Uncrewed aerial vehicle (UAV) has emerged as a promising solution for automating railway inspections due to its high mobility, flexible deployment, and reduced labor cost. In this paper, we investigate UAV-assisted railway inspections, which include object recognition, humidity monitoring, and critical infrastructure modeling, each with distinct data volumes and computational requirements. Particularly, we introduce a UAV-assisted railway inspection framework. Different types of sensors are divided into several clusters. The UAV departs from the hive, flies over each cluster to collect their computational requirements, and performs task offloading before returning to the hive. This process is formulated as a joint optimization problem of trajectory planning and task offloading to minimize the weighted sum of latency and energy consumption. Considering the constrained computing and storage capabilities of UAVs, it is crucial but challenging to develop a lightweight yet high-performing solution for the multi-objective optimization problems. As such, a novelArtificial General Intelligence (AGI)-orientedTransformer (AoT) algorithm is proposed to solve the optimization problem. It uses an encoder-only architecture to process either sensor location or task features, and then directs the encoded outputs to different output heads to make decisions on UAV trajectory and task offloading. Simulation results demonstrate that the proposed AoT algorithm outperforms benchmark algorithms in terms of trajectory length and average offloading cost.

The increase of bandwidth-intensive applications in sixth-generation (6 G) wireless networks, such as real-time volumetric streaming, and multi-sensory extended reality, demands intelligent multicast routing solutions capable of delivering differentiated quality-of-service (QoS) at scale. Traditional shortest-path and multicast routing algorithms are either computationally prohibitive or structurally rigid, and they often fail to support heterogeneous user demands, leading to suboptimal resource utilization. Neural network-based approaches, while offering improved inference speed, typically lack topological generalization and scalability. To address these limitations, this paper presents a graph neural network (GNN)-based multicast routing framework that jointly minimizes total transmission cost and supports user-specific video quality requirements. The routing problem is formulated as a constrained minimum-flow optimization task, and a reinforcement learning algorithm is developed to sequentially construct efficient multicast trees by reusing paths and adapting to network dynamics. A graph attention network (GAT) is employed as the encoder to extract context-aware node embeddings, while a long short-term memory (LSTM) module models the sequential dependencies in routing decisions. Extensive simulations demonstrate that the proposed method closely approximates optimal dynamic programming-based solutions while significantly reducing computational complexity. The results also confirm strong generalization to large-scale and dynamic network topologies, highlighting the method's potential for real-time deployment in 6 G multimedia delivery scenarios. Code is available athttps://github.com/UNIC-Lab/GNN-Routing.

The rapid growth of mobile-based global live streaming services has intensified the challenge of delivering high-quality, real-time video transmission, particularly due to the mismatch between diverse network requirements and rigid resource adaptation strategies. Traditional multipath transmission approaches often lack the dynamic adaptability needed to support service diversity, with isolated path selection leading to resource contention and static or coarse-grained allocation mechanisms failing to respond promptly to network changes. These limitations negatively impact both service quality and overall resource utilization. To address these challenges, this paper presents a flexible real-time service transmission system. Specifically, the system introduces a service diversity-aware mechanism coupled with collaborative optimization of network resource paths, enabling high-quality differentiated transmission services. Furthermore, a dynamic routing optimization algorithm is proposed, leveraging In-band Network Telemetry (INT) technology to monitor network resources in real time and flexibly generate optimal routing strategies. We conducted long-distance (over 2000 kilometers) cross-domain testing in real-world large-scale Information Service Providers (ISPs) networks. Experimental results demonstrate that our solution can operate effectively in existing solutions while outperforming current approaches in terms of Quality of Service (QoS).

Multipath transmission offers bandwidth aggregation capabilities for mobile networks. However, path heterogeneity and user mobility often lead to increased packet out-oforder (OFO) rate, causing buffer blocking, reduced throughput, and degraded transmission quality. To mitigate the OFO effect in multipath transmission, this paper proposes LooM, a learning-based multipath scheduler. LooM is designed to optimize throughput and OFO rate, employing a learning-based scheduling strategy to achieve the optimal packet scheduling under fluctuating paths. Particularly, LooM employs singleround scheduling as its basic unit, calculating the number of OFO packets across scheduling units to dynamically set path blocking delay, thereby adjusting packet transmission order to ensure in-order delivery. Simulation results show that, compared to traditional scheduling algorithms, LooM reduces the OFO rate by 16% while maintaining high throughput and achieving a lower packet loss rate.

Deep learning plays increasingly important role in future wireless network management and optimization. Existing training methods such as label-based supervised learning and label-free learning have inherent limitations. The performance of supervised learning is limited by labels, while label-free training methods require extensive exploration. To address these limitations, this paper proposes a novel mixture of gradients (MoG) method, which integrates gradients from different sources within the training process in order to improve the convergence performance of neural networks (NNs). Particularly, MoG is a modular, plug-and-play solution requiring no structural modifications to existing NNs. Its implementation necessitates only minor modifications to the loss function, where the label-based supervised loss is combined with a label-free loss through weighted summation. The label-free loss can be either unsupervised loss or reinforcement learning loss. This flexibility allows seamless integration into nearly all NN-based methods, making it applicable to a wide range of wireless optimization problems with minimal implementation cost. Extensive simulations across multiple classic wireless scenarios demonstrate that MoG can significantly enhance the performance of NN decision-making, leading to higher transmission rates.

To fulfill future diverse user requirements, 6G networks are envisioned to provide everyone-centric customized services ubiquitously and precisely. However, the diversity in user requirements and the heterogeneity in network resources challenge conventional network operators in network management and service provision. In this article, we investigate the artificial intelligence (AI) service provision in the multilayer heterogeneous network. To provide ubiquitous intelligence to users with different computing requirements, an intelligence-native network architecture is designed. Based on the proposed architecture and the AI model stitching mechanism, we formulate the joint AI provision and access selection problem as a mixed integer nonlinear programming (MINLP) problem to maximize the average user satisfaction value and user satisfaction rate. Then, a heuristic solution based on Dung Beetle algorithm is proposed to optimize the AI model selection, AI service deployment, user access, and stitching coefficient jointly. Extensive simulations are conducted to evaluate the performance of our proposed architecture and algorithm.

Presents corrections to the paper, (Correction to “Toward Native Intelligence: An Efficient and Flexible AI Services Provision Scheme in Multilayer Heterogeneous Networks”).

In the current era of rapid advancements in Artificial Intelligence of Things (AIoT), with the increase in cloud data center operations and the limited security computing capabilities of AIoT terminal devices, link flooding attack (LFA) has emerged as a complex and stealthy new threat. However, the existing defense methods based on programmable networks usually have issues of slow offline inference and delayed defense activation. To address these issues, we propose a collaborative programmable defense framework (CPDTG) to predict, detect, and mitigate LFA. First, an early attack intention prediction model based on temporal graph learning (TGL) is proposed to accurately locate attacks and promptly activate defenses to save resource consumption during idle time. Second, a switch-native clustering algorithm independent of the global perspective is introduced for line-speed detection of LFA. The unsupervised algorithm does not rely on labeled datasets for training, which enhances its robustness against differentiated attack scenarios. Third, we propose a distributed defense mechanism that achieves the pushback deployment of adaptive rate-limiting strategies. Compressing the potential attack vector space effectively increases the difficulty of launching rolling attacks. Extensive experimental validation demonstrates the effectiveness of the proposed CPDTG in predicting and defending against LFA.

