Federated Learning (FL) has become a prevalent distributed paradigm for privacy-sensitive edge applications, thanks to its decentralized data storage without raw data transmission. However, the distributed nature of FL brings critical model security challenges, especially for intellectual property ownership protection and malicious accountability tracing. Existing researches rarely propose a holistic solution that balances privacy preservation, model robustness and training efficiency concurrently. To address these limitations, this paper presents a novel framework named Secure and Traceable Federated Learning for Edge Computing (STFL-EC). Specifically, a K-medoids clustering based delay-aware client grouping method is designed to alleviate the straggler effect and improve training efficiency. Besides, a periodic watermark embedding scheme is developed to assign unique watermarks for different training cycles, enabling reliable ownership verification and tampering resistance. Moreover, an enhanced watermarking strategy combining traitor tracing and Enhanced Watermark Embedding (EWE) is proposed to ensure accountability with negligible model performance loss. Extensive experiments verify that STFL-EC reaches 98.3% watermark detection accuracy, induces less than 1% model performance degradation, and cuts total training latency by around 21%, offering a practical secure FL solution for resource-constrained edge environments.

Automotive Ethernet as an in-vehicle networking paradigm has gradually become the main automotive backbone network. However, with the ever-increasing time-critical in-vehicle traffic, it is being confronted with enormous challenges to realize deterministic-latency communications, due to the inherent limitations of its distributed network architecture and the adopted MAC protocols, including limited-computing power, low-speed and unreliable traffic transmission. Furthermore, it is often incompatible with emerging vehicular functions and protocols, which can provide tremendous potential for better vehicular Quality-of-Service (QoS). Therefore, in this paper, we first design a Future Automotive Ethernet (FAE) architecture and then, built on the representative Time-Sensitive Networking (TSN) and industrial summation frame, propose a Deterministic-Latency MAC (DLM) protocol running in FAE to tackle these issues. The FAE architecture includes three functional domains, three in-vehicle computing units, and no fewer than three intelligent network processing modules, which can integrate with the emerging LAN protocols to realize cross-domain and intra-domain Ethernet-based communications. Under the umbrella of this architecture, DLM classifies the driving situations into driving, reversing, left turn, right turn and parking states, following the real-world vehicle behaviors, and assigns all traffic associated with driving safety in five states different recommended priorities to be delivered. Furthermore, an optimized deterministic-latency mechanism integrated with TSN and the industrial summation frame is developed to realize the timely and accurate transmission of high-priority and medium/low-priority traffic. Simulation results obtained from diversified scenarios demonstrate that the proposed DLM running in FAE can significantly improve transmission latency determinacy and reliability compared with the existing technical strategies.

Personalized Federated Learning (PFL) has been widely adopted in Mobile Edge Computing (MEC) to enable tailored services without private user data ever leaving the devices. Previous efforts have illustrated that the weighted aggregation determined by the number of samples on clients will hurt the convergence of PFL. Furthermore, the over-personalization of PFL may result in model overfitting and lack of generalization capabilities. Therefore, in this paper, we propose novel quality/discrepancy-aware Multi-task Personalized Federated Learning (MPFL) for MEC to tackle these issues. Specifically, a number of personalized learning objectives of different clients in PFL are considered as multiple tasks. Both local private Batch Normalization (BN) and global shared BN layers are introduced into PFL as the specialized experts to better balance the personalization and generalization capabilities of the local models. Furthermore, the statistical discrepancies between such two BN layers and the model quality of clients are jointly taken into account to design aggregation weights for quick model aggregation with better performance gains. Extensive experiments conducted on three well-known datasets demonstrate that the proposed framework outperforms the state-of-the-art benchmarks in terms of convergence speed and learning accuracy.

In space communications, the signal’s long-distance transmission between a flying transmitter-receiver pair encounters two obstacles: a huge path-loss and a high-speed movement. The huge path-loss results in a low signal-to-noise ratio (SNR) and the high-speed movement brings a dynamic Doppler-shift, thus posing a great challenge for Doppler-shift acquisition. Under the low SNR, the Doppler-shift acquisition has to accumulate many symbols in a long-time period. However, during this period, the dynamic Doppler-shift disperses all these symbols’ total energy over a wide range, thus causing the energy dispersion problem. To address this problem, we propose a probabilistic-search and neighbor-density (PSND) scheme, where the probabilistic-search considers the element’s amplitude and sacrifices some redundant signal elements for a narrower search-range, while the neighbordensity sums the signal element’s all neighbors for a larger signal energy. The PSND scheme includes two algorithms: the Generic PSND and Iterative PSND. The Generic PSND algorithm first selects some search-elements with their probabilities to construct a probabilistic-search-range, then selects some density-elements with their neighbor-elements to derive the neighbor-densities, and finally searches the largest neighbor-density to obtain the acquisition result. Built upon the Generic PSND algorithm above, the Iterative PSND algorithm iteratively updates the searchelements to further strengthen the neighbor-density in a narrower probabilistic-search-range. Moreover, the simulations results have demonstrated our PSND scheme’s higher acquisition probability, as compared with the existing schemes.

The feature fusion of optical and Synthetic Aperture Radar (SAR) images is widely used for semantic segmentation of multimodal remote sensing images. It leverages information from two different sensors to enhance the analytical capabilities of land cover. However, the imaging characteristics of optical and SAR data are vastly different, and noise interference makes the fusion of multimodal data information challenging. Furthermore, in practical remote sensing applications, there are typically only a limited number of labeled samples available, with most pixels needing to be labeled. Semi-supervised learning has the potential to improve model performance in scenarios with limited labeled data. However, in remote sensing applications, the quality of pseudo-labels is frequently compromised, particularly in challenging regions such as blurred edges and areas with class confusion. This degradation in label quality can have a detrimental effect on the model's overall performance. In this paper, we introduce the Difference-complementary Learning and Label Reassignment (DLLR) network for multimodal semi-supervised semantic segmentation of remote sensing images. Our proposed DLLR framework leverages asymmetric masking to create information discrepancies between the optical and SAR modalities, and employs a difference-guided complementary learning strategy to enable mutual learning. Subsequently, we introduce a multi-level label reassignment strategy, treating the label assignment problem as an optimal transport optimization task to allocate pixels to classes with higher precision for unlabeled pixels, thereby enhancing the quality of pseudo-label annotations. Finally, we introduce a multimodal consistency cross pseudo-supervision strategy to improve pseudo-label utilization. We evaluate our method on two multimodal remote sensing datasets, namely, the WHU-OPT-SAR and EErDS-OPT-SAR datasets. Experimental results demonstrate that our proposed DLLR model outperforms other relevant deep networks in terms of accuracy in multimodal semantic segmentation.

