 1) the large number of devices powered by battery in IIoT; 2) the complex communication environments; and 3) the finite computing resources for task data processing. To cope with these challenges, a satellite-terrestrial integrated CPN (STICPN) framework is introduced in this article. Within this framework, a task offloading link selection scheme is proposed, which minimizes the delay and the consumption of energy. The task offloading optimization problem is modeled as a markov decision process (MDP). Meanwhile, deep reinforcement learning (DRL) algorithm is employed to adapt to the dynamic states of environment. Specifically, a Dueling Double Deep Q Network (D3QN) is used to make optimal decisions and delay as well as energy consumption can be reduced significantly. Moreover, the D3QN-based scheme extends the usage time of IIoT devices. The simulation results indicate that the proposed scheme outperforms the comparison schemes significantly.

As the industrial Internet of Things (IIoT) is being built and promoted, digital and intelligent production methods are advancing rapidly. However, with the increasing number of deployed devices and complicated resource optimization schemes, several inevitable problems, such as excessive energy overhead, are brought. Driven by these issues, we propose and design a green system architecture and optimization scheme that consists of perceptual control, heterogeneous system model, and decision optimization. Based on this aspect, we focus on optimizing energy efficiency in the IIoT by utilizing ambient backscatter communication (AmBC) technology in the perception control layer, and reducing training costs through collective deep reinforcement learning (CDRL) among edge nodes. Simulation results show that our proposed scheme has significant advantages in the area of energy efficiency.

The integration of advanced technologies such as the sixth-generation (6 G) mobile communications, artificial intelligence (AI) and blockchain have given new impetus to the development of the Internet of Things (IoT). However, these applications require higher computational power and lower latency, which present challenges to traditional network architecture. To address these issues, a novel computing power network (CPN) architecture is proposed in this paper based on reconfigurable intelligent surface (RIS)-unmanned aerial vehicle (UAV)-assisted non-orthogonal multiple access (NOMA)-Terahertz (THz) communication, and it aims to meet high computational demands. To increase the efficiency of the proposed architecture, it is crucial to rationally allocate computational and transmission resources. Therefore, a joint optimization problem is formulated to minimize system consumption, encompassing both time and energy usage. To achieve efficient resource allocation, an adaptive N-Step method based on soft actorcritic (SAC) algorithm is employed. Simulation results demonstrate the superiority of the proposed method over the existing baselines.

The security and reliability risks of industrial data have constrained the advancement of the Industrial Internet of Things (IIoT). Although blockchain can protect the security and reliability of industrial data through hash verification mechanisms, there are numerous challenges in the existing blockchain-enabled IIoT systems, such as the trilemma of scalability, decentralization and security, high computational power consumption of consensus protocols and limited computational resources of industrial devices. To address these problems, an intelligent sharding blockchain-enabled IIoT framework is proposed, in which the intelligent sharding based on the reputation mechanism and the adaptive switching for multi-consensus protocols are utilized to enhance the decentralization, security and scalability of blockchain. Considering higher requirement of computational power of the sharding blockchain, a cloud-edge-end collaborative computing framework is introduced, in which the parallel computational offloading and the Terahertz communication technology are utilized to enhance the cooperation of the cloud-edge-end networks. Furthermore, due to the highly dynamic nature of industrial devices and industrial data, we consider and design the optimization problem as a Markov decision process (MDP), which is solved via the Proximal Policy Optimization (PPO) algorithm. Simulation results show that our proposed scheme can minimize total delay and maximize transaction throughput while guaranteeing the safety as well as decentralization of blockchain-enabled IIoT systems.

With the continuous growth of urban populations, communication-based train control (CBTC) systems for urban rail transit have garnered increasing attention. The previously adopted train-to-ground (T2G) communication is no longer sufficient to meet future transportation demands. Train-to-train (T2T) communication shares many similarities with vehicular ad hoc networks (VANETs). Based on this framework, we propose a protocol specifically designed for T2T communication. This scheme clusters trains based on their transmission ranges and assigns varying priorities to the packets transmitted over the control channel (CCH) to ensure the safe operation of the trains. Meanwhile, it introduces a novel cooperative mechanism specifically designed for safety packets, further enhancing their transmission reliability. Additionally, the protocol allows service providers to reserve time slots on the service channels (SCHs) in advance, thereby enhancing channel utilization efficiency.

As an essential element of intelligent transport systems, Internet of vehicles (IoV) has brought an immersive user experience recently. Meanwhile, the emergence of mobile edge computing (MEC) has enhanced the computational capability of the vehicle which reduces task processing latency and power consumption effectively and meets the quality of service requirements of vehicle users. However, there are still some problems in the MEC-assisted IoV system such as poor connectivity and high cost. Unmanned aerial vehicles (UAVs) equipped with MEC servers have become a promising approach for providing communication and computing services to mobile vehicles. Hence, in this article, an optimal framework for the UAV-assisted MEC system for IoV to minimize the average system cost is presented. Through joint consideration of computational offloading decisions and computational resource allocation, the optimization problem of our proposed architecture is presented to reduce system energy consumption and delay. For purpose of tackling this issue, the original non-convex issue is converted into a convex issue and the alternating direction method of multipliers-based distributed optimal scheme is developed. The simulation results illustrate that the presented scheme can enhance the system performance dramatically with regard to other schemes, and the convergence of the proposed scheme is also significant.

With the advancement of urbanization, communication-based train control (CBTC) systems for urban rail transit and train-to-train (T2T) communication have garnered significant attention. T2T communication establishes mobile ad hoc networks (MANETs), similar to those in vehicular ad hoc networks (VANETs). Building upon this foundation, we propose an adaptive cooperative (ADCO) MAC protocol for T2T communication. The scheme introduces clustering and cooperative transmission mechanisms, which enhance the efficiency and reliability of safety packet transmission. Additionally, the protocol assigns different priorities to packets engaging in contention on the control channel (CCH) and enables trains to access service channels (SCHs) without contention through pre-reserved time slots. To analyze the transmission probabilities and success rates of packets with varying priorities, a Markov-based model is utilized, ultimately determining the optimal ratio of the CCH interval (CCHI) to the SCH interval (SCHI) for maximizing channel utilization. Theoretical analysis and simulation results demonstrate that the proposed MAC protocol ensures reliable transmission of safety packets while simultaneously optimizing the throughput on SCHs.