The surge in mobile application services has led to diversified traffic and increased demands on network resources. Traditional multipath algorithms, designed for resource integration through subflow scheduling across paths, struggle with disharmonious transmission caused by terminal mobility and differentiated path resources. Especially when differentiated services are transmitted concurrently, disharmonious transmission can give rise to resource contention, causing a large number of subflows to congest a single path and leading to performance degradation. To mitigate these challenges, this paper introduces HarmonyPath, a fine-grained flexible multipath transmission mechanism that can ensure harmonious resource occupation. Specifically, HarmonyPath firstly employs an in-band telemetry protocol to gather path resource information, generating a network resource distribution map. Based on this map, it flexibly allocates path resources according to the network resource distribution and service requirements. Then, HarmonyPath establishes a collaborative matching model for service demands and path resources. Through matrix transformation and calculation, it rapidly generates and deploys the scheduling strategy. To further alleviate service contention, HarmonyPath employs heuristic algorithms to optimize the scheduling strategy and achieve precise multipath transmission. Experiments demonstrate that HarmonyPath surpasses traditional algorithms in the multipath transmission of differentiated services, offering flexible service resource guarantees and enhancing network resource utilization efficiency.

Delay-sensitive applications like telemedicine and VR/AR intensify competition for network resources and elevate congestion risks, particularly in mobile networks with highly dynamic link conditions. Traditional end-to-end congestion control methods suffer from prolonged response times, rendering them ineffective for Delay-sensitive applications. To this end, this paper proposes a novel In-Network Congestion Control (INCC) mechanism that accelerates congestion control by enabling network nodes to proactively identify bottlenecks and promptly notify end-hosts. Unlike traditional end-host-centric approaches, INCC facilitates collaborative congestion decision-making between end-hosts and in-network unit. INCC classifies congestion into two phases: “yellow” and “red” based on the local queue length bottleneck awareness and global congestion flow bottleneck statistics. For the “yellow” local congestion phrase, we design an in-network local control algorithm that performs proactive packet dropping and rate adjustment to mitigate emerging congestion. For the “red” global congestion phrase, we design an end-host and network cooperative global congestion control algorithm to make precise sending rate adaptation by proactive bottleneck awareness. We implement INCC via Linux kernel modifications and design three experiments to compare with Cubic, NewReno, and BBR. Experimental results demonstrate INCC has good performance on round-trip time and throughput, achieving 99.03% scheduling fairness in flow contention scenarios. Additionally, INCC has low execution overhead on CPU utilization and realize microsecond computational latency.

UAVs can significantly improve the access networks of next-generation mobile networks during the building of smart cities. Drones equipped with base stations can expand the coverage of communication networks and assist more users’ devices to access the 5G/6G network, in which reliable authentication for drones becomes essential. However, traditional authentication methods still utilize the overt channel to transmit identity and key information, which are vulnerable and very easy to be eavesdropped, hijacked, and forged by malicious third parties. Therefore, this paper proposes an authentication scheme (CCRA). It includes 1) covert channels to assist authentication and key negotiation, and 2) a covert channel algorithm (EIDOP). Specifically, CCRA transmits fake identity information, part of the key information, and unimportant data in the overt channel, while using the covert channel to transmit important data and another part of the key for authentication and key negotiation to enhance the reliability of authentication. In addition, this paper proposes an algorithm called EIDOP based on the order of packet delay intervals to establish the covert channel for embedding and hiding important information. Finally, we conduct experiments on physical machines and compare EIDOP with other covert timing mechanisms to conclude that our algorithm has better concealment and latency overhead and still guarantees a very low BER under such circumstances.

Integrated Sensing and Communication (ISAC) introduces greater challenges to network transmission in terms of delay, bandwidth, and reliability. Achieving stable and efficient congestion control is a critical issue in emerging ISAC scenarios. However, many traditional congestion control algorithms primarily focus on transmission efficiency but perform poorly in ensuring fairness between different data flows. To address this limitation, this paper proposes a queuing-aware fair congestion control (Q-FCC) solution for ISAC. In particular, Q-FCC incorporates a queue status monitoring module which can provide real-time feedback on the queuing delays at targeted network switches. Additionally, this paper analyzes the traditional BBR algorithm and identifies an inherent flaw: longer RTT flows have a higher bandwidth gain coefficient compared to shorter RTT flows, leading to unfairness. Based on this insight, Q-FCC introduces bandwidth gain factor. Q-FCC uses the queue status monitoring module to categorize data flows into three types and interacts with bursty flow endpoints via ACK packets to assist them in calculating the bandwidth gain factor, which enables the control of the transmission rate. Finally, the algorithm was implemented in the Linux kernel. The results of the semi-physical simulation show that Q-FCC outperforms the traditional BBR and CUBIC algorithms in terms of bandwidth fairness and transmission stability, respectively.

With the advent of the Industry 4.0 era, the widespread deployment of Automated Guided Vehicles (AGVs) in factories has enabled them to serve as sensor relays, assisting in collecting sensor data in areas with poor signal quality. Traditionally, the objective of sensor data collection has been primarily to reduce the delay in data acquisition. However, latency alone offers an incomplete reflection of the significance of sensor data to industrial tasks. Value of information (VoI) has emerged as a novel metric that more accurately reflects the impact of sensor data on the performance of upstream tasks. In this background, we introduce an innovative AGV-assisted sensor data collection strategy to minimize the loss of sensor data VoI. This strategy encompasses the selection of data fusion nodes, choice of transmission modes, and AGV path planning. We introduce a new metric called structural value entropy, which effectively reduces VoI loss during the data fusion process, and through the design of a metaheuristic algorithm based on ant colony optimization, achieves the selection of transmission modes and the planning of AGV paths with minimal VoI loss. Simulation experiments validate the effectiveness of the proposed strategy in maintaining VoI, demonstrating significant performance enhancements and acceptable convergence speed compared to baseline strategies, affirming the strategy's efficiency and feasibility in handling large-scale sensor data collection tasks.

Due to the stringent latency requirements for computationally intensive rendering in virtual reality (VR) transmission and the limitations of computational resources on VR devices, extensive research has focused on task offloading with joint communication and computing resource scheduling to address these issues. Traditional model-based theoretical methods face challenges with long online processing times, while data-driven methods lack interpretability. This paper proposes a knowledge-driven rendering task offloading strategy for immersive wireless VR with mobile edge computing (MEC). The rendering approaches include local, MEC, and collaborative offloading between VR devices and MEC servers. First, we formulate an optimization problem to maximize user quality of experience (QoE), which is defined as the weighted sum of latency and video resolution. To solve the optimization problem, we propose a knowledge-driven belief propagation (KD-BP) algorithm where the structure of the BP algorithm is regarded as knowledge. Specifically, the operations with high computational complexity in the BP algorithm are replaced by a deep neural network, termed the knowledge-fused deep learning (DL) method. Finally, numerical results show that when the number of users reaches 10, the proposed KD-BP algorithm significantly reduces online processing latency and closely matches the convergence speed and performance compared to the BP algorithm.