The accurate prediction of Quality of Service (QoS) in terms of response time, packet loss rate, latency and throughput for component services is essential for 5 G to fulfill specific Service Level Agreements (SLAs). However, most current efforts failed to fully exploit the time-varying mobility features of users and parallel iteration multi-rules to perform QoS prediction for component services, incurring poor prediction accuracy. Therefore, in this paper, we are devoted to accurate QoS Prediction of Component Services (QPCS) for 5 G via Graph-based Deep Reinforcement Learning (GDRL) to tackle this issue. Towards this end, the QoS prediction is modeled as GDRL-based QoS tensor factorization by designing a Spatio-Temporal-Recurrent-based Graph Attention Network (STR-GAT) and introducing it into Deep Deterministic Policy Gradient (DDPG) to factorize QoS tensor with multiple available rules in parallel. Specifically, a low-rank QoS tensor and an adjacency tensor are established, which include partial QoS observations of component services in each Base Station (BS), along with some missing elements, and evolving spatial information of users across these BSs, respectively. Then, the novel STR-GAT is designed by introducing spatio-temporal relations into conventional GAT to fully derive the mobility features of users to explore potential actions, while the derivative DDPG is adopted to perform tensor factorization with multiple available rules in parallel. Furthermore, the action smoothing and hierarchical-based replay buffer with priority-based and random sampling are designed and introduced into DDPG to stabilize training process and accelerate model convergence. Experimental simulation results on real-world datasets validate the superiorities of QPCS compared with the state-of-the-art approaches in predicting the QoS of component services in 5 G.

The accurate prediction of required resources in terms of storage, computing and bandwidth is essential for 5G to host diverse services. The existing efforts illustrate that it is more promising to efficiently predict the unknown required resources with a third-order tensor compared to the 2D-matrix-based solutions. However, most of them fail to leverage the inherent features hidden in network traffic like temporal stability and service correlation to build a third-order tensor for the multi-dimensional required resource prediction in an intelligent manner, incurring coarse-grained prediction accuracy. Furthermore, it is difficult to build a third-order tensor with rate-varied measurements in 5G due to different lengths of measurement time slots. To address these issues, we propose an Accurate Prediction of Multi-Dimensional Required Resources (APMR) approach in 5G via Federated Deep Reinforcement Learning (FDRL). We first confirm the resource requests originated from different Base Stations (BSs) at varied measurement rates have similar features in service and time domains, but cannot directly form a series of regular tensors. Built on these observations, we reshape these measurement data to form a series of standard third-order tensors with the same size, which include many elements obtained from measurements and some unknown elements needed to be inferred. In order to obtain accurately predicted results, the FDRL-based tensor factorization approach is introduced to intelligently utilize multiple specific iteration rules for local model learning, and the accuracy-aware and latency-based depreciation strategies are exploited to aggregate local models for resource prediction. Extensive simulation experiments demonstrate that APMR can accurately predict the multi-dimensional required resources compared to the state-of-the-art approaches.

Recent years have witnessed the proliferation of wireless energy transfer for Wireless Sensor Networks (WSNs), which are mainly used for data gathering in real-world applications. A number of studies have investigated mobile vehicle scheduling to charge sensor nodes via wireless Mobile Chargers (MCs). Unfortunately, most of them cannot parallelly charge all nodes in an intelligent manner with the global network attributes. Furthermore, the time-variable charging ignores the optimal data gathering, resulting in poor Joint Energy Replenishment and Data Gathering (JERDG). To fill this gap, this paper proposes a Federated Deep Reinforcement Learning (FDRL)-based JERDG (FERG) solution for WSNs. To this end, FERG first partitions the networks into a set of clusters to distribute the workload evenly among multiple MCs, and then designs an FDRL-based framework that incorporates various time-variant network attributes to determine the optimal schedule for charging and data gathering via multiple MCs and a base station (BS). The BS as the cloud server is responsible for global training of JERDG models, while multiple MCs will parallelly train local models to jointly charge energy-exhausted nodes and gather the data from all nodes in clusters. To reserve more personalized characteristics of each cluster, a density-based partial aggregation strategy is designed to train the global model. Furthermore, a reward-weighted update and selection solution is proposed to generate and exploit reference samples with high rewards. Simulation results obtained from various scenarios demonstrate that FERG significantly outperforms the state-of-the-art approaches in terms of network lifetime, energy efficiency and data collection latency.

Trajectory synthesis with a series of fake locations has been deemed as a promising obfuscation technology to preserve the individual privacy of users in Location-Based Services (LBSs). However, a number of previous approaches fail to take into consideration the geographic distance and motion direction of the real locations to synthesize trajectories. As a result, most of them always cannot represent the statistical characteristics of real trajectories in a privacy-preserving manner, and thus suffer from various attacks through data analysis. To tackle this issue, this paper presents SPSD, a novel privacy-preserving trajectory synthesis approach with a$k$-anonymous guarantee, through extracting the semantic, geographic and directional similarity of locations from the real trajectories to create plausible trajectories. SPSD first classifies all historical trajectory data into a series of sets for location identity, by introducing the visiting time and visiting duration, which can clearly represent the semantic information of locations. Then,$4k$locations and$2k$of$4k$ones have been selected from each set to act as the initial disguises of each corresponding real location, with quantitative semantic and geographic similarities, respectively. In order to find enough fake locations for each real location in less time, the candidate locations have been narrowed down to$k$in direction recovery through step-by-step screening, with the$k$-anonymous property. Experiment results built on the real-world trajectory datasets indicate that SPSD has outperformed the previous approaches in terms of semantic similarity, directional accuracy and security resistance to synthesize privacy-preserving trajectories at the tolerable time cost.

