最新刊期
卷 10 ， 期 1 ， 2026
- 摘要：Conventional Internet of things (IoT) systems are typically deployed in terrestrial or low-altitude domains with isolated functionalities such as communication and sensing. As global communication technologies evolve towards 6G, they increasingly struggle to meet the demands of emerging applications like Industry 5.0, comprehensive emergency response, and intelligent ocean exploration. These applications require both “ubiquitous coverage across space, air, ground, and sea” and “deep integration of communication, sensing, intelligence, and computing”, promoting the emergence of the 6G cross-domain IoT as a pivotal paradigm. A systematic review of research progress and key technologies in this field was conducted to provide a systematic reference framework for both theoretical research and industrial implementation of 6G cross-domain IoT with unified communication, sensing, intelligence, and computing. Firstly, from a scenario dimension, the development landscape of IoT in four domains, including air-domain, sea-domain, and ground-domain was summarized, highlighting their heterogeneous characteristics and the need for cross-domain integration. Secondly, from a functional dimension, three integration paradigms, including integrated sensing and communication (ISAC), communication-intelligence convergence, and communication-computing coordination, were analyzed, and the necessity of synergistic interaction among communication, sensing, intelligence, and computing were emphasized. Then, a five-layer cross-domain integration architecture spanning hardware, physical, link, network, and application layers was established, and key performance metrics along with inherent trade-offs for global-scale scenarios were identified. Furthermore, the state of research on key enabling technologies was elaborated in detail, including channel measurement and pervasive modeling, cross-domain transmission and universal communication, advanced flexible multi-antenna techniques, energy efficiency optimization, and simultaneous wireless information and power transfer, channel map and digital twins, foundation model-empowered ISAC, intelligent computing with cloud-edge-end collaboration, as well as native security and privacy preservation. Finally, future technical challenges and suggest promising research directions were proposed, such as continuous-space radio channel measurement and modeling, electromagnetic information theory, AI foundation models for multi-source data fusion, and the development of cross-domain unified standards.关键词：6G Internet of Things;integrated space-air-ground-sea coverage;integrated communication-sensing-intelligence-computing;key enabling technologies;network architecture216|96|0更新时间：2026-04-16
Review
- 摘要：Federated learning, due to its distributed and privacy-preserving characteristics, has attracted widespread attention in the field of data security in vehicular networks. The asynchronous federated learning mechanism can better adapt to the dynamic changes of vehicle computing power and network conditions, and at the same time improve the efficiency of global model updates and realize effective protection of local privacy data. However, the malicious vehicles in federated learning training may perform poisoning attacks by uploading malicious models to the global model, which in turn affects the local training of normal vehicles. During model dissemination, although increasing the number of candidate models can improve the probability of avoiding malicious models, it will significantly increase communication latency and affect system performance. To balance security and latency, a federated learning model transmission migration method was proposed. The interaction process between moving vehicles and roadside units (RSUs) on urban roads were modeled, as well as the security of model dissemination. Through reinforcement learning, the vehicle-to-RSU transmission migration strategy was optimized, ensuring the security of model dissemination while effectively reducing communication latency. Simulation results show that, compared with baseline methods, the proposed method reduces the average transmission latency by about 7%, which verifies its advantages in terms of security and communication latency.关键词：Internet of vehicles;federated learning;latency optimization;reinforcement learning;transmission migration108|49|0更新时间：2026-04-16