The convergence of Blockchain and Internet of Things (BIoT) is fully considered as a paradigm for mitigating threats related to the trust, security, and privacy of Internet of Things (IoT) data. However, because the bandwidth across nodes and time varies in practical IoT networks, it is difficult for existing BIoT mechanisms guarantee blockchain consensus performances. The consensus time could become long owing to low-bandwidth nodes taking longer to download blocks than high-bandwidth nodes. Conventional wisdom holds that removing low-bandwidth nodes can decrease the consensus time, but the nodes could have high-bandwidth at another time owing to bandwidth variability; thus, kicking which nodes out of the consensus is a great challenge. In this article, a novel lightweight BIoT convergence (namely, E-Chain) is proposed to overcome bandwidth variability. The E-Chain first decouples the blockchain into on-chain validating and off-chain voting components. In the off-chain voting part, each node incurs a one-bit communication overhead for voting on a block based on a reputation index. This voting component does not need to download the full content of the block, and is therefore not affected by bandwidth variability. The reputation index was formulated using a rating algorithm with multidimensional IoT network metrics. In addition, the voting mechanism is secure and can still reach the correct consensus when suffering from byzantine attacks. By contrast, a block is validated and stored in a dispersed manner in the on-chain validating part. The E-Chain performances were then evaluated and compared with state-of-the-art mechanisms. Experimental results show that the E-Chain mechanism can significantly decrease both the consensus time and memory resources, and incur an acceptable memory overhead for resource-constrained IoT nodes.

This paper proposes a novel knowledge-driven approach for resource allocation in wireless networks using the graph neural network (GNN) architecture. To meet the millisecond-level timeliness and scalability required for the dynamic network environment, our proposed approach, named UWGNN, incorporates the deep unrolling of the weighted minimum mean square error (WMMSE) algorithm, referred to as domain knowledge, into GNN, thereby reducing computational delay and sample complexity while adapting to various data distributions. Specifically, by unrolling WMMSE algorithm into a series of interconnected submodules, UWGNN aligns closely with the optimization steps of the algorithm. Our analysis reveals the effectiveness of the deep unrolling method within UWGNN, which decomposes complicated end-to-end mappings, leading to a reduction in model complexity and parameter count. Experimental results demonstrate that UWGNN maintains optimal performance with computation latency 3 to 4 orders of magnitude lower than the WMMSE algorithm and exhibits strong performance and generalization across diverse data distributions and communication topologies without the need for retraining. Our findings contribute to the development of efficient and scalable wireless resource management solutions for distributed and dynamic networks with strict latency requirements.

Multipath transmission brings strong bandwidth aggregation capability for services in wireless networks. Nonetheless, the heterogeneous nature of paths and the motion of terminals results in varying transmission delays, leading to out-of-order (OFO) delivery and transmission quality decrease. Traditional algorithms, limited in their scope, fail to strike a balance between high bandwidth and low OFO extent. Recent studies have focused on utilizing learning algorithms to find a multi-performance joint optimal transmission strategy. In light of this, this paper proposes a framework called DRL-based OFO-Friendly Multipath Scheduling (DOFMS) to ensure high bandwidth and low OFO extent transmission in mobile heterogeneous networks. In particular, the framework introduces a novel OFO evaluation index to assess the degree of OFO more accurately. To achieve elastic scheduling, the framework employs the Double Deep Q Network (DDQN) to dynamically regulate the scheduling ratio. Recognizing the dynamic and unpredictable nature of path delays, an asynchronous module is introduced to enhance learning accuracy. Experimental results demonstrate that the framework reduces the OFO rate by 25% compared to traditional bandwidth aggregation algorithms, while maintaining low bandwidth and packet loss rates. Furthermore, compared to conventional OFO avoidance algorithms, the framework improves bandwidth by 4% and reduces fluctuation by 90%.

Semantic communication (SC) is one of the promising solutions for future wireless communications due to its superior transmission efficiency. However, the semantic information cannot be transmitted accurately under noisy channels by the existing methods. For this reason, we propose a fairness-based transmission strategy for STAR-RIS assisted SC systems. On this basis, we investigate two operating protocols of STAR-RIS, energy splitting (ES) and mode switching (MS). More specifically, we maximize the minimum signal-to-noise ratio (SNR) of the users by jointly optimizing the active beamforming and the passive beamforming under the constraint of limited power at the base station (BS). To tackle this max-min optimization problem, for ES, we develop a double-loop iterative algorithm by using the successive convex approximation (SCA) and penalty function methods. For MS protocol, we further add an additional penalty in the objective function to address the optimization problem. Moreover, we rigorously prove that the proposed algorithm can converge to a locally optimal solution. At last, we conduct various experiments to verify the performance of the proposed algorithms. Simulation experiments demonstrate that our algorithm outperforms other benchmark methods in fairness and semantic similarity.

The rapid growth of cloud data centers has reduced the organizational cost of botnets while significantly increasing the risk of Link Flooding Attack (LFA) to network service providers. The attacker utilizes legitimate low-rate flows with non-spoofing addresses to congest the bottleneck link, which aims to disconnect the target area. To overcome certain hitches of traditional defenses, we propose an in-network collaborative link flooding attack defense scheme (ICDLFA) to implement detection and mitigation. First, an adaptive anomaly detection algorithm, namely constrained clustering inference, is proposed to detect malicious flows at line rate without pre-trained models, which improves the adaptability of the detection algorithm to different scenarios. In particular, the anomaly detection algorithm is executed independently on a programmable switch, which significantly improves the detection efficiency by escaping the global view of the controller. Second, the collaborative mitigation mechanism propagates the traffic limitation policy to the vicinity of the attack source, which alleviates the impact on legitimate flows. In addition, the distributed defense can effectively limit the flexible transformation of attack vectors and reduce the possibility of launching subsequent attacks. Simulation results demonstrate that our in-network LFA defense scheme could accurately and effectively detect and mitigate LFA, quickly adapt to attack changes, and reduce network resource overhead.

Task offloading is a potential solution for computation-intensive vehicular applications due to limited on-board computing resources. However, traditional model-driven methods are hindered by long online processing time, while data-driven methods are deficient in interpretability and generalizability. To overcome this challenge, this paper formulates the resource allocation for task offloading in connected autonomous vehicles (CAVs) as a multi-objective optimization problem, and proposes a novel knowledge-driven algorithm that integrates both model-driven and data-driven methods. Specifically, the framework of a model-driven alternating minimization (AM) algorithm, which solves the formulated problem via alternatively optimizing power allocation subproblem and bandwidth and CPU frequency allocation subproblem, is regarded as knowledge. Inspired by such knowledge, our proposed knowledge-driven neural network consists of two long short term memory networks (LSTMs) to alternatively updating these two subproblems. Furthermore, to get away from the local optimum usually occurred in the AM algorithm, our proposed knowledge-driven neural network updates network parameters with the global loss function. Simulation results demonstrate that our method outperforms both the AM algorithm and the LSTM without knowledge.