Recently, interest has grown in the use of proxy variables of unobserved confounding for inferring the causal effect in the presence of unmeasured confounders from observational data. One difficulty inhibiting the practical use is finding valid proxy variables of unobserved confounding to a target causal effect of interest. These proxy variables are typically justified by background knowledge. In this paper, we investigate the estimation of causal effects among multiple treatments and a single outcome, all of which are affected by unmeasured confounders, within a linear causal model, without prior knowledge of the validity of proxy variables. To be more specific, we first extend the existing proxy variable estimator, originally addressing a single unmeasured confounder, to accommodate scenarios where multiple unmeasured confounders exist between the treatments and the outcome. Subsequently, we present two different sets of precise identifiability conditions for selecting valid proxy variables of unmeasured confounders, based on the second-order statistics and higher-order statistics of the data, respectively. Moreover, we propose two data-driven methods for the selection of proxy variables and for the unbiased estimation of causal effects. Theoretical analysis demonstrates the correctness of our proposed algorithms. Experimental results on both synthetic and real-world data show the effectiveness of the proposed approach.

The utilization of deep learning methods in remote sensing image scene classification (RSISC) has gained significant attention, showcasing remarkable performance. However, these methods rely solely on the network for automatic weight assignment learning, which may introduce biases in attention calculations for remote sensing images. To address this issue, we propose a multi-view collaborative representation network (MCRNet) for RSISC. Specifically, we introduce a multiview collaborative representation framework (MCRF) to evaluate the impact of local features on key information within global features by different data augmentation. Furthermore, the introduction of a semantic summarization dictionary (SSD) aims to enhance the reconstruction of global semantic features through the optimization of a low-redundancy dictionary. Experiment results on two publicly available datasets confirm that the proposed model effectively improves the classification performance.

Federated Graph Learning (FGL) has garnered widespread attention by enabling collaborative training on multiple clients for semi-supervised classification tasks. However, most existing FGL studies do not well consider the missing inter-client topology information in real-world scenarios, causing insufficient feature aggregation of multi-hop neighbor clients during model training. Moreover, the classic FGL commonly adopts the FedAvg but neglects the high training costs when the number of clients expands, resulting in the overload of a single edge server. To address these important challenges, we propose a novel FGL framework, named SpreadFGL, to promote the information flow in edge-client collaboration and extract more generalized potential relationships between clients. In SpreadFGL, an adaptive graph imputation generator incorporated with a versatile assessor is first designed to exploit the potential links between subgraphs, without sharing raw data. Next, a new negative sampling mechanism is developed to make SpreadFGL concentrate on more refined information in downstream tasks. To facilitate load balancing at the edge layer, SpreadFGL follows a distributed training manner that enables fast model convergence. Using real-world testbed and benchmark graph datasets, extensive experiments demonstrate the effectiveness of the proposed SpreadFGL. The results show that SpreadFGL achieves higher accuracy and faster convergence against state-of-the-art algorithms.

The fusion of hyperspectral imagery (HSI) and light detection and ranging (LiDAR) data is widely used for land cover classification. However, due to different imaging mechanisms, HSI and LiDAR data always present significant image differences, and the dimensions and feature distributions of HSI and LiDAR are highly dissimilar. This makes it challenging to represent and correlate semantic information from multimodal data. Current methods for classifying pixel-by-pixel features, which rely on cascaded or attention-based fusion, cannot effectively use multimodal features. To achieve accurate classification results, extracting and fusing similar high-order semantic information and complementary discriminative information contained in multimodal data is vital. In this paper, we propose a cross-modal semantic enhancement network (CMSE) for multimodal semantic information mining and fusion. Our proposed CMSE framework extracts features from the image on multiple scales, capturing more representative local sparse features with different sizes of convolution kernels. To represent high-level semantic features related to land cover, we establish a Gaussian-weighted matrix and semantically transform the spatial and spectral features of distinct branches. Finally, we build a multi-level residual fusion module to incrementally fuse spectral features from HSI and elevation features from LiDAR. Additionally, we introduce a cross-modal semantically constrained loss to guide multimodal semantic feature alignment. We evaluate our approach on three multimodal remote sensing datasets, namely the Houston2013, Trento, and MUUFL datasets. The experimental results demonstrate that our proposed CMSE model achieves superior performance in terms of accuracy and robustness compared to other related deep networks.

Multitarget domain adaptation (MTDA) presents a formidable challenge in remote sensing image scene classification (RSICS), where the objective is to transfer knowledge from a labeled source domain to several unlabeled target domains. Compared to single-source-single-target domain adaptation (S3TDA), MTDA is inherently more complex due to domain shifts among multiple target domains. Directly merging the unique features of multitarget domains can result in corrupted information and poor classification performance. To address these challenges, we propose a hierarchical feature progressive alignment network (HFPAN) for RSICS in MTDA. First, our method introduces a fine-grained and contextual information extraction (FCIE) network to extract the global-local correlation in remote sensing (RS) images. Second, we construct a hierarchical feature embedding (HFE) framework that maintains hierarchical inter, intra constraints for the extracted features. Finally, we perform an alignment process for the constructed hierarchical features to minimize the differences in MTDA, progressing from coarse to fine granularity. To evaluate the efficacy of our proposed method, we conducted several cross-domain scene classification experiments on five public datasets. These experiments demonstrate the novelty of our approach and its ability to achieve improved classification performance.

Quantitative performance analysis plays a pivotal role in theoretically investigating the performance of Vehicular Edge Computing (VEC) systems. Although considerable research efforts have been devoted to VEC performance analysis, all of the existing analytical models were designed to derive the average system performance, paying insufficient attention to the worst-case performance analysis, which hinders the practical deployment of VEC systems to support mission-critical vehicular applications, such as collision avoidance. To bridge this gap, we develop an original performance analytical model by virtue of Stochastic Network Calculus (SNC) to investigate the worst-case end-to-end performance of VEC systems. Specifically, to capture the bursty feature of task generation, an innovative bivariate Markov Chain is firstly established and rigorously analysed to derive the stochastic task envelope. Then, an effective service curve is created to investigate the severe resource competition among vehicular applications. Driven by the stochastic task envelope and effective service curve, a closed-form end-to-end analytical model is derived to obtain the latency bound for VEC systems. Extensive simulation experiments are conducted to validate the accuracy of the proposed analytical model under different system configurations. Furthermore, we exploit the proposed analytical model as a cost-effective tool to investigate the resource allocation strategies in VEC systems.

