Chungang Yang

The rapid evolution of next-generation wireless networks poses new challenges for delivering ultra-high data rates and seamless connectivity across diverse environments. In remote areas, where licensed spectrum bands in terrestrial networks (TNs) are often underutilized, it is possible to allow non-terrestrial networks (NTN) to opportunistically access these spare spectrum resources. However, such spectrum sharing must maintain TN performance while enhancing the overall performance of the satellite-terrestrial integrated network (STIN), including network capacity and area spectral efficiency. In this paper, we propose a spectrum-sharing mechanism that enables an NTN to share TN bandwidth, using a three-dimensional (3D) conical protection-zone-based approach to mitigate co-channel interference from NTN to TN users. Leveraging tools from stochastic geometry, we introduce a novel spherical Poisson hole process (SPHP) to model the spatial distribution of satellites and derive tractable expressions for user coverage probabilities and the weighted-sum area data rate (WS-ADR) of the spectrum-sharing-enabled STIN (SS-STIN). Analytical results are validated through extensive Monte Carlo simulations based on Starlink constellations. Moreover, we investigate the impact of key design parameters on coverage probabilities of typical users and the WS-ADR. Simulation results indicate that optimizing the protection angle and bandwidth allocation factor enables the proposed SS-STIN to achieve up to 30 times higher WS-ADR than STINs without spectrum sharing, and more than threefold WS-ADR compared to SS-STINs without protection zones, while ensuring that the area data rate threshold for each user type is met.

Task-oriented heterogeneous Flying Ad Hoc Networks (FANETs) are emerging as network paradigms to meet increasingly complex task requirements. However, conventional cross-domain routing protocols face challenges such as heavy address matching, high routing overhead, and a lack of task-adaptive capabilities. We propose an intent-driven cross-domain routing framework, termed ICRT. The ICRT framework explores and exploits typical capabilities of intent-driven networks and named data networks to decouple the task control plane from the network forwarding plane to achieve routing flexibility. Furthermore, we propose a novel ICRT protocol to assign appropriate cross-domain forwarding routes to different services, ensuring that the transmission links of the services are adapted to the business requirements. Finally, we construct an emulation platform to validate the feasibility and efficiency of the presented ICRT framework and protocol. Simulation results show that the ICRT protocol outperforms the conventional FANET routing protocol, achieving a 350 ms reduction in end-to-end delay, an 11.8% increase in packet delivery ratio, a 1.5 Mbps improvement in network throughput, and a 10% reduction in routing overhead. It also ensures that the differences between all service requirements and link metrics remain within the order of $10^{-4}$.

As differentiated services emerge, intent-driven management and orchestration in the 6G terrestrial networks will face two key challenges. On the one hand, the intent mapping gap, limited orchestration flexibility, and lack of policy abstraction constrain intent refinement across the Business Support System, Operation Support System, and Network Operation Provider layers. On the other hand, multi-domain orchestration among the radio access, transport, and core networks remains hard due to limited global awareness, resource conflicts, and inconsistent policy models. In this paper, we present LAMIO-6G, a large AI model-empowered framework for cross-layer intent management and multi-domain policy orchestration, which autonomously generates policies at different levels of abstraction from intents. The LAMIO-6G incorporates two key models: (i) a unified network policy model and (ii) a monitor-analyze-plan-execute-knowledge feedback closed-loop model. To address limited intent generality and scenario generalization in the Business Support System layer, we then introduce intent decomposition techniques via generic large AI models using low-rank adaptation-based fine-tuning, design of intent decomposition prompts, and few-shot learning-assisted intent decomposition. Within the Operation Support System layer, we design an intent reasoning and optimization scheme through collaboration between domain-specific large AI models guided by long-short chain-of-thought techniques and lightweight proximal policy optimization model. Finally, we present a proof-of-concept implementation of a wireless energy-saving intent. Simulation results demonstrate that the DeepSeek-R1-14B model achieves 17% to 30% gains over all baseline schemes in fine-tuned metrics, intent decomposition and reasoning accuracy, and intent optimization performance.