Low Earth Orbit (LEO) satellite networks are gaining more interest as a crucial component of future space-air-ground integrated networks. However, the traditional IP-based communication mode is not well-suited for supporting low-cost and highly reliable routing in inter-satellite packet transmission. On one hand, the centralized IP address allocation model increases server resource consumption and also leads to excessive communication between satellites. On the other hand, the single-path routing feature of IP cannot guarantee timely recovery of the path in the event of a satellite node failure. Therefore, this paper proposes a mechanism called Relative Position-based Efficient Routing (RP-ER) for LEO satellite networks. RP-ER can achieve distributed address allocation at a low cost and enable redundant routing in the event of a path failure. In particular, RP-ER first establishes the relative position model based on the laws of satellite motion. Then, the central satellite broadcasts the address allocation instructions, and each satellite reacts and disperses packets. Finally, these satellites allocate independent addresses and generate primary and backup routes simultaneously. Compared to other routing mechanisms, RP-ER utilizes fewer satellite resources during the network addressing phase. Additionally, it can establish redundant high-quality paths during the communication phase with a concise routing table.

Multipath transmission can effectively utilize multiple paths and provide high Quality of Service (QoS) performance for video streaming services. However, when multiple video streaming services are transmitted simultaneously, the network is prone to the preemption of path resources by these services, which can reduce QoS. This is because the traditional multipath scheduling algorithm aims to achieve high QoS performance for all services. Therefore, this paper proposes a Friendliness Balancing based Multipath Scheduling algorithm (FBMS) to maximize the utilization of path resources and achieve a friendly and balanced consumption of network resources. First, FBMS obtain the path resources and service requirements to build adaptation matrices. Then, FBMS considers the friendliness balancing value as the optimization objective and utilizes a two-stage evaluation-based Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) algorithm to assess each path. Finally, FBMS preferentially selects a single transmission path that meets the service requirements in order to avoid resource competition. If there is no qualified path, FBMS will balance the demands of each service, integrate them friendly, and schedule multiple paths for transmission. Experiments show that, compared to traditional scheduling algorithms, FBMS improves path resource utilization, reduces competition among services, and ensures high QoS performance for each service.

With the development of economic globalization and emerging applications such as transnational communication and webcasting, inter-cloud link transmission has become a key factor for green networking. Optimized transmission policies can effectively reduce network energy consumption and improve resource utilization by dynamically adjusting the optimal network paths. In this paper, we collect first-hand and over-million-level network datasets from practical nodes on three continents (Asia, Europe, and North America), and analyze the characteristics of international links among cloud centers in different continents. According to the actual test results, we discover that the network transmission quality strongly correlates with factors such as time zone and cloud service provider. Besides, we conclude that the quality of inter-cloud networks can be effectively improved according to regional activity and triangular routing. Based on the in-depth observation, we further discuss the optimization directions of network transmission and provide relevant suggestions. This work is of significant reference value for research on green transmission of inter-cloud links.

Deep learning has been successfully adopted in mobile edge computing (MEC) to optimize task offloading and resource allocation. However, the dynamics of edge networks raise two challenges in neural network (NN)-based optimization methods: low scalability and high training costs. Although conventional node-output graph neural networks (GNN) can extract features of edge nodes when the network scales, they fail to handle a new scalability issue whereas the dimension of the decision space may change as the network scales. To address the issue, in this paper, a novel link-output GNN (LOGNN)-based resource management approach is proposed to flexibly optimize the resource allocation in MEC for an arbitrary number of edge nodes with extremely low algorithm inference delay. Moreover, a label-free unsupervised method is applied to train the LOGNN efficiently, where the gradient of edge tasks processing delay with respect to the LOGNN parameters is derived explicitly. In addition, a theoretical analysis of the scalability of the node-output GNN and link-output GNN is performed. Simulation results show that the proposed LOGNN can efficiently optimize the MEC resource allocation problem in a scalable way, with an arbitrary number of servers and users. In addition, the proposed unsupervised training method has better convergence performance and speed than supervised learning and reinforcement learning-based training methods. The code is available at https://github.com/UNIC-Lab/LOGNN.

As a fundamental problem, many studies are dedicated to the optimization of signal-to-interference-plus-noise ratio (SINR), in a multi-user setting. Although traditional model-based optimization methods achieve strong performance, it has high complexity. To fully leverage the high performance of traditional methods and the low complexity of the neural network (NN) based method, a knowledge distillation (KD) based algorithm distillation (AD) method is proposed in this paper, where traditional optimization methods serve as "teachers" for NN "students", improving unsupervised and reinforcement learning. This approach tackles common issues: unattainable optimal labels, overfitting, and inefficient training. Simulations confirm the advantages of AD, paving the way for traditional optimization integration with NNs in wireless communication.

Abstract It is well known that the Sixth Generation (6G) communication system integrating multiple access networks promotes the internet of everything world-widely. However, due to the differentiated underlying network protocols, it is difficult to find a general authentication solution to support various authentication methods in different access networks. Blockchain is a new technology that supports network heterogeneity, which provides a potential solution for differentiated authentication. In this paper, we propose a blockchain-based differentiated authentication mechanism for 6G Heterogeneous Networks (HetNets), which can efficiently authenticate user identities through scheduling different authentication methods. Particularly, we analyze the authentication architecture of 6G HetNets and put forward a blockchain-based differentiated authentication framework. Besides, to improve the scalability of user authentication, it is the first time to use various blockchain authentication contracts to represent different authentication methods. Meanwhile, a differentiated authentication management contract is proposed to uniformly manage different authentication contracts to realize differentiated identity authentication. Based on the evaluation of the prototype system, the proposed mechanism can dynamically provide differentiated authentication services (e.g. EAP-MD5, 5G-AKA) with low additional time (milliseconds levels) cost.

With the continuous development of autonomous vehicles, telemedicine, digital media and other time-sensitive applications, a soaring number of network services have high demand for the quality of service (QoS) with extra low delay and jitter. Traditional network architecture only offers best-effort services which cannot meet the stringent delay and jitter requirements. In this paper, we propose a resilient-priority queue scheduling algorithm (RPQ) for delay-sensitive services. RPQ can guarantee stable delay in a fine-grained manner. Particularly, on the premise of meeting the delay requirements of high priority streams, RPQ can give consideration to the delay requirements of lower priority streams depending on its resilient scheduling mechanism. We implement RPQ on programmable switch. The experimental results show that RPQ not only guarantees QoS with low delay and low jitter for delay-sensitive streams but also improves network throughput by comparing with the existing solutions, i.e., SP-PIFO and WRR.