Load prediction is an essential technique to improve edge system performance by proactively configuring and allocating system resources. Traditional load prediction methods obtain high prediction when handling loads exhibiting cyclical trend behavior, but they are unable to capturing highly-variable loads in edge computing environments. Existing studies fit prediction models via independent time series and output single-point real-value predictions. However, in practical edge scenarios, it is more valuable to obtain application value by utilizing the probability distribution of future loads rather than directly predicting specific values. To solve these problems, we propose an Edge Load Prediction method empowered by Deep Auto-regressive Recurrent networks (ELP-DAR). The ELP-DAR uses the time-series data of edge loads to train deep auto-regressive recurrent networks, which integrate Long Short-Term Memory (LSTM) into the S2S framework to calculate the parameters of the probability distribution at the next time-point. Therefore, the ELP-DAR can efficiently extract the essential representations of edge loads and learn their complex patterns, and the probability distribution for highly-variable edge loads can be accurately predicted. Extensive simulation experiments are conducted to validate the effectiveness of the proposed ELP-DAR method based on real-world edge load datasets. The results show that the ELP-DAR achieves higher prediction accuracy than other benchmark methods with different prediction lengths.

Mobile CrowdSensing (MCS) is an emerging paradigm that employs massive mobile devices (MDs) to complete sensing tasks cooperatively. To provide ubiquitous MCS services, Unmanned Aerial Vehicle (UAV), featured by high agility and flexibility, becomes increasingly attractive as a powerful assistant for MCS to collect sensing data in hard-to-reach and infrastructure-restrained areas. Focusing on urban MCS scenarios where a tremendous amount of data needs to be uploaded by massive mobile devices, we propose a Three-Dimensional Multi-UAV assisted crowdsensing, termed 3DM, to collect sensing data efficiently in an infrastructure-free manner. Different from the existing methods, 3DM has two unique advantages: 1) removing the assumption of the ideal distributions of mobile devices and 2) fully exploiting the 3D flexibility to optimize the device matching and data transmission between UAVs and MDs. By employing a joint optimization metric that incorporates both energy efficiency and collection latency, 3DM dynamically maintains cost-effective UAV-MD links and 3D UAVs trajectories thus completes the collection tasks with less time and energy. Compared with the baseline algorithm and two state-of-the-art counterparts, extensive simulations demonstrate that 3DM saves at least 50% energy and 25% time of baseline while achieving 76% improvement of the sub-optimal competitor on overall utility.

The existing deep networks have shown excellent performance in remote sensing scene classification (RSSC), which generally requires a large amount of class-balanced training samples. However, deep networks will result in underfitting with imbalanced training samples since they can easily bias toward the majority classes. To address these problems, a multigranularity decoupling network (MGDNet) is proposed for remote sensing image scene classification. To begin with, we design a multigranularity complementary feature representation (MGCFR) method to extract fine-grained features from remote sensing images, which utilizes region-level supervision to guide the attention of the decoupling network. Second, a class-imbalanced pseudolabel selection (CIPS) approach is proposed to evaluate the credibility of unlabeled samples. Finally, the diversity component feature (DCF) loss function is developed to force the local features to be more discriminative. Our model performs satisfactorily on three public datasets: UC Merced (UCM), NWPU-RESISC45, and Aerial Image Dataset (AID). Experimental results show that the proposed model yields superior performance compared with other state-of-the-art methods.

Remote sensing image semantic segmentation (RSISS) remains challenging due to the scarcity of labeled data. Semi-supervised learning can leverage pseudo-labels to enhance the model’s ability to learn from unlabeled data. However, accurately generating pseudo-labels for RSISS remains a significant challenge that severely affects the model’s performance, especially for the edges of different classes. In order to overcome these issues, we propose a semi-supervised semantic segmentation framework for remote sensing images based on edge-aware class activation enhancement (ECAE). Firstly, the baseline network is constructed based on the average teacher model, which separates the training of labeled and unlabeled data using student and teacher networks. Secondly, considering local continuity and global discreteness of object distribution in remote sensing images, the class activation mapping enhancement (CAME) network is designed to predict local areas more remarkably. Finally, the edge-aware network (EAN) is proposed to improve the performance of edge segmentation in remote sensing images. The combination of the CAME with the EAN further heightens the generation of high-confidence pseudo-labels. Experiments were performed on two publicly available remote sensing semantic segmentation datasets, Potsdam and ISPRS Vaihingen, which verify the superiorities of the proposed ECAE model.

The quantitative performance analysis plays a critical role in assessing the capability of vehicular edge computing (VEC) systems to meet the requirements of vehicular applications. However, developing accurate analytical models for VEC systems is extremely challenging due to the unique features of intelligent vehicular applications. Specifically, recent work revealed that the tasks generated by intelligent vehicular applications exhibit a high degree of burstiness, rendering the existing models that were designed based on the assumption of the non-bursty Poisson process unsuitable for VEC systems. To fill this gap, we developed an original analytical model to investigate the performance of VEC systems with bursty task arrivals. To facilitate vehicle cooperation, a new priority-based resource allocation scheme is exploited to schedule the tasks of vehicular applications, which are modelled by a Markov Modulated Poisson Process (MMPP). Next, a multi-state Markov chain is established to investigate the impact of load sharing strategy on the performance of VEC systems. Then, the end-to-end transmission latency is derived based on the proposed model. Comprehensive experiments are conducted to validate the accuracy of this analytical model under various system configurations. Furthermore, the developed model is used as a cost-effective tool to investigate the performance bottleneck of VEC systems.

Resource provisioning for the ever-increasing applications to host the necessary network functions necessitates the efficient and accurate prediction of required resources. However, the current efforts fail to leverage the inherent features hidden in network traffic, such as temporal stability, service correlation and periodicity, to predict the required resources in an intelligent manner, incurring coarse-grain prediction accuracies. To tackle this problem, in this paper, we propose an Accurate Prediction of Required virtual Resources (APRR) approach via Deep Reinforcement Learning (DRL). We first confirm the resource requests have more similar features and identify the high-dimensional required resources in computing, storage and bandwidth can be effectively consolidated into a single standardized value. Built upon these observations, we then model the required resources as a time-variant network matrix, which includes a number of elements, obtained from the network measurements, and some missing elements needed to be inferred. To obtain accurately predicted results, DRL-based matrix factorization with a set of available rules has been introduced into APRR and alternately executed in agent to minimize the prediction errors. Moreover, the error-prioritized designed for model training with quicker convergence. Simulation experiments on real-world datasets illustrate that APRR can accurately predict the required virtual resources compared with the related approaches.