- 摘要：Path planning is critical for autonomous underwater vehicles to achieve efficient and safe navigation in dynamic ocean environments. However, in complex marine settings characterized by coexisting strong shear currents and vortex fields, autonomous underwater vehicles face challenges such as excessive energy consumption, path oscillations, and inadequate threat avoidance. To address these issues, firstly, a multi-physics-field-integrated ocean environment model was constructed, enabling high-fidelity characterization of complex marine environments featuring coexisting shear currents and vortex fields. Subsequently, a novel MFD-A* (multi-field-driven A*) algorithm was proposed. By formulating a comprehensive cost function, three key hydrodynamic constraints-a drag energy consumption model, a heading synergy model, and a vortex threat field model- were embedded into the A*-search framework, achieving global optimization of energy efficiency, heading stability, and navigation safety. Simulation results demonstrate that in ocean environments with strong shear currents combined with dual-vortex and multi-vortex configurations, the MFD-A* algorithm reduces energy consumption by 15.04% and 22.89%, respectively, compared to the standard A* algorithm. The average heading-current angle is reduced by 27.48% and 34.2%, while 100% avoidance of vortex core regions is achieved in both scenarios.关键词：autonomous underwater vehicle;path planning;resistance energy consumption;threat avoidance;heading stability66|39|0更新时间：2026-04-16
- 摘要：With the intelligent transformation of China's shipping network, large navigation hub infrastructures, represented by the Yangtze River trunk line, have become highly complex and heterogeneous under the empowerment of digitalization. These networks face severe cybersecurity threats, posing a challenge to shipping and even national strategic security. To address this challenge, a security protection framework for cross-domain collaboration paradigm was proposed in this paper. The framework aimed to integrate protection technologies and strategies from different security domains to achieve tight collaboration and efficient response. The research background, architectural framework, key technologies, and future research priorities of cross-domain collaborative security protection technology for large navigation hub critical infrastructure were delved, providing feasible references for enhancing its security capabilities.关键词：navigation hub infrastructure;cross-domain collaborative protection;Internet of things security;industrial control network56|94|0更新时间：2026-04-16
- 摘要：To address the problems of low positioning accuracy and difficult parking in indoor parking garages, an IoT-based autonomous parking system enabled by ultra-wideband (UWB) cooperative localization was developed. The system adopted a "infrastructure-vehicle" distributed architecture built on robot operating system 2 (ROS2), supporting multi-vehicle management and global trajectory distribution. To improve UWB stability under non-line-of-sight (NLOS) and multipath conditions, a multi-stage fusion method was proposed, consisting of ranging preprocessing, spherical positioning, and an improved adaptive extended Kalman filter (IAEKF). For planning and control, feasible trajectories were generated by integrating an improved A* algorithm with smooth curve refinement, and a credibility-aware model predictive control (MPC) strategy was introduced to enhance tracking robustness under fluctuating localization quality. Experimental results showed that the proposed system outperforms five localization methods in both positioning accuracy and control robustness in complex environments. Moreover, with the proposed fusion algorithm applied to the domestic UWB chip MK8000, the overall performance approached that of systems based on the DW1000 chip, demonstrating the feasibility of a low-cost and domestically deployable autonomous parking solution.关键词：UWB;automatic parking;indoor localization;non-line-of-sight;trajectory tracking67|42|0更新时间：2026-04-16
Smart Transportation and Intelligent Connectivity
- 摘要：A cross-domain knowledge-driven meta-intelligent network algorithm framework was proposed in this paper to address the limitations of existing automated operation and maintenance models in supporting multi-scenario and real-time intelligent management in 6G networks. Traditional approaches often rely on static rules or single-domain optimization, which are insufficient for 6G demands such as heterogeneous perception, dynamic policy adaptation, and multi-objective scheduling. The framework modeled network states across environmental, network, and user behavior domains, leveraging lightweight models and graph neural networks for high-level intent parsing and online knowledge fusion. A global knowledge base was dynamically updated via knowledge distillation. Multi-layer meta-intelligent agents formed a closed-loop control process of perception, reasoning, knowledge generation, decision issuance, validation, and memory retrieval. Self-supervised learning, reinforcement learning, and meta-learning techniques were integrated to support rapid policy adaptation and continual optimization. Centered on a low-altitude traffic control scenario, the framework was evaluated through three tasks: knowledge-driven networking, intent-guided agent management, and swarm path planning. Experimental results show that the proposed method consistently outperforms baseline approaches in throughput, failure recovery time, traffic prediction accuracy, decision latency, execution success rate, resource fairness, path efficiency, and task success rate.关键词：network knowledge;knowledge-driven network;network meta-intelligence;intelligent network76|43|0更新时间：2026-04-16