Telemedicine services put forward high transmission demands for network transmission, such as low latency and high throughput. However, telemedicine services suffer undesirable latency due to the high re-transmission probability caused by congestion and queuing. To reduce the probability of re-transmission, this paper firstly proposes in-band network telemetry (INT)-based delay-guaranteed transmission framework (IDTF) to make concurrent transmission control. In IDTF, we propose a proximal policy optimization (PPO)-based adaptive multipath concurrent flow scheduling algorithm (PAMA) for control policy adjustment. In detail, PAMA makes a joint minimum optimization with flow scheduling and network resource management to reduce the probability of congestion and long-time queuing. Finally, we implement extensive simulations on a programming protocol-independent packet processors (P4)-based programmable network platform to perform performance analysis. Simulation results show that PAMA outperforms existing classical algorithms in re-transmission rate, round-trip time, and throughput.

Space/aerial-assisted internet of things (IoT) is promising to provide extensive coverage and heterogeneous network services. However, it also faces the risk of eavesdropping attacks due to the peculiarity of highly open transport. In this paper, we propose a combating eavesdropping solution with resilient multipath (CERM) for space/aerial-assisted IoT. Firstly, we analyze the dynamics of space/aerial-assisted IoT and build a betweenness centrality based eavesdropping probability model. Furthermore, we formulate multipath selection problem as an integer optimization by minimizing eavesdropping probability. Based on this, we propose a programmable CERM solution to flexibly schedule multipath traffic to reduce eavesdropping risk. Extensive experimental results verify the proposed CERM solution decreases eavesdropping probability as well as increases transmission throughput compared with the traditional single-path and Round-Robin multipath solutions.

Efficient transmission control is a challenging issue in vehicular networks due to the highly dynamic network environment. In this paper, we propose a Deep reinforcement learning based adaptive Transmission Scheduling Mechanism (DTSM), which is able to adaptively select different transmission control policies based on the current network status and the history data learning. In particular, we first introduce the adaptive transmission scheduling units (ATSU) in both Software-Defined Vehicular Networking (SDVN) controllers and the corresponding base stations. Based on this architecture, we formulate a mathematical model for optimal decision-making in SDVN controllers. Besides, in ATSUs, we proposed a deep Q-learning based transmission control method to dynamically adapt to the time-varying vehicular network scenarios. Simulation results verify that the proposed DTSM solution outperforms the single transmission control method of four existing benchmarks (e.g., TcpVegas, TcpBic, TcpWestwood, TcpVeno) in terms of average throughput and round-trip time.

State-of-the-art mechanisms against eavesdropping first encrypt all packet payloads in the application layer and then split the packets into multiple network paths. However, versatile eavesdroppers could simultaneously intercept several paths to intercept all the packets, classify the packets into streams using transport fields, and analyze the streams by brute-force. In this article, we propose a programming protocol-independent packet processors (P4)-based network immune scheme (P4NIS) against the intractable eavesdropping. Specifically, P4NIS is equipped with three lines of defenses to provide a softwarized network immunity. Packets are successively processed by the third, second, and first line of defenses. The third line basically encrypts all packet payloads in the application layer using cryptographic mechanisms. Additionally, the second line re-encrypts all packet headers in the transport layer to distribute the packets from one stream into different streams, and disturbs eavesdroppers to classify the packets correctly. Besides, the second line adopts a programmable design for dynamically changing encryption algorithms. Complementally, the first line uses programmable forwarding policies which could split all the double-encrypted packets into different network paths disorderly. Using a paradigm of programmable data planes-P4, we implement P4NIS and evaluate its performances. Experimental results show that P4NIS can increase difficulties of eavesdropping and transmission throughput effectively compared with state-of-the-art mechanisms. Moreover, if P4NIS and state-of-the-art mechanisms have the same level of defending eavesdropping, P4NIS can decrease the encryption cost by 69.85%-81.24%.

It is well known that concurrent multipath transfer (CMT) can improve the transmission rate. However, due to multiple heterogeneous paths from users to the access network, a large number of out-of-order packets significantly degrade the overall transmission reliability. Cybertwin provides a potential solution to alleviate the packet out-of-order problem by accurately detecting and perceiving the path state. In this article, we investigate the data scheduling problem and propose a learning-based cybertwin-driven CMT algorithm to obtain the optimal data scheduling policy. In particular, we first formulate the data scheduling problem as an integer linear programming by taking the QoS metrics into account. To cope with the packet out-of-order problem in CMT, we propose a reliable cybertwin-CMT with deep reinforcement learning (CMT-DRL) algorithm to determine the data scheduling decisions. The proposed algorithm takes multipath throughput, end-to-end delay, and packet loss rate into account. Besides, CMT-DRL adopts an asynchronous learning framework to efficiently execute data collection, packet scheduling, and neural network training in sequence by decoupling model training and execution. We conduct extensive experiments in a P4-based programmable network platform. Experimental results indicate that the CMT-DRL outperforms the existing benchmarks in terms of the number of out-of-order packets, round-trip time, and throughput.

In this paper, we investigate the joint task assignment and resource allocation for deep neural network (DNN) inference in the device-edge-cloud based industrial Internet of things (IIoT) networks. To efficiently orchestrate the limited spectrum and computing resources in IIoT networks for massive DNN inference tasks, a resource management problem is formulated with the objective of maximizing the average inference accuracy while satisfying the quality-of-service of DNN inference tasks. Considering the strict delay requirements of inference tasks, we transform the formulated problem into a Markov decision process, and propose a deep deterministic policy gradient based learning algorithm to obtain the solution rapidly. Simulation results show that the proposed algorithm can achieve high average inference accuracy.

In this paper, we propose a multiobjective optimization framework to jointly optimize power and position of full-duplex (FD) receiver in the covert communication. By introducing a legitimate FD receiver (Bob) with random transmit power, the signal of a legitimate transmitter (Alice) can be transmitted covertly since an eavesdropper (Willie) is confronted with interference uncertainty and makes an incorrect decision for signal detection. Therefore, we optimize the position and the transmit power range of Bob in order to maximize the achievable transmission rate from Alice to Bob and average covert probability at Willie simultaneously. Due to the presence of multiple optimization objectives, the nondominated sorting genetic algorithm II (NSGA-II) is utilized to explore the Pareto front and to give a set of solutions that reveal different tradeoffs between the two conflicting objectives. Simulation results are provided to reveal the Pareto front and to illustrate the effect of transmit power of Alice and Bob on the Pareto front.

The Internet has made a significant success, which is on the basis of TCP/IP stacks. However, due to the dramatic development of the Internet of Things and 5G, giving rise to the continuous expansion of the network scale and the emergence of new applications, it becomes more and more complicated to manage the Internet. Specifically, the best-effort model and the device-centric working manner have become the inhibitors to meet the demands of the intelligent and coordinated transmission under heterogeneous networks in the future. In this paper, we proposed a novel Internet architecture named Smart Integration Identifier Networking (SINET-I) after comprehensively summarizing the related researches of the future Internet. SINET-I enhanced the ability of network automation and realized heterogeneous networks collaboration via introducing intent scheme and making full use of machine learning technologies. The experiment results show that SINET-I performs well in coordinated transmission across different heterogeneous protocols scenario and the available bandwidth of multi-paths is more than 2 times of that of single-path.