Network Functions Virtualization (NFV), which decouples network functions from the underlying hardware, has been regarded as an emerging paradigm to provide flexible virtual resources for various applications through the ordered interconnection of Virtual Network Functions (VNFs), in the form of Service Function Chains (SFCs). In order to achieve the desired performance as dedicated hardware, how to efficiently deploy SFCs in NFV-enabled networks with limited resources is still a tremendous challenge. In this article, RQAP, an effective Resource and Quality of Service (QoS) Aware SFC Placement approach is proposed to mitigate this issue with the QoS-guaranteed service provisioning at acceptable resource consumption. With the Markov property of VNFs, the resource and QoS aware placement of SFCs is modeled as a Markov-chain-based optimization problem, where the set of all possible placement states on diverse nodes is regarded as a state space in the Markov chain and each state is jointly determined by the initial state and transition matrices. Furthermore, the SFCs associated with traffic requests are re-sorted so as to efficiently instantiate VNFs of the same type in a resource-saving manner. On this basis, an efficient Backward-Viterbi-based heuristic mechanism is presented to conduct the optimal VNF placement in Markov chain space, with the aim of consumed-resource reduction, along with the QoS-based instantiation of virtual links between adjacent VNFs. Simulation results conducted in several scenarios demonstrate that RQAP can significantly achieve a trade-off between resource consumption optimization and QoS guarantee. Besides, the results show that our proposed approach can also effectively improve the SFC acceptance ratio and achieve desirable load balancing and scalability.

Over the past few years, fog radio access networks (F-RANs) have become a promising paradigm to support the tremendously increasing demands of multimedia services, by pushing computation and storage functionalities toward the edge of networks, closer to users. In F-RANs, distributed edge caching among fog access points (F-APs) can effectively reduce network traffic and service latency as it places popular contents at local caches of F-APs rather than the remote cloud. Due to the limited caching resources of F-APs and spatiotemporally fluctuant content demands from users, many cooperative caching schemes were designed to decide which contents are popular and how to cache them. However, these approaches often collect and analyze the data from Internet-of-Things (IoT) devices at a central server to predict the content popularity for caching, which raises serious privacy issues. To tackle this challenge, we propose a federated learning-based cooperative hierarchical caching scheme (FLCH), which keeps data locally and employs IoT devices to train a shared learning model for content popularity prediction. FLCH exploits horizontal cooperation between neighbor F-APs and vertical cooperation between the baseband unit (BBU) pool and F-APs to cache contents with different degrees of popularity. Moreover, FLCH integrates a differential privacy mechanism to achieve a strict privacy guarantee. Experimental results demonstrate that FLCH outperforms five important baseline schemes in terms of the cache hit ratio, while preserving data privacy. Moreover, the results show the effectiveness of the proposed cooperative hierarchical caching mechanism for FLCH.

Deep learning has achieved excellent performance in remote-sensing image scene classification, since a large number of datasets with annotations can be applied for training. However, in actual applications, there is just a few annotated samples and a large number of unannotated samples in remote-sensing images, which leads to overfitting of the deep model and affects the performance of scene classification. In order to address these problems, a semi-supervised representation consistency Siamese network (SS-RCSN) is proposed for remote-sensing image scene classification. First, considering intraclass diversity and interclass similarity of remote-sensing images, Involution-generative adversarial network (GAN) is utilized to extract the discriminative features from remote-sensing images via unsupervised learning. Then, Siamese network with a representation consistency loss is proposed for semi-supervised classification, which aims to reduce the differences of labeled and unlabeled data. Experimental results on UC Merced dataset, RESICS-45 dataset, aerial image dataset (AID), and RS dataset demonstrate that our method yields superior classification performance compared with other semi-supervised learning (SSL) methods.

Blockchain has recently been regarded as an important enabler for building secure energy trading in microgrid systems because of its inherent features of distributively providing immutable data record, storage, and sharing across networks in a peer-to-peer (P2P) manner. However, designing highly efficient and scalable blockchain-enabled energy trading mechanisms is extremely challenging because of the unique features of microgrid systems, e.g., bandwidth-constrained and high-latency communications and large-scale renewable energy source (RES) integration. To address this challenge, in this article, we propose a novel scalable blockchain-based energy trading framework for cooperative microgrid systems, which include four planes, i.e., data plane, consensus plane, smart plane, and application plane. Different from the existing solutions without consideration of network transmission, these four planes are designed with the capability of perceiving the status of block generation and transmission over interrupted P2P networks, and thus proactively improving the consensus process to guarantee the reliability of energy trading in cooperative microgrids. Meanwhile, built on this framework, a novel redundant data exchange strategy is proposed to improve the scalability of block creation with the presence of large-scale RES penetration and interrupted and dynamic communication links. Simulation results show that the proposed system framework outperforms the benchmark blockchain solutions. Furthermore, we investigate the potential applications of the proposed solutions in the practical microgrid systems to facilitate a clear understanding of the mechanisms of the proposed solutions.

Network slicing has emerged as a promising networking paradigm to provide resources tailored for Industry 4.0 and diverse services in 5G networks. However, the increased network complexity poses a huge challenge in network management due to virtualized infrastructure and stringent quality-of-service requirements. Digital twin (DT) technology paves a way for achieving cost-efficient and performance-optimal management, through creating a virtual representation of slicing-enabled networks digitally to simulate its behaviors and predict the time-varying performance. In this article, a scalable DT of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments. The proposed DT exploits the novel graph neural network model that can learn insights directly from slicing-enabled networks represented by non-Euclidean graph structures. Experimental results show that the DT can accurately mirror the network behaviour and predict E2E latency under various topologies and unseen environments.