- 摘要：Integrated sensing and communication (ISAC) is a key enabler for 6G, aiming to equip wireless networks with sensing capabilities to support applications, such as intelligent transportation and digital twins. However, the present reference signal (RS)-based ISAC mechanisms are unable to strike a balance among sensing accuracy, coverage, and communication quality of service (QoS). The ISAC schemes based on B5G/6G RSs were investigated in this paper. Firstly, a multi-signal fusion and cooperative architecture was proposed to overcome sparse signal placement and enhance sensing coverage and resolution without degrading communication quality. On this basis, a robust parameter estimation algorithm was developed to address challenges including low signal-to-noise ratio (SNR), limited observation samples, and range-velocity ambiguity, significantly improving sensing performance. This demonstrates the feasibility of efficient RS-based ISAC strategies, providing a technically viable and theoretically sound approach for the integration of communication and sensing in 6G.关键词：ISAC;RS;collaborative sensing;low SNR;target ambiguity128|55|0更新时间：2026-04-16
- 摘要：Internet of things (IoT) enables intelligent interaction and data sharing, facilitating connectivity among objects and humans. It has been widely applied in smart homes, intelligent transportation, industrial automation, etc. Traditional IoT development processes rely on manual hardware-software collaborative development, which involves a high technical barrier. Low-code development technology significantly lowers this barrier by providing graphical interfaces and highly abstracted programming application programming interfaces. Nevertheless, it still faces limitations in customization capabilities. With the maturity of artificial intelligence (AI) and related technologies represented by large language models, an emerging AI-native paradigm for IoT computing task generation characterized by leveraging AI models to provide high-level semantic representations of IoT application development workflows is gaining traction and presenting novel opportunities for IoT application development. Therefore, on the basis of reviewing the development of software development technology for the IoT, an AI-native framework for generating computing tasks of IoT was proposed in this paper, which was divided into two stages: intent understanding and task planning. Based on this, the key technologies and challenges were systematically analyzed, a comprehensive review of the latest research was provided, and the future development directions of AI-native computing task generation were finally looked forward to.关键词：IoT;AI-native computing;Low-code development;large language model74|48|0更新时间：2026-04-16
- 摘要：With the rapid development of the digital economy, cybersecurity risks have become increasingly severe. According to relevant reports, ransomware has emerged as one of the most destructive threats in cyberspace. Alarmingly, cybercriminals are continuously leveraging advanced artificial intelligence (AI) technologies to develop next-generation ransomware, making these attacks more intelligent, covert, and damaging. Consequently, it is imperative to comprehensively examine the new impact of AI on cybersecurity, deeply reveal the operating principles of AI-assisted ransomware, and build effective defense strategies. At present, there is a lack of systematic and comprehensive literature analyzing the operating principles and impacts of AI-assisted ransomware. To address this gap, firstly, ransomware was categorized. Subsequently, the attack process of ransomware was analyzed. And then, combined with the latest research progress, the operating principles of AI-assisted ransomware were elaborated in depth. Finally, response measures to operating principles ransomware were systematically summarized from five key perspectives: prevention, prediction, detection, identification and mitigation. Additionally, the development trends and potential future research directions of AI-assisted ransomware were analyzed, aiming to provide valuable insights and guidance for practitioners in the field of cybersecurity.关键词：ransomware;cybersecurity;artificial intelligence;defense system32|29|0更新时间：2026-04-16
