Distributed AI model training generates bursty, low-entropy elephant flows that challenge existing single-path transport protocols in multi-stage Clos networks, leading to congestion and inefficiency. Multipath transport emerges as a promising solution, leveraging multiple paths to balance traffic and enhance resilience. However, current multipath RDMA solutions suffer from scalability, congestion control, and load-balancing inefficiencies. This paper introduces Unified Delay-driven Multipath Protocol (UDMP), a novel approach that co-designs congestion control and load balancing using network delay as a unified signal. UDMP employs delay-gradient-based congestion control to precisely resolve unavoidable congestion. Moreover, UDMP leverages delay-assisted load balancing to shift traffic across paths with minimal latency adaptively, maintaining throughput when encountering avoidable congestion. A novel Token Pool design integrates these components, eliminating per-path state overhead while achieving fine-grained traffic distribution. Implementations on DPDK and NS3 demonstrate that UDMP achieves up to 2x higher throughput and reduces flow completion times by up to 30% compared to state-of-the-art methods like MPRDMA and QP-Scaling. These results highlight UDMP’s effectiveness in meeting the stringent performance requirements of modern distributed AI training workloads.

This paper addresses the challenges of privacy protection, device constraints, resource heterogeneity, and trusted inference in the integration of large language models (LLMs) with Internet of Things (IoT) devices, proposing a Hierarchical Federated Collaborative Computing (HFCC) framework. Unlike traditional federated learning, HFCC employs horizontal splitting + chunking to reduce LLMs computation overhead. The framework dynamically splits LLMs into: 1) global shared layers optimized by edge servers, and 2) device-local layers trained on private data, ensuring raw data remains on-device. During inference, chunking of shared layers and dynamic task allocation adjust computational loads based on real-time device states, mitigating high-load security risks. Furthermore, leveraging the hierarchical federated learning architecture, the system employs an anonymized parameter aggregation mechanism during training to achieve multi-level privacy protection. Simultaneously, a cross-device consensus verification mechanism performs trusted validation of distributed intermediate results, effectively identifying malicious node behavior. Experiments show 58% faster inference in resource-constrained environments, significantly reduced data exposure risks, and 94% malicious node detection accuracy versus traditional federated learning. This lays a solid foundation for building an intelligent, efficient, and secure IoT ecosystem.

In the context of 6G communication networks, large communication models emerge as the core application for edge communication networks. They hold immense application potential in areas like intelligent connected vehicles, collaborative robots, and holographic communications. However, practical implementations of these applications face challenges such as unstable learning environments, resource constraints, information theft, and heterogeneity of edge devices. This paper delves into the distributed deployment of large communication models under resource-constrained nodes and introduces a distributed architecture based on cloud-edge collaboration. Crucially, we introduce a negotiation and debate mechanism between small AI models. This mechanism adopts innovative strategies, enabling it to match or even surpass the capabilities of large language models in terms of inference and accuracy. Furthermore, addressing the data confidentiality issues of large model parameter transmissions, this study proposes a secure federated learning mechanism based on privacy computing. Combining novel model layering technology with privacy protection measures, it aims to enhance the security of model parameter transmissions. Experimental results confirm that while improving learning efficiency and inference accuracy, this strategy successfully ensures the privacy security of edge nodes, offering a practical solution for future privacy protection.

In recent years, with the continuous development of internet of things (IoT) technology, many fields have benefited a lot, including the maritime transportation system (MTS). But there are also corresponding risks, such as security and privacy, interference attacks, ransomware attacks, and so on. How to ensure the reliability and efficiency of information transmission is very important for maritime transportation system. In order to solve this problem, we propose an IoT-enabled maritime transport communication system, which is a distributed system composed of base stations and offshore buoys, and uses the unique structure of the blockchain to solve the problems of security and reliability in the network. There are two main advantages: First, the decentralized network is reliable and can handle node failures. Second, the use of blockchain technology can integrate computing resources into the entire network to support different tasks, while taking into account information security and transaction security. On this basis, with the help of edge computing technology, we have also improved the energy efficiency and performance of IoT devices in the system.

Maritime intelligent transportation system provides intelligent, safe and efficient maritime transport services, which greatly facilitates the applications related to monitoring, safety, infotainment and cargo online management. The Internet of Things (IoT) is especially suitable for the networked communication environment at sea, and drives the development of maritime intelligent transportation on the trend. However, the existing data processing and forwarding methods pose great challenges to Intelligent Transportation Systems (ITS). In particular, realtime multi-type of data adopts different access technologies in wireless communication systems or use the same wireless access technology but belong to different wireless carriers. Utilizing the existing multi-type wireless communication systems, the architecture of the heterogeneous network through inter-system convergence makes multi-system complement to meet the demand of mobile communication services, so as to comprehensively play their respective advantages. In this paper, we consider a multiattribute decision-making method based on Analytic Hierarchy Process (AHP) and Rough Set based on the architecture of maritime wideband communication system with software defined network (SDN) and fog computing architecture. This paper aims to select a feasible network routing scheme for this heterogeneous network, based on multi-attribute of different networks. Finally, we simulate a communication network selection case based on the future maritime communications architecture, and solve the architecture optimization problem through our proposed algorithm. The issue of such network choice necessarily exists in maritime communications architecture, and our tentative assumptions and solutions will be an important basis for such issues.