As an indispensable part of modern critical infrastructures, cameras deployed at strategic places and prime junctions in an intelligent transportation system can help operators in observing traffic flow, identifying any emergency situation, or making decisions regarding road congestion without arriving on the scene. However, these cameras are usually equipped with heterogeneous and turbulent networks, making the real-time smooth playback of traffic monitoring videos with high quality a grand challenge. In this article, we propose a lightweight Deep Reinforcement Learning-based approach, namely, sRC-C (smart bitRate Control with a Continuous action space) , to enhance the quality of real-time traffic monitoring by adjusting the video bitrate adaptively. Distinguished from the existing bitrate adjusting approaches, sRC-C can overcome the bias incurred by deterministic discretization of candidate bitrates by adjusting the video bitrate with more fine-grained control from a continuous action space, thus significantly improving the Quality-of-Service (QoS). With carefully designed state space and neural network model, sRC-C can be implemented on cameras with scarce resources to support real-time live video streaming with low inference time. Extensive experiments show that sRC-C can reduce the frame loss counts and hold time by 24% and 15.5%, respectively, even with comparable bandwidth utilization. Meanwhile, compared to the-state-of-art approaches, sRC-C can improve the QoS by 30.4%.

With the rapid growth of networked multimedia services in the Internet, wireless network traffic has increased dramatically. However, the current mainstream content caching schemes do not take into account the cooperation of different edge servers, resulting in deteriorated system performance. In this paper, we propose a learning-based edge caching scheme to enable mutual cooperation among different edge servers with limited caching resources, thus effectively reducing the content delivery latency. Specifically, we formulate the cooperative content caching problem as an optimization problem, which is proven to be NP-hard. To solve this problem, we design a new learning-based cooperative caching strategy (LECS) that encompasses three key components. Firstly, a temporal convolutional network driven content popularity prediction model is developed to estimate the content popularity with high accuracy. Secondly, with the predicted content popularity, the concept of content caching value (CCV) is introduced to weigh the value of a content cached on a given edge server. Thirdly, an novel dynamic programming algorithm is developed to maximize the overall CCV. Extensive simulation results have demonstrated the superiority of our approach. Compared with the state-of-the-art caching schemes, LECS can improve the cache hit rate by 8.3%-10.1%, and reduce the average content delivery delay by 9.1%-15.1%.

The knowledge of network distances, in the form of delay or latency, for example, is beneficial to a number of distributed applications. Notice that it is difficult and expensive to implement global network measurements to obtain network distance, a feasible idea is to predict unknown distances by introducing network coordinates with limited network measurements. The existing solutions always represent the unknown network distances in a rather unique number. However, research and applications indicate that the real network distances are hard to be accurately figured out and changes subtly in an interval over time with the dynamic network environments. Accordingly, this article proposes a tensor-based network distance prediction (TNDP) approach to represent network distance with confidence intervals, by exploiting the random distance tensor and distributed matrix factorization. With a small set of network measurements among the nodes selected randomly, a distance matrix tensor has been established and factorized into the product of two location matrixes with the adaptive SGD-based learning solution. By introducing the important training determinants, including weight matrix, regularization coefficient, and minibatch gradient descent with the exponential decay rates, the unknown distances among nodes can be accurately inferred in the forms of confidence intervals, with quick convergence and less overfitting. Extensive experimental simulations on a wide variety of available data sets demonstrate that TNDP is superior to other approaches in terms of accuracy for network distance prediction.

Remote sensing image scene classification, which requires large amounts of labeled data, plays a critical role in a range of fields.However, in the actual complex environment, the obtained remote sensing images are sometimes unlabeled due to data perturbation and the cost of manual labeling, which limits the training effect and generalization ability. To solve this issue, a semi-supervised siamese network with label fusion is proposed for remote sensing image scene classification. The siamese network is developed to extract features from remote sensing image, where loss function based on the low-entropy principle is constructed to select the unlabeled data as pseudo-label samples. The labeled and pseudo-label samples are mixed to further train the siamese network. The results on UC Merced dataset and WHU-RS19 show that our method is capable to achieve excellent performance compared with other semi-supervised learning methods.

Cellular communications have been regarded as promising approaches to deliver high-broadband communication links for unmanned aerial vehicles (UAVs), which have been widely deployed to conduct various missions, e.g., precision agriculture, forest monitoring, and border patrol. However, the unique features of aerial UAVs, including high-altitude manipulation, 3-D mobility, and rapid velocity changes, pose challenging issues to realize reliable cellular-enabled UAV communications, especially with the severe intercell interference generated by UAVs. To deal with this issue, we propose a novel position-based robust beamforming algorithm through complementarily integrating the navigation information and wireless channel information to improve the performance of cellular-enabled UAV communications. Specifically, in order to achieve the optimal beam weight vector, the navigation information of the UAV system is innovatively exploited to predict the changes of the direction-of-Arrival (DoA) angle. To fight against the high mobility of UAV operations, an optimization problem is formed by considering the tapered surface of DoA angle and solved to correct the inherent position error. Comprehensive simulation experiments are conducted and the results show that the proposed robust beamforming algorithm could achieve over 90% DoA estimation error reduction and up to 14-dB SINR gain compared with five benchmark beamforming algorithms, including linearly constrained minimum variance (LCMV), position-based beamforming, diagonal loading (DL), robust capon beamforming (RCB), and robust LCMV algorithm.

Network function virtualization (NFV) is critical to the scalability and flexibility of various network services in the form of service function chains (SFCs), which refer to a set of Virtual Network Functions (VNFs) chained in a specific order. However, the NFV performance is hard to fulfill the ever-increasing requirements of network services mainly due to the static orchestrations of SFCs. To tackle this issue, a novel Scalable SFC Orchestration (SSCO) scheme is proposed in this paper for NFV-enabled networks via federated reinforcement learning. SSCO has three remarkable characteristics distinguishing from the previous work: (1) A federated-learning-based framework is designed to train a global learning model, with time-variant local model explorations, for scalable SFC orchestration, while avoiding data sharing among stakeholders; (2) SSCO allows for parameter update among local clients and the cloud server just at the first and last epochs of each episode to ensure that distributed clients can make model optimization at a low communication cost; (3) SSCO introduces an efficient deep reinforcement learning (DRL) approach, with the local learning knowledge of available resources and instantiation cost, to map VNFs into networks flexibly. Furthermore, a loss-weight-based mechanism is proposed to generate and exploit reference samples in replay buffers for future training, avoiding the strong relevance of samples. Simulation results obtained from different working scenarios demonstrate that SSCO can significantly reduce placement errors and improve resource utilization ratio to place time-variant VNFs compared with the state-of-the-art mechanisms. Furthermore, the results show that the proposed approach can achieve desirable scalability.