With the rapid development of network, network monitoring is a significance means to ensure network security and reliability. In-band network telemetry (INT) can collect items in line-rate, and support large traffic volumes and rates network telemetry. However, existing INT monitoring schemes are quite limited in flexibly expanding the execution monitoring tasks. In this paper, we propose Fast-INT, an efficient network monitoring framework combined with learning. The goal of Fast-INT is to design a light-weight INT network collection framework by quickly implementing dynamic and scalable collection of network status information. In our approach, an INT scheduling algorithm based on reinforcement learning is designed to dynamically deploy and adjust INT monitoring tasks when dealing with network inner change event. Particularly, Fast-INT can implement specific INT monitoring tasks on target point to shorten the time of monitoring and make the network monitoring more efficient. The evaluate results show that Fast-INT has a good performance on network monitoring and achieves the goal of intelligently deploying network monitoring tasks.

Many problems in the Internet of Things (IoT) can be regarded as online optimization problems. For this reason, an online-constrained problem in IoT is considered in this article, where the cost functions change over time. To solve this problem, many projected online optimization algorithms have been widely used. However, the projections of these algorithms become prohibitive in problems involving high-dimensional parameters and massive data. To address this issue, we propose a Frank- Wolfe Adam online learning algorithm called Frank-Wolfe Adam (FWAdam), which uses a Frank-Wolfe method to eschew costly projection operations. Furthermore, we first give the convergence analysis of the FWAdam algorithm, and prove its regret bound to O(T3/4) when cost functions are convex, where T is a time horizon. Finally, we present simulated experiments on two data sets to validate our theoretical results.

In this paper, a comprehensive software-defined networking (SDN) based transmission protocol (SDTP) is presented for fifth generation (5G) communication networks, where an SDN controller gathers network state information from the physical network to improve data transmission efficiency between end hosts, with in-path packet retransmission. In the SDTP, we first develop a new two-way handshake mechanism for connection establishment between a pair of end host. With the aid of SDN control module, signaling exchanges for establishing E2E connections are migrated to the control plane to improve resource utilization in the data plane. A new SDTP packet header format is designed to support efficient data transmission with in-path packet caching and packet retransmission. Based on the new data packet format, a novel in-path receiver-based packet loss detection and caching-based packet retransmission scheme is proposed to achieve in-path fast recovery of lost packets. Extensive simulation results are presented to validate the effectiveness of the proposed protocol in terms of low connection establishment delay and low end-to-end packet transmission delay.

The Internet of Things (IoT) has gained great attention in recent years, due to its significant role in industry innovations and promotions. However, it is still facing many technical challenges before fully gaining ground, mainly resulting from limited computational and energy resources of IoT devices and best-effort underlying network paradigms. Thanks to the emerging edge computing that optimizes the cloud computing by processing data at edge networks, IoT devices can offload computation-intensive tasks to their assigned edge computing servers with response time guaranteed and energy consumption saved. As a result, how to perform task offloading by IoT devices has become a key challenge widely discussed. Nevertheless, most of the existing works focus on the tradeoff between executing a task locally and remotely through techniques, such as optimization and game theory, rather than related theoretical model to analyze communication procedures of offloading policies. Thus, in this paper, we propose a multiqueue model to explore the impact of offloading policies on performance of the IoT devices with their assigned edge computing server. Particularly, we consider two simple policies, namely Locality-First policy and Probability-based policy, and obtain their analytic solution of the task mean response time and energy consumption of the IoT devices and edge computing server. Extensive simulations are performed and related results have proved accuracy of the proposed model.

Internet of Things (IoT) computing offloading is a challenging issue, especially in remote areas where common edge/cloud infrastructure is unavailable. In this paper, we present a space-air-ground integrated network (SAGIN) edge/cloud computing architecture for offloading the computation-intensive applications considering remote energy and computation constraints, where flying unmanned aerial vehicles (UAVs) provide near-user edge computing and satellites provide access to the cloud computing. First, for UAV edge servers, we propose a joint resource allocation and task scheduling approach to efficiently allocate the computing resources to virtual machines (VMs) and schedule the offloaded tasks. Second, we investigate the computing offloading problem in SAGIN and propose a learning-based approach to learn the optimal offloading policy from the dynamic SAGIN environments. Specifically, we formulate the offloading decision making as a Markov decision process where the system state considers the network dynamics. To cope with the system dynamics and complexity, we propose a deep reinforcement learning-based computing offloading approach to learn the optimal offloading policy on-the-fly, where we adopt the policy gradient method to handle the large action space and actor-critic method to accelerate the learning process. Simulation results show that the proposed edge VM allocation and task scheduling approach can achieve near-optimal performance with very low complexity and the proposed learning-based computing offloading algorithm not only converges fast but also achieves a lower total cost compared with other offloading approaches.

Software-defined networking (SDN) enables routing control to program in the logically centralized controllers. It is expected to improve the routing efficiency even in highly dynamic situations. In this article, we make an in-depth observation of practical Internet datasets and investigate the relationship between betweenness centrality and network throughput . Furthermore, we propose a new routing observation factor, differential ratio of betweenness centrality (DRBC), to denote the varying amplitude of betweenness centrality to node degree. We reveal an interesting phenomenon that DRBC is proportional to the routing efficiency when the maximum betweenness centrality varies in a small range. Based on this, a DRBC-based routing scheme is proposed to improve routing efficiency. The experimental results verify that DRBC-based routing can improve the network throughput and accelerate the routing optimization.

Information-Centric Networking (ICN) provides great potential to promote the development of the Internet of Things (IoT) due to its multicast nature and mobility support. However, the stateful forwarding peculiarity introduces new varietal attacks named Interest Flooding Attacks (IFA), which is stealthy but destructive for the resource-limited IoT devices. In this paper, we propose a lightweight BLoom-filter based Attack Mitigating (BLAM) mechanism to reduce the detecting memory cost, while guaranteeing both the detecting accuracy and delay. Specifically, each IoT node employs a small Bloom filter to check attack behaviors instead of the traditional memory-consuming operations, i.e., recording malicious requests. Bloom filter values by hashing the published data names with a set of hash functions, are encapsulated and distributed via a new message named Ba-NACK. Based on this design, two specific schemes are further proposed for the attack detecting and Bloom filter updating. We formulate the memory cost minimum problem and theoretically analyze that BLAM can reduce the memory cost. We also implement BLAM in a realistic network testbed to evaluate its performance. The results show that BLAM reduces the memory cost by 78.6%, and reduces the delay from millisecond to microsecond with slight sacrifice of the accuracy by 0.4% compared with other state-of-the-art mechanisms.

