As satellite networks have played an indispensable role in many fields, how to integrate them with terrestrial networks (e.g., the Internet) has attracted significant attention in academia. However, it is challenging to efficiently build such an integrated network, since terrestrial networks are facing a number of serious problems, and since they do not provide good support for heterogeneous network convergence. In this article, we propose a flexible network architecture, HetNet, for efficient integration of heterogeneous satellite-terrestrial networks. Specifically, the HetNet synthesizes Locator/ID split and Information-Centric Networking to establish a general network architecture. In this way, it is able to achieve heterogeneous network convergence, routing scalability alleviation, mobility support, traffic engineering, and efficient content delivery. Moreover, the HetNet can further improve its network elasticity by using the techniques of Software-Defined Networking and Network Functions Virtualization. In addition, to evaluate the HetNet performance, we build a proof-of-concept prototype system and conduct extensive experiments. The results confirm the feasibility of the HetNet and its advantages.

Low Earth Orbit (LEO) satellite networks have recently been regarded as a promising solution to provide ubiquitous user access and flexible content delivery. To meet the increasing demands of satellite services, multipath routing is leveraged to transmit each flow via multiple transmission paths concurrently. However, dynamically changed satellite topologies have brought challenges to multipath route planning and traffic splitting among different paths. Thus, in the paper, we propose a GNN-enabled Multipath Routing (GMR) scheme to maximize the network efficiency. Particularly, we firstly formulate the mutipath routing issue as a stochastic optimization problem under the bandwidth limitation and flow conservation constraint, and further present a Link Disjoint Multipath Routing (LDMR) scheme for the central route calculation, where available transmission paths and uneven traffic density are jointly considered to maximize the link utilization. Then, to balance the load distribution of different paths, a GNN-based MultiPath Traffic Engineering (GNN-MPTE) algorithm is designed for dynamic flow splitting based on estimated path quality. Finally, we implement the proposed GMR scheme and corresponding algorithms in Network Simulator NS-3 and make comparisons with other benchmarks. Simulation results demonstrate that the proposed GNN-MPTE can be extended to arbitrary inclined/polar orbit constellations without repetitive training, and significantly prompt the transmission quality including average delay, throughput, and flow completion ratio.

Edge caching has been regarded as a promising technique for low-latency, high-rate data delivery in future networks, and there is an increasing interest to leverage Machine Learning (ML) for better content placement instead of traditional optimization-based methods due to its self-adaptive ability under complex environments. Despite many efforts on ML-based cooperative caching, there are still several key issues that need to be addressed, especially to reduce computation complexity and communication costs under the optimization of cache efficiency. To this end, in this paper, we propose an efficient cooperative caching (FDDL) framework to address the issues in mobile edge networks. Particularly, we propose a DRL-CA algorithm for cache admission, which extracts a boarder set of attributes from massive requests to improve the cache efficiency. Then, we present an lightweight eviction algorithm for fine-grained replacements of unpopular contents. Moreover, we present a Federated Learning-based parameter sharing mechanism to reduce the signaling overheads in collaborations. We implement an emulation system and evaluate the caching performance of the proposed FDDL. Emulation results show that the proposed FDDL can achieve a higher cache hit ratio and traffic offloading rate than several conventional caching policies and DRL-based caching algorithms, and effectively reduce communication costs and training time.

Ubiquitous Internet of Things (IoT) devices have fueled plenty of innovations in the emerging network paradigms. Among them, IoT edge caching has emerged as a promising technique to cope with the explosive growth in network data traffic, with Quality of Service (QoS) improved and energy saved. However, the intrinsic storage limitations of the edge servers poses a critical challenge for the IoT edge caching system. Enabling edge servers to cooperate with each other can provide a potential perspective to improve the edge storage utilization widely discussed. Nevertheless, it also incurs an additional communication overhead, eventually making the caching system more complex. As a result, how to perform an efficient cooperative caching becomes a critical issue. Thus, in this paper, we propose a deep reinforcement learning-based cooperative edge caching approach, which allows the distributed edge servers to learn to cooperate with each other. Specifically, edge servers determine their cache actions based on the local caching state. After that, the centralized remote server evaluates these actions and feeds back the evaluation results to edge servers for subsequent caching actions optimization. We show that, by designing an appropriate reward function, our approach promotes cooperation between edge servers as well as improving the system hit rate. On this basis, we consider a practical and reasonable scenario with inconsistent data item size and propose a novel multi-agent actor-critic caching algorithm. Extensive simulation results demonstrate the performance improvement using our proposed solution over three other caching algorithms.

The Internet has achieved unprecedented success in human history. However, its original design has encountered many challenges in the past decades due to the significant changes of context and requirements. As a result, the design of future networks has received great attention from both academia and industry, and numerous novel architectures have sprung up in recent years. Among them, the locator/identifier (Loc/ID) split networking is widely discussed for its decoupling of the overloaded IP address semantics, which satisfies several urgent needs of the current Internet such as mobility, multihoming, routing scalability, security, and heterogeneous network convergence. Hence, in this paper, we focus on Loc/ID split network architectures, and provide a related comprehensive survey on their principles, mechanisms, and characteristics. First, we illustrate the major serious problems of the Internet caused by the overloading of IP address semantics. Second, we classify the existing Loc/ID split network architectures based on their properties, abstract the general principle and framework for each classification, and demonstrate related representative architectures in detail. Finally, we summarize the fundamental features of the Loc/ID split networking, compare corresponding investigated architectures, and discuss several open issues and opportunities.

Since Internet of Things (IoT) communications can enjoy many advantages brought by content-centric networking (CCN) in nature, there is an increasing interest on their integration for better information retrieval and distribution. Nevertheless, different from the conventional multimedia traffic of which contents are hardly changed, IoT data are always transient and updated by their producers according to the actual situation. As a result, if without any effective countermeasures, outdated copies are inevitably stored by CCN routers and then distributed to the associated consumers, degrading both caching efficiency and user experience. In fact, most of related policies take little account of information freshness for cached contents, and how to tackle transient IoT data in CCN is still an ignored but crucial issue required for further explorations. Therefore, in this article, we propose an efficient popularity-based cache consistency management scheme, which aims to guarantee freshness of IoT data returned by on-path routers and avoid heavy signalling costs introduced at the same time. Extensive simulations were performed under both real-world scare-free and binary-tree topologies, and corresponding results have proved the efficiency of the proposed scheme in timely evictions of outdated IoT data stored by CCN in-network caching.