5G networks are expected to provide cost-efficient, reliable, and flexible services for industrial productions and applications potentially, by introducing emerging network technologies like blockchain and network functions virtualization (NFV), which virtualizes network functions and runs them on standard infrastructure rather than customized hardware. However, how to deal with the emerging security challenges and fulfil the requirement of ultra-reliable and low-latency communications (URLLC) has not been fully resolved. In this article, we present an NFV-enabled 5G paradigm for the industry with the guarantee of URLLC through service chain acceleration and dynamic blockchain-based spectrum resource sharing among a variety of industry applications running in NVF-based equipment. First, we elaborate the benefits and shortcomings of NFV for industry, by executing an industry application experiment in virtualized and nonvirtualized data center networks. Then, we illustrate an NFV-enabled 5G paradigm for URLLC in detail, with a special focus on the service chain acceleration and spectrum sharing built on NFV, blockchain, software-defined networking, and mobile edge computing. Finally, we establish a mathematical model to study the worst-cast transmission latency of NFV-enabled 5G with the input of the bursty traffic. The proposed model can be exploited to support the plan, management, and optimization of NFV-enabled 5G URLLC systems for industry.

Content Caching at the edge of vehicular networks has been considered as a promising technology to satisfy the increasing demands of computation-intensive and latency-sensitive vehicular applications for intelligent transportation. The existing content caching schemes, when used in vehicular networks, face two distinct challenges: 1) Vehicles connected to an edge server keep moving, making the content popularity varying and hard to predict. 2) Cached content is easily out-of-date since each connected vehicle stays in the area of an edge server for a short duration. To address these challenges, we propose a Mobility-aware Proactive edge Caching scheme based on Federated learning (MPCF). This new scheme enables multiple vehicles to collaboratively learn a global model for predicting content popularity with the private training data distributed on local vehicles. MPCF also employs a Context-aware Adversarial AutoEncoder to predict the highly dynamic content popularity. Besides, MPCF integrates a mobility-aware cache replacement policy, which allows the network edges to add/evict contents in response to the mobility patterns and preferences of vehicles. MPCF can greatly improve cache performance, effectively protect users' privacy and significantly reduce communication costs. Experimental results demonstrate that MPCF outperforms other baseline caching schemes in terms of the cache hit ratio in vehicular edge networks.

The ever increasing demand for computing resources has led to the creation of hyperscale datacentres with tens of thousands of servers. As demand continues to rise, new technologies must be incorporated to ensure high quality services can be provided without the damaging environmental impact of high energy consumption. Virtualisation technology such as network function virtualisation (NFV) allows for the creation of services by connecting component parts known as virtual network functions (VNFs). By optimising the placement and routing of VNFs this technique can be used to maximally utilise available datacentre resources, to maintain a high quality of service whilst minimising energy consumption. Current research on this problem has focussed on placing VNFs and considered routing as a secondary concern. In this work we argue that the opposite approach, a routing-led approach is preferable. We propose a novel routing-led algorithm and analyse each of the component parts over a range of different topologies on problems with up to 16000 variables and compare its performance against a traditional placement based algorithm. Empirical results show that our routing-led algorithm can produce significantly better solutions to large problem instances on a range of datacentre topologies.

Mobile Cloud Computing (MCC) is regarded as a promising method to increase the data storage and enhance the processing power of mobile devices. Technologies such as Software Defined Networking (SDN) and Network Function Virtualisation (NFV) will be deployed in MCC to simplify the network management and accelerate mobile service deployment. In order to achieve a deeper understanding of future MCC, we developed a comprehensive analytical model to investigate the performance of MCC in the presence of both NFV service chains and SDN networks. The model is capable of capturing the interactions between SDN and NFV when they share the same underlying physical infrastructure. The end-to-end latency is derived for different scales of service deployments and network configurations. Comprehensive simulation experiments are conducted and the results demonstrate that the proposed analytical model corresponds well with the simulation experiments. In addition, we show how the analytical model can be a useful tool to investigate the impact of centralised SDN control on the performance of NFV traffic transmission.

Knowledge of node locations is essential to Wireless Sensor Networks (WSNs) in a wide range of potential applications and their function-dependent network protocols. A number of localization approaches have already been proposed to fulfill this requirement, but few of them can be applicable to mobile sensor networks, due to their low-dimensional embeddings, Euclidean distance representation limitations, frequent node mobility and additional measurement overhead in the network. In this paper, a resilient range-based d-dimensional localization (RRDL) approach is proposed for mobile WSNs to resolve the issues. RRDL distinguishes itself from previous work with three remarkable characteristics: (1) it works for mobile networks embedded in d-dimensional Non-Euclidean space; (2) it allows static ordinary nodes with pre-known locations to act as the alternative anchor nodes, thus tolerating the motion of the original anchor nodes to ensure that other ordinary nodes can obtain their locations in an efficient manner; and (3) it introduces an efficient path-learning approach, with the knowledge of the existing paths, to represent the real network distances as far as possible, thereby eliminating additional measurement overhead and tolerating node mobility in localization. With these characteristics, RRDL exploits the iterative factorization of the random distance matrix, formed by the distances to and from a set of k-hop static neighbors, to assign each current node d-dimensional Non-Euclidean coordinate in a distributed manner. Simulation results demonstrate that RRDL achieves higher localization accuracy with a moderate communication cost in mobile sensor networks.

In this paper, we propose a novel video coding scheme to significantly reduce the coding complexity and enhance overall coding efficiency in videos acquired by high mobility devices such as unmanned aerial vehicles (UAVs). In order to reduce the encoded data bits and encoding time to facilitate real-time data transmission, as well as minimize the image distortion caused by the jitter of onboard camera, a sensor-assisted global motion estimation (GMV) algorithm is designed to calculate perspective transformation model and global motion vectors, which are used in both the inter-frame coding to improve the coding efficiency and intra-frame coding to reduce block search complexity. We conducted comprehensive simulation experiments on official HM-16.10 codec and the performance results show the proposed method can achieve faster block search by 50% to 60% speedup and lower bitrate by 15% to 30% compared with standard HEVC coding software.