Intent-Based Networking (IBN) enables the automatic deployment, correction, and optimization of network infrastructure configurations based on business intentions, thereby forming a closed-loop, autonomous, and business-centric network system. The comprehensive capture and accurate understanding of business intents are prerequisites for IBN, which, however, are challenging due to the inherent complexity and the temporal-spatial inconsistency of business objectives across diverse stakeholders. To this end, this paper introduces a hypergraph theory to represent multi-perspective intents in network businesses from a holistic viewpoint and proposes a Heterogeneous Isolated Graph Information Aggregation (HIGIA) model, unifying the following five key aspects. To express intents, knowledge graphs are employed to represent intents of different entities. Then, to address the semantic, structural, and temporal-spatial differences among diverse businesses, we design a Hybrid Mapping and Sharing Graph Attention Network (HMS-GAT) to capture the commonalities and differences among stakeholders’ demands. Next, to explore the inconsistency in the expression of intents across views, we incorporate the Gale–Shapley algorithm to enhance entity alignment. To address the lack of prior knowledge, bootstrapping is introduced to generate pseudo-alignment seeds for entity alignment; Finally, to mitigate missing or redundant information caused by heterogeneous expectations, we employ graph information aggregation to associate, complete, and refine intent descriptions, thus constructing a holistic hypergraph for business intents. Furthermore, to evaluate the hypergraph’s aggregation quality over all involved stakeholders, we propose information aggregation metrics based on information coverage and refinement. Experimental results demonstrate that HIGIA effectively captures service intents in IBN and provides a novel approach for multi-view heterogeneous intent aggregation.

Vehicular networks should be with great potentials to coordinate traffic scheduling and ensure road safety, where cloud-edge-end vehicular networks have been as promising paradigms to improve vehicle scheduling efficiency according to user task intents. However, as user demands become increasingly complex and diverse, task intent decomposition is crucial for handling the diversity of task intents and the complexity of their content. Furthermore, the dynamic changes in task intents and vehicular network node resources lead to uncertainty in the task execution, which significantly reduces vehicle scheduling efficiency. In this paper, we present an intent-driven task-oriented resource collaboration framework, referred to as ITRC, which consists of the intent, policy, and infrastructure layers from a top to bottom perspective. Specifically, we propose a coarseto-fine complex intent decomposition algorithm assisted by a generative pre-trained transformer. To mitigate hallucination during the decomposition, a hybrid hallucination suppression mechanism is introduced based on similarity analysis and natural language inference. Furthermore, the task-resource uncertainty is solved using a maximum likelihood estimation approach, and an efficient optimal allocation algorithm is proposed for dynamic task scheduling. Extensive simulations demonstrate that the proposed algorithm consistently outperforms compared baseline methods across multiple metrics. In terms of quality of service, it reduces end-to-end latency by 60% to 89%; in terms of resource utilization, it achieves improvements ranging from 5% to 110%. For task distribution balance, the algorithm significantly reduces the variance of resource allocation across nodes to mitigate load imbalance, with the standard deviation decreasing by 38% to 87%. In terms of execution efficiency, the proposed algorithm maintains the shortest running time across all task scales and avoids the exponential time complexity typically observed in traditional optimization algorithms, demonstrating strong scalability and real-time performance.

With the construction of low-earth orbit (LEO) satellite constellations, ubiquitous connectivity has been achieved. Terrestrial networks (TNs), such as cellular networks, are mainly deployed in specific urban areas and use licensed spectrum. However, in remote areas where terrestrial infrastructure is sparse, licensed spectrum bands are often underutilized. To accommodate the increasing communication needs, non-terrestrial networks (NTNs) can opportunistically access this idle spectrum to improve spectrum efficiency via spectrum sharing (SS). Therefore, bringing NTNs to a shared spectrum with TNs can improve network capacity under reasonable interference management. In satellite-terrestrial integrated networks (STINs), the comprehensive coverage of a satellite and the unbalanced communication resources of STINs make it challenging to manage mutual interference between NTN and TN effectively. This article presents the fundamentals and prospects of SS in STINs by introducing four SS frameworks, their potential application scenarios, and technical challenges. Furthermore, advanced SS approaches related to interference management in STINs and performance metrics of SS in STINs are introduced. Moreover, a preliminary performance evaluation showcases the potential for sharing the spectrum between NTN and TN. Finally, future research opportunities for SS in STINs are discussed.