- 摘要：To address the issues in spectrum sharing systems, such as unreliable sensing results because of the data falsification and unfair access allocation, a spectrum sharing model based on the sensing quality was proposed. By jointly optimizing sensing quality and access resource allocation, this model improved efficiency and fairness. In the sensing phase, a leader-follower game modeled the interaction between sensing users and demanders: the sensing users optimized sensing quality to maximize their benefits, while the demanders determined data purchases based on sensing quality, ensuring efficient and reliable data collection. In the access phase, spectrum resources were dynamically allocated based on the sensing quality, with the VCG (Vickrey-Clarke-Groves) mechanism ensuring truthful reporting and preventing data falsification and fraud. This led to fair and optimized spectrum allocation, enhancing the overall system efficiency. Simulation results show that the proposed mechanism effectively incentivizes users to report the true sensing quality and protects the honest users.关键词：dynamic spectrum sharing;sensing quality;resource allocation;game theory;VCG mechanism47|27|0更新时间：2026-04-16
- 摘要：The development wave of general artificial intelligence drives the generation and processing of massive data, and large-scale and heterogeneous graph data networks constitute an important foundation of the digital world. However, the continuously growing scale of data not only increases the difficulty of graph data processing, but also creates the need to reduce graph size and maximize the amount of graph information. Existing methods make it difficult to synergistically control the graph size and optimize the amount of graph information, which limits the effectiveness of graph data analysis and processing. In response to the need for balanced control of graph data scale and information content, the graph reducing problem with scale regulation as the constraint and information maximization as the goal was proposed. Specifically, a graph fusion algorithm and a deep reinforcement learning-based graph reducing algorithm were designed to solve the problem, including graph reducing operations such as node fusion, composite mapping, and methods used for similarity metrics. Experiments verified the balanced regulation ability of the reducing algorithm, and comparisons with four algorithms across three evaluation metrics—feature similarity, graph similarity, and edge information loss—showed that the proposed graph reduction method could achieve performance improvements of at least 20.7%, 19.9%, and 26.3%, respectively.关键词：graph reducing;deep reinforcement learning;scale regulation;amount of information;similarity59|34|0更新时间：2026-04-16
- 摘要：Network digital twin technology plays a significant role in improving the maintenance efficiency and decision-making accuracy of IP bearer network simulation and testing. However, it still faces challenges, such as low simulation accuracy and insufficient simulation performance. A high-performance network digital twin simulation engine, extended PNetLab (ePNetLab), based on the PNetLab simulation platform was proposed. Firstly, the original platform was optimized in terms of performance and functionality. The interface response mechanism was improved, a cross-node communication scheme was designed, and the efficiency of topology construction was enhanced, along with the ability to form clustered networks. Secondly, a topology dynamic construction method based on community detection algorithms was designed and implemented, effectively reducing the construction time and resource overhead in the large-scale simulation scenarios. Finally, experimental evaluations were conducted to verify the feasibility and efficiency of the proposed solution. The experimental results show that ePNetLab improves the topology construction efficiency by 82.9% compared with the native PNetLab under the optimal conditions. Meanwhile, the community partitioning algorithm introduced greatly improves simulation efficiency, resource utilization, and business performance compared with the other algorithms.关键词：IP network;digital twin network;simulation engine;community partitioning algorithm66|41|0更新时间：2026-04-16
- 摘要：The frequent occurrence of flood disasters is found to pose a serious threat to socio-economic stability and residents' property security, and the improvement of prediction accuracy and timeliness is identified as an urgent issue. To address this problem, a multimodal flood disaster prediction architecture based on cloud-edge collaboration was proposed, which overcame the bottlenecks of traditional cloud computing in terms of transmission latency, computational load, and real-time performance. In this architecture, raw data was collected by IoT devices, a local real-time prediction model based on LSTM networks was constructed at the edge layer to generate local prediction results, and a global fusion model based on Transformer networks was built in the cloud to capture long-range dependencies and produce global results. Moreover, an adaptive weight adjustment algorithm was designed to optimize the coordination between local and global outputs. Experimental results show that the proposed architecture outperforms traditional centralized cloud computing in prediction accuracy, data transmission latency, actual bandwidth rate, and edge computing resource utilization. It is concluded that cloud-edge collaboration and multimodal fusion effectively enhance the accuracy and timeliness of flood disaster prediction, providing new insights for disaster prevention, mitigation, and scientific decision-making.关键词：flood disaster prediction;cloud-edge collaboration;LSTM;Transformer61|40|0更新时间：2026-04-16