Unmanned Aerial Vehicles (UAVs) have demonstrated exceptional capabilities in many real-world applications such as remote sensing, emergency medicine delivery and precision agriculture. LTE networks are regarded as key candidates to offer high performance broadband wireless services to support UAV applications and safe deployment. However, the unique features of aerial UAVs including high-altitude manipulation, three-dimension (3D) mobility and rapid velocity changes, pose challenging issues for optimising LTE wireless communications to support UAVs, especially under the severe inter-cell interference generated by UAVs in the sky. To deal with this issue, we propose a novel position-based robust beamforming algorithm to improve the performance of LTE networks to serve UAVs. For obtaining optimal weight vectors that could tolerate Direction-of-Arrival (DoA) estimation errors, we propose a hybrid method to integrate the channel information and UAV flight information to accurately estimate the DoA angle range. In order to validate the performance of the proposed robust beamforming algorithm, we conduct comprehensive simulation experiments under practical configurations. The results show that the proposed robust beamforming algorithm outperforms benchmark Linearly Constrained Minimum Variance (LCMV) beamforming and GPS-based beamforming algorithms.

Network function virtualization (NFV) has been considered as a promising technology for future Internet to increase the network flexibility, accelerate the service innovation, and reduce the Capital Expenditures and Operational Expenditures costs through migrating network functions from dedicated network devices to commodity hardware. Recent studies reveal that although this migration of network function brings the network operation unprecedented flexibility and controllability, NFV-based architecture suffers from serious performance degradation compared with traditional service provisioning on dedicated devices. In order to achieve a comprehensive understanding of the service provisioning capability of NFV, this paper proposes a novel analytical model based on Stochastic Network Calculus (SNC) to quantitatively investigate the end-to-end performance bound of the NFV networks. To capture the dynamic and on-demand NFV features, both the non-bursty traffic, e.g., the Poisson process, and the bursty traffic, e.g., the Markov Modulated Poisson Process, are jointly considered in the developed model to characterize the arriving traffic. To address the challenges of resource competition and end-to-end NFV chaining, the property of convolution associativity and leftover service technologies of SNC are exploited to calculate the available resources of the Virtual Network Function nodes in the presence of multiple competing traffic and transfer the complex NFV chain into an equivalent system for performance derivation and analysis. Both the numerical analysis and extensive simulation experiments are conducted to validate the accuracy of the proposed analytical model. Results demonstrate that the analytical performance metrics match well with those obtained from the simulation experiments and numerical analysis. In addition, the developed model is used as a practical and cost-effective tool to investigate the strategies of the service chain design and resource allocations in the NFV networks.

Information-centric networking (ICN) is an emerging paradigm that decouples content from the host to achieve fast and cost-efficient communication and content distribution in the future Internet. A key feature of ICN is the deployment of ubiquitous in-network caching to speed up service delivery and improve network resource utilisation. ICN caching has been widely studied in terms of caching strategies and caching performance. However, the economic aspect of ICN has received marginal consideration so far, although it is vital to understand the potential cost- efficiency of ICN before its wide deployment in service provider network. To address this issue, we propose a cost-aware caching scheme to study the Quality-of-Service (QoS) and cost of ICN and investigate the inner association between them. Two new models are designed to characterise the cost and QoS of ICN with arbitrary topology under heterogeneous bursty content requests. A multi- objective evolution algorithm is adopted to find the optimal cache resource allocation. Numerical results show the effectiveness of the proposed scheme in achieving cost- efficiency and QoS guarantee in ICN caching.

Software-Defined Networking (SDN) is an emerging architecture for the next-generation Internet, providing unprecedented network programmability to handle the explosive growth of big data driven by the popularisation of smart mobile devices and the pervasiveness of content-rich multimedia applications. In order to quantitatively investigate the performance characteristics of SDN networks, several research efforts from both simulation experiments and analytical modelling have been reported in the current literature. Among those studies, analytical modelling has demonstrated its superiority in terms of cost-effectiveness in the evaluation of large-scale networks. However, for analytical tractability and simplification, existing analytical models are derived based on the unrealistic assumptions that the network traffic follows the Poisson process, which is suitable to model nonbursty text data, and the data plane of SDN is modelled by one simplified Single-Server Single-Queue (SSSQ) system. Recent measurement studies have shown that, due to the features of heavy volume and high velocity, the multimedia big data generated by real-world multimedia applications reveals the bursty and correlated nature in the network transmission. With the aim of capturing such features of realistic traffic patterns and obtaining a comprehensive and deeper understanding of the performance behaviour of SDN networks, this article presents a new analytical model to investigate the performance of SDN in the presence of the bursty and correlated arrivals modelled by the Markov Modulated Poisson Process (MMPP). The Quality-of-Service performance metrics in terms of the average latency and average network throughput of the SDN networks are derived based on the developed analytical model. To consider a realistic multiqueue system of forwarding elements, a Priority-Queue (PQ) system is adopted to model the SDN data plane. To address the challenging problem of obtaining the key performance metrics, for example, queue-length distribution of a PQ system with a given service capacity, a versatile methodology extending the Empty Buffer Approximation (EBA) method is proposed to facilitate the decomposition of such a PQ system to two SSSQ systems. The validity of the proposed model is demonstrated through extensive simulation experiments. To illustrate its application, the developed model is then utilised to study the strategy of the network configuration and resource allocation in SDN networks.

Carrier Aggregation (CA) has emerged as a promising technique for Long-Term Evolution Advanced (LTE-A) wireless communications to satisfy the ever-increasing bandwidth requirements. However, this technical envisagement puts forward new challenges on radio resource allocation such as serious unbalanced loads among different Component Carriers (CCs). To alleviate this problem, a novel QoS-aware resource allocation scheme, termed as Cross-CC User Migration (CUM) scheme, is proposed in this paper to support real-time services, taking into consideration the system throughput, user fairness and QoS constraints. The experiment results show that the proposed scheme outperforms the well-known Two-Level scheduling scheme in terms of packet loss probability, average queue length and throughput per user.

The rapid development in wireless technologies and multimedia services has given rise to new requirements for the Internet, such as supporting billions of mobile devices and transmitting huge amount of multimedia content in real time. Content-Centric Networking (CCN), a future Internet architecture for efficient content dissemination, has been attracting ever-increasing attention from both academia and industry. In this paper, a new analytical model is developed as a cost-effective tool to investigate the performance of caching in CCN under bursty content requests. The accuracy of the model is validated through comparing the analytical results with those obtained from the extensive simulation experiments. As an example of its applications, the analytical model is used to investigate the effects of the cache size, content size, and bursty content requests on the cache hit ratio in CCN.