Connected and autonomous vehicles (CAVs) are envisioned as a promising solution integrating the powerful AI and communication technologies to realize fully self-driving. However, there is few vehicular dataset open to study AI assisted self-driving. To make effectively use of AI technologies to optimize self-driving maneuver, we develop an open VeData platform to share the collected datasets. We also develop a Vehicular network Data harvester (VeData), which can collect various vehicular data at an arbitrary frequency. Based on this, we have incrementally collected diversified first-hand data in many different vehicular scenarios, including driving-in-campus, driving-around-campus, driving-in-downtown, and driving-on-highway. More datasets will be collected and shared to promote the research of AI assisted CAVs.

In recent years, the mobile edge computing (MEC) has achieved various of research interests. By offloading data from the user equipments (UEs) to the MEC servers, many computationally demanding applications can be processed at the edge of the mobile networks. However, the data offloading of MEC needs to share the bandwidth with the conventional traffic in the mobile edge link. Simply using TCP on MEC offloading causes bandwidth robbery to the conventional TCP traffic. On the other hand, in the highly lossy wireless link environments, TCP fails to satisfy the MEC's strict requirement on the short transport delay. Therefore, we propose the MEC offloading transport (MOT) mechanism. MOT uses the prioritized queueing to avoid bandwidth robbery to the conventional traffic, and also uses the per-hop reliability to achieve loss-insensitive bandwidth utilization. The evaluation results show that MOT successfully avoids degrading the QoS of the conventional services, and achieves almost full utilization on the remaining bandwidth.

It is a significant challenge for device-to-device (D2D) networks to deliver mobile videos among mobile users due to the highly nondeterministic and intermittent connectivity. In this paper, we propose to integrate the random mobility of users in mobile opportunistic D2D networks with crowdsourcing to push mobile video Ads. Incentives are key to the success of video Ads push as it heavily depends on how actively mobile users participate in it. To stimulate users to perform mobile video Ads push tasks, we model the interaction between depositories and the Ad provider as a reverse auction. More specifically, we try to maximize the utility of Ad provider by selecting a subset of depositories before a specified deadline. We first propose an online auction (OA) algorithm, which runs efficiently in polynomial time, guarantees individual rationality, profitability. However, it does not guarantee truthfulness and thus limits its practicality. We then introduce two truthful OA algorithms, i.e., TOA and TOA-MM. We carry out trace-driven simulation to verify the three OA algorithms. The simulation results corroborate that the proposed algorithms have superior performance and efficiently stimulate mobile users to make contribution to video Ads push.

In this paper, an Air-Ground Integrated VEhicular Network (AGIVEN) architecture is proposed, where the aerial high-altitude platforms (HAPs) proactively push contents to vehicles through large-area broadcast, while the ground roadside units (RSUs) provide high-rate unicast services on demand. To efficiently manage the multi-dimensional heterogeneous resources, a service-oriented network slicing approach is introduced, where the AGIVEN is virtually divided into multiple slices and each slice supports a specific application with guaranteed quality of service (QoS). Specifically, the fundamental problem of multi-resource provisioning in AGIVEN slicing is investigated by taking into account the typical vehicular applications of location-based map and popularity-based content services. For the location-based map service, the capability of HAP-vehicle proactive pushing is derived with respect to the HAP broadcast rate and vehicle cache size, wherein a saddle point exists, indicating the optimal communication-cache resource trading. For the popular contents of common interests, the average on-board content hit ratio is obtained with HAPs pushing newly generated contents to keep on-board cache fresh. Then, the minimal RSU transmission rate is derived to meet the average delay requirements of each slice. The obtained analytical results reveal the service-dependent resource provisioning and trading relationships among RSU transmission rate, HAP broadcast rate, and vehicle cache size, which provides guidelines for multi-resource network slicing in practice. Simulation results demonstrate that the proposed AGIVEN network slicing approach matches the multi-resources across slices, whereby the RSU transmission rate can be saved by 40% while maintaining the same QoS.

Information-centric networking (ICN), as a novel network paradigm, is expected to natively support mobility, multicast, and multihoming in vehicular ad hoc networks (VANETs). In this paper, the adoption of ICN principles for multimedia streaming in multihomed VANETs is investigated, with a major emphasis on the tradeoff between the quality of experience and energy efficiency (EnE). To formalize this problem, a cost optimization model is first proposed, based on queueing theory arguments. Then, a novel green information-centric multimedia streaming (GrIMS) framework is designed to drive the system toward optimal working points in practical settings. GrIMS consists of three enhanced mechanisms for on-demand cloud-based processing, adaptive multipath transmission, and cooperative in-network caching. Finally, a massive simulation campaign has been carried out, demonstrating that, thanks to its core components, the GrIMS enables flexible multimedia service provisioning and achieves an improved performance in terms of start-up delay, playbacks continuity, and EnE with respect to state-of-the-art solutions.

Vehicle‐assisted data offloading is envisioned to significantly alleviate the problem of explosive growth of mobile data traffic. However, due to the high mobility of vehicles and the frequent disruption of communication links, it is very challenging to efficiently optimize collaborative offloading from a group of vehicles. In this paper, we leverage the concept of Software‐Defined Networking (SDN) and propose a software‐defined collaborative offloading (SDCO) solution for heterogeneous vehicular networks. In particular, SDCO can efficiently manage the offloading nodes and paths based on a centralized offloading controller. The offloading controller is equipped with two specific functions: the hybrid awareness path collaboration (HPC) and the graph‐based source collaboration (GSC). HPC is in charge of selecting the suitable paths based on the round‐trip time, packet loss rate, and path bandwidth, while GSC optimizes the offloading nodes according to the minimum vertex cover for effective offloading. Simulation results are provided to demonstrate that SDCO can achieve better offloading efficiency compared to the state‐of‐the‐art solutions.

Information-Centric Networking (ICN) introduces ubiquitous in-network caching to reduce network load and improve Quality of Service (QoS). This peculiarity requires high-speed caching technologies to support wire-speed and large-amount data forwarding, which brings new challenges to existing routers. To promote practical ICN deployment, many emerging researches focus on how to accelerate caching. In this paper, we propose a novel two-layer High-speed Caching scheme (HCaching), which leverages the characteristics of both SRAM and DRAM to accelerate caching for ICN routers. In particular, using DRAM as a primary cache and SRAM as a secondary one, HCaching is able to: (i) reduce excessive utilization of high-cost SRAM, (ii) speed up access of DRAM, (iii) and improve total network throughput. We implement and analyze HCaching performance by comparing with another two state-of-the-art solutions. The results show that HCaching achieves an improved throughput by 3-10 times faster than the compared solutions.