- 摘要：The cache revenue of edge nodes is a key performance metric for the cellular-vehicle caching system. Based on the mobility characteristics of vehicular users, the caching deployment method at edge nodes was mathematically modeled. Network coding technology was introduced to comparatively analyze the performance differences between random caching and network coding-based random caching methods. A network coding-based edge content caching algorithm for vehicular networks was proposed, and a theoretical limits of the algorithm's caching benefits were analyzed. Experimental results showed that the proposed method outperforms the classic algorithms, exhibits greater robustness against uncertain factors such as instantaneous vehicle speed, and increases a cache hit rate improvement of over 20% at roadside units.关键词：cellular-vehicle to everything;edge caching;mobility aware;network coding47|30|0更新时间：2026-04-16
- 摘要：With the deep integration of intelligent Internet of things technology and 5G/6G communication technology, satellite edge computing (SatEC) offers new computational services to areas with weak terrestrial network coverage through its aerospace collaborative computing network. However, the SatEC system faces dual challenges of unbalanced dynamic resource allocation between satellite and ground and insufficient task priority control under multi-dimensional spatiotemporal constraints. Existing methods have defects in hierarchical decision-making, spatiotemporal feature extraction, and task urgency quantification mapping, which limit the efficiency of time-sensitive task processing. To address this problem, a multi-agent deep reinforcement learning algorithm based on self-attention temporal convolutional networks was proposed in this paper. The algorithm achieved joint optimization of task prioritization and resource allocation by constructing a multi-agent architecture, employed a hybrid neural network integrating spatiotemporal features to accurately extract dynamic correlation characteristics of satellite-ground collaboration scenarios, and established a dynamic scheduling mechanism based on a probabilistic model to synergistically optimize latency constraints and task completion rates. Simulation results show that, compared with the baseline algorithm, the proposed algorithm achieves significant improvements in both task completion rate and delay control, demonstrating its effectiveness and superiority in complex satellite edge computing scenarios.关键词：SatEC;resource allocation;task priority;self-attention temporal convolutional network;multi-agent deep reinforcement learning42|39|0更新时间：2026-04-16
- 摘要：In order to deal with the problem of multi-dimensional resource allocation in future wireless Mesh networks with limited resources and dynamic changes in network topology and user demands in emergency communication scenarios, a dynamic Mesh network slicing end-to-end service stable matching algorithm for 6G networks was proposed. Firstly, according to the differentiated service requirements of different services and based on Gale-Shapley matching idea, the multi-service end-to-end service problem was expressed as hierarchical bipartite stable matching process. Then, preference lists of requesters and service providers were established, and stable matching of user-slice-base station and service flow-service path were carried out on the access side and the return side respectively. Complete an end-to-end service that differentiates task types. The simulation results showed that the proposed stable matching algorithm had good performance in reducing network cost, improving the success rate of service and distinguishing the differentiated needs of high reliability, low latency and large bandwidth services of service types.关键词：stereoscopic wireless Mesh network;task-driven;end-to-end slicing;stable matching algorithm53|35|0更新时间：2026-04-16
- 摘要：With the development of IoT technologies, the demand for quality of service across different business scenarios has become increasingly diverse. Currently, how to accurately interpret IoT service requirements and effectively guarantee quality of service (QoS) for differentiated business scenarios remains a significant challenge in the industry. To address this challenge, in-depth research on intent-driven IoT resource allocation mechanisms is urgently needed. Given the dynamic and complex nature of IoT environments, along with the notable differences in service requirements, traditional demand interpretation methods are found to be inadequate for achieving accurate mapping from user intents to IoT policies. Therefore, an intent-driven dual-time-scale resource allocation method was proposed. Firstly, scenarios were categorized based on their QoS requirements, and an intent translation algorithm based on a large language model with retrieval enhancement was designed. By integrating device and service information, user intents were translated into executable IoT policies. Secondly, focusing on both resource allocation efficiency and the dynamic state changes in IoT environments, a dual-time-scale resource allocation framework was constructed with the optimization objective of maximizing the overall system revenue. This framework included: at the long time scale, the dueling double deep Q-network (D3QN) algorithm was adopted for global resource allocation among slices; at the short time scale, the mixed-integer linear programming (MILP) algorithm was employed for fine-grained resource scheduling within slices. Experimental results demonstrated that the proposed method enabled accurate generation of upper-level policies through intent translation and achieved elastic scheduling of lower-level resources via the resource allocation algorithms. Compared with single-time-scale algorithms, the proposed approach allowed for more efficient resource allocation that better adapted to the state of downstream IoT systems, thereby ensuring differentiated QoS for various business scenarios within the same IoT environment.关键词：resource allocation;autonomous network;intent-driven network;deep reinforcement learning61|58|0更新时间：2026-04-16
- 摘要：To address the multiple access issue in satellite communication systems under spectrum scarcity, a semi-grant-free (SGF) transmission strategy based on non-orthogonal multiple access (NOMA) was proposed. In this strategy, mobile terminals termed as grant-free (GF) users were equipped with a planar array, while the earth station termed as grant-based (GB) user was equipped with a high gain directional antenna, and they access the satellite network simultaneously. Firstly, to ensure the quality of service for GB users, the maximum tolerable interference threshold was calculated by the GB user under the condition of only known statistical channel state information (SCSI), and was broadcasted by the satellite to all GF users. GF users who satisfy the threshold condition shared the same spectrum resource with the GB user by utilizing NOMA technology. Then, corresponding low complexity beamforming methods were proposed for GF users employing both continuous and discrete phase beamforming. Furthermore, under the assumption that the satellite channel follows a Shadowed-Rician distribution and accounts for imperfect successive interference cancellation (SIC) at the receiver, a closed-form expression for the system throughput under the proposed SGF transmission strategy was derived. Finally, computer simulations were conducted to validate the correctness of the theoretical analysis and the superiority of the proposed transmission strategy, while quantitative analyses were performed to evaluate the impact of typical parameters such as imperfect SIC, discrete bit count, and number of antennas on system performance.The results showed that when the phase discrete bit number was 3 bits, the system performance approached the level achieved with continuous phase BF.关键词：satellite communication;non-orthogonal multiple access;semi-grant-free transmission;beam forming;imperfect successive interference cancellation23|15|0更新时间：2026-04-16
- 摘要：Anomaly detection is proving to be a key capability in energy Internet of things(IoT) scenarios such as industrial equipment fault monitoring, enabling IoT systems to identify abnormal patterns in time-series data in real time, thereby improving system security, stability, and operational efficiency. However, the scarcity of time-series data is emerging as a major bottleneck limiting model performance, mainly due to the high cost of acquiring high-quality labeled data and the limited data collection conditions in industrial production, which make it difficult to cover all possible scenarios. Traditional data augmentation methods are increasingly being regarded as inadequate for capturing the complexity and diversity of abnormal events, further constraining the performance of detection models. To address these issues, a data augmentation method based on time-series generation was proposed to enhance the anomaly detection capability of models under data-scarce conditions. The method utilized a variational autoencoder generative model to synthesize realistic and diverse time-series data from limited samples, thereby mitigating the impact of data scarcity on model performance and significantly improving the robustness and accuracy of anomaly detection. Experimental results demonstrated that the proposed method exhibited good adaptability in energy IoT scenarios such as smart manufacturing, providing effective technical support for building efficient and intelligent anomaly detection systems.关键词：anomaly detection;variational autoencoder;time series generation;data augmentation;energy Internet of Things50|34|0更新时间：2026-04-16
Theory and Technology
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
- Total Visits：212845 Visits Today：668
0