Existing satellite communication has a low efficiency due to the inherent defects of the traditional design, i.e., coarsegrained control, and long configuration delay. In some previous work, researchers developed Software Defined Satellite Networks (SDSN). We reconsidered many characteristics equipped in satellite links, and deployed SDSN in the prototype by leveraging Delay Tolerant Network (DTN) and OpenFlow. However, it is necessary to develop a theoretical tool for this new network architecture to evaluate its performance. In this paper, we propose such an analytical model for SDSN using the queueing model. In particular, the Jackson's theorem is adopted to model the communication between a controller and forwarding nodes, and the store-and-forward process. The comparisons between the numerical and experimental results indicate that the proposed model is able to accurately evaluate the performance of SDSN, and will provide great benefits for the further related researches.

Due to the severe environment along the High-Speed Railway (HSR), it is essential to research an efficient HSR communication system. In our previous work, we collected and analyzed an amount of the first hand dataset of signal intensity in HSR networks. We first observed that the link status variation presented an obvious Two-Time-Scale characteristics. However, that work did not analyze the cause of the Two-Time-Scale characteristics clearly. In this work, we focus on the fundamental cause of the periodic Two-Time-Scale characteristics, and make a lot of in-depth studies on this interesting phenomenon. Furthermore, we rebuild Two-Time-Scale characteristics by leveraging the relationship between the link state variation and the geographical position along HSR lines. In particular, considering the distribution of urban areas and rural ones along the HSR, a periodic distance based small time-scale model and a path-loss based large time-scale model are proposed respectively. Simulation results show the proposed models can perfectly explain the Two-Time-Scale characteristics and predict HSR link quality.

To design efficient high-speed railway (HSR) communication systems, it is essential to characterize the wireless link quality. In this paper, we made a large amount of field investigations on link quality of HSR network, and built a practical model to reflect the changing pattern of link quality along HSR lines in terms of round trip time (RTT) and packet loss rate (PLR). After analyzing a great number of collected dataset of RTT and PLR we excitedly found that their behaviors presented an obvious two-scale time- varying phenomenon. To this end, we analyzed the potential reasons and further characterized link quality of HSR network using a generalized reference model based on hidden Markov chain. An improved forward induction algorithm was proposed to simulate the two-time-scale phenomenon of RTT and PLR. Evaluation results show that the proposed model is able to well reflect the network link quality varying along the HSR line with accuracies of 71.2% and 63.5% in terms of PLR and RTT. The proposed model can be used to guide the HSR link quality prediction and evaluation.

Content-Centric Networking (CCN) is an entirely novel networking paradigm, in which packet forwarding relies upon lookup operations on content names directly instead of fixed-length host addresses. The unique features of CCN names, i.e., variable length, huge cardinality, and hierarchical structure, introduce new challenges that could hinder the deployment of such a new architecture at the Internet scale. In this paper, we make an in-depth study of characteristics of large-scale CCN names, and propose a simple yet efficient CCN-customized name lookup engine (named by TB2F), which capitalizes the strengths of Tree-Bitmap (TB) and Bloom-Filter (BF) mechanisms, while counteracts their main limitations. To this end, TB2F splits CCN prefix into a constant size T-segment and a variable length B-segment with a relative short length, which are treated using TB and BF, respectively. Furthermore, an optimal length of the T-segment is found to improve the lookup efficiency. Experimental comparisons with respect to the reference Name Prefix-Trie and Bloom-Hash have been also carried out. The results show that TB2F properly configured has good scalability and efficiency by (i) speeding up lookup operations and reducing the false positive rate with respect to Bloom-Hash; (ii) requiring less memory than Name Prefix-Trie; (iii) achieving a low overhead in updating operations in the large scale case.

As a promising solution to the scalability issue of the current routing infrastructure, locator/identifier separation has gained variety of attentions and resulted in thousands of peer-reviewed publications. However, there is still significant ongoing work addressing many challenges of the secure Locator/Identifier Separation Context (LISC). In this paper, we propose a novel Cognitive Adaptive Access-Control solution (CAAC) for a secure LISC with three modules, which are Tag-aware Access-Control module (TAC) that devotes to generate user tag (UTag) and service tag (STag) by cognizing their natural and dynamic attributes, Adaptive Policy Generation paradigm (APG) that serves to select proper policy instance for adaptive and intelligent access control, and Cooperative Decision Making module (CDM) that contributes to provide efficient decision-making by multi-peer parallel cooperation. We implement the designed CAAC in our identifier-based network platform to verify its advantages.

High-quality multimedia streaming services in Vehicular Ad-hoc Networks (VANETs) are severely hindered by intermittent host connectivity issues. The Information Centric Networking (ICN) paradigm could help solving this issue thanks to its new networking primitives driven by content names rather than host addresses. This unique feature, in fact, enables native support to mobility, in-network caching, nomadic networking, multicast, and efficient content dissemination. In this paper, we focus on exploring the potential social cooperation among vehicles in highways. An ICN-based COoperative Caching solution, namely ICoC, is proposed to improve the quality of experience (QoE) of multimedia streaming services. In particular, ICoC leverages two novel social cooperation schemes, namely partner-assisted and courier-assisted, to enhance information-centric caching. To validate its effectiveness, extensive ns-3 simulations have been executed, showing that ICoC achieves a considerable improvement in terms of start-up delay and playback freezing with respect to a state-of-the-art solution based on probabilistic caching.

Extension for the multi-homing feature of Stream Control Transport Protocol (SCTP), Concurrent Multipath Transfer (CMT) can achieve bandwidth aggregation by making use of parallel transmisson over selected paths. However, if CMT-based path selection depended solely upon the information provided by transport layer, it cannot really make the desired bandwidth aggregation. Motivated by the urgent needs of cross-layer bandwidth aggregation and the advances of Ant Colony Optimization (ACO) in network selection, this paper proposes a novel ACO based cross-layer bandwidth aggregation scheme for efficient Concurrent Multipath data Transfer (CMT-ACO) in wireless transmission. CMT-ACO provides an efficient data delivery with two modules, which are ACO-based Efficiency Aware model (ACO-EA) that devotes to sense paths' transmission efficiency(supported by a cross-layer factor) and reduce ``ping-pongquot; path switching (enabled by a stabilization factor), and ACO-based Bandwidth Aggregation scheme (ACO-BA) that contributes to provide a cross-layer optimal bandwidth aggregation scheme. The results gained by a close realistic simulation topology show that how CMT-ACO outperforms existing CMT protocol in terms of performance and quality of service in multi-homed SCTP-based wireless networks.

Information-Centric Networking (ICN) is a clean-slate networking architecture that puts information is focus instead of addressed hosts. Construction of content retrieval model to estimate the delivery performance is challenging in this ICN-based Mobile Ad hoc Networks (MANETs). In this paper, we propose a novel content retrieval model (PRCRM) for Information-Centric MANETs (ICMs) in 2-dimensional case. By investigating the distribution of content popularity, receiver-driven mechanism, content caching and replacement mechanism and generalized mobility model in 2-dimensional space, PRCRM constructs a novel content retrieval model based on the content hit/miss probability to estimate the content retrieval-related performance. We evaluate PRCRM by comparing its performance with another state of the art solution in terms of RTT and throughput. Simulation results demonstrate PRCRM's rationality and validity and it is shown that PRCRM is available to analyze content retrieval in ICMs.