In wireless localization, non-line-of-sight (NLOS) propagation in complex environments significantly degrades the time-of-arrival (TOA) positioning accuracy of ultra-wideband (UWB) systems. However, existing robust optimization methods mainly rely on interval uncertainty set modeling for NLOS errors, which inherently neglects the non-uniformity and correlation of NLOS errors, with these interval set bounds often being conservatively predefined. To address these issues, this paper proposes replacing interval sets with ellipsoidal uncertainty sets for a more accurate characterization of the statistical properties of NLOS errors. In particular, the ellipsoidal uncertainty set is constructed based on the mean vector and covariance matrix of NLOS errors predicted by a deep learning model. Since ellip-soidal uncertainty sets inherently lead to nonconvex formulations, we introduce auxiliary variables for reparameterization and apply the S-lemma, thereby reformulating the original problem into a tractable convex optimization problem. Simulation and experimental results demonstrate that, compared with existing methods, our ellipsoidal set-based approach, which accounts for the non-uniformity and correlation of NLOS errors, significantly improves localization accuracy and robustness across various complex environments.

With flexible antenna deployment, the Cell-Free Massive MIMO (CF-mMIMO) system can reduce wireless communication distance between access antennas and users, and provide multi-antenna access services for mobile users. In this paper, we consider introducing directional antennas in Cell-Free Massive MIMO system (CF-mMIMO-DA) to improve the network coverage and transmission capacity. In CF-mMIMO-DA systems, access control, which specifies the serving antennas, subcarriers, as well as the tilt angle and allocated transmit power, plays a crucial role for system performance. In this paper, we propose an access control optimization model in CF-mMIMO-DA systems with objective of maximizing the network throughput. Considering that the problem is NP-hard, we decompose the original problem into two subproblems, antenna tilt angle adjustment and user association. Then, to solve the two subproblems, we propose an antenna tilt angle adjustment algorithm based on the particle swarm optimization, and a user association algorithm based on the combination of concave-convex procedure and alternating direction of method of multipliers. In addition, we proposed an optimized joint access control mechanism based on alternating optimization between the two subproblems. Numerical results show that the deployment of directional antennas in CF-mMIMO can significantly improve the system throughput, and our proposed algorithm outperforms benchmarks.

Collaborative inference among Internet-of-Things (IoT) devices can reduce deep neural network (DNN) inference latency by exploiting the communication and computing resources of IoT devices. However, existing collaborative inference strategies often overlook the padding data integrity in information interaction among devices, leading to the loss of boundary data or redundant communication overhead, thus undermining the inference latency improvements. To address these issues, in this paper, we propose PIDC, a padding-aware IoT device collaboration framework for accelerating DNN inference, which jointly optimizes DNN partitioning and padding interaction among devices to minimize inference latency. First, the minimum amount of data exchanged for padding interaction is analyzed. Then, we formulate the latency minimization problem as a nonlinear integer programming problem, and transform it into a linear programming formulation by introducing auxiliary variables, enabling efficient solution with existing solvers. We implement a prototype using heterogeneous devices to validate the effectiveness of PIDC in real-world settings. Experimental results demonstrate that PIDC achieves significant inference latency reductions, with up to 43.0% latency reductions across different DNN models and datasets compared to the state-of-the-art methods.

Large Language Models (LLMs), with advanced content creation and inference capabilities, can provide immersive intelligent services to users in mobile edge networks. However, the increasing demand for real-time artificial intelligence (AI) applications aggravates the limitations of cloud-based LLMs due to the long response time. Meanwhile, Small Language Models (SLMs), which are cost-effective and locally deployable for terminal devices, can serve as an efficient supplement to LLMs for performing latency-sensitive tasks with lower generalization capability. Due to the resource constraints of edge networks and the diverse requirements of user tasks, it is critical to design an inference framework that effectively coordinates the deployment and collaboration of LLMs and SLMs. In this paper, we propose an LLM-SLM collaborative inference (LSCI) scheme under a mobile edge computing (MEC) architecture, which jointly decides where to cache models and how to offload inference tasks to balance latency, accuracy, and resource costs. To optimize inference performance subject to resource constraints, we jointly solve the inference task offloading and model caching problem in LSCI scheme. Specifically, we employ deep reinforcement learning (DRL) to select highly popular SLMs to be cached on the edge server, and distributed belief propagation technique to solve the associated inference task offloading issue. Numerical results show that the proposed LSCI scheme can achieve significant performance gain in terms of inference performance when compared with a number of baseline solutions.

Uncrewed aerial vehicle (UAV) assisted wireless network (UAWN) is emerging as a promising architectural innovation for the provisioning of ubiquitous coverage and enhanced connectivity in the forthcoming 6G era. To accommodate the increasingly diversified services of 6G without deploying individual UAWNs for each service type, the integration of network slicing with UAWNs becomes essential. However, unlike terrestrial networks, the dynamic and uncertain network conditions caused by the mobility of the UAVs pose significant challenges to the UAWN slicing problem. In this paper, we investigate the UAWN slicing problem by jointly considering UAV deployment, channel allocation, and power allocation under uncertain network conditions including imperfect channel state information, uncertain user demand, and imprecise user location. As expected, this problem turns out to be a robust nonconvex mixed-integer problem, making it overwhelmingly difficult to solve. In light of the limited computing power of the UAV, we propose a lightweight optimization named RUNs, which jointly exploits problem decomposition, the augmented Lagrange method, and the batch coordinate descent method. We prove that the RUNs framework runs fast in the sense that it converges to the stationary point at a log-linear rate. Meanwhile, the numerical results demonstrate that RUNs has significant performance gains over existing benchmark solutions.

Integrated Sensing and Communication (ISAC) is driving the evolution of edge intelligence. In ISAC-enabled wireless edge networks, federated learning (FL) is crucial for realizing edge intelligence by supporting the networks with privacy protection, efficient data management, and dynamic adaptability. Specifically, FL allows distributed computing nodes (e.g., sensor devices) to first train local models by using data collected or sensed via ISAC and subsequently send them to one or multiple aggregation nodes for global model collaboration. However, traditional FL frameworks face significant challenges in the ISAC scenarios. For example, the privacy sensitivity of heterogeneous sensor data and the lack of transparency in model parameter exchange make it difficult to ensure the credibility of local and global models. Sharding distributed ledger technology (DLT), which divides the ledger into smaller and manageable shards, offers a potential solution to address these challenges by utilizing multi-node trust capabilities to facilitate distributed consensus during FL training. In this paper, we propose a trusted FL framework that incorporates sharding DLT within ISAC-enabled wireless edge networks to enhance both model training and consensus performance. Specifically, we develop a theoretical model to examine the interactions between model training performance and network capacities of sensing nodes (e.g., storage, computing, and communication capabilities) based on ISAC’s real-time channel state information. Based on this theoretical model, we design a trusted clustering scheme for aggregating local models. Numerical results demonstrate that in ISAC-enabled wireless edge networks, our proposed scheme significantly increases network throughput for model transmission while ensuring optimal model learning performance compared to some classical baselines.

The integration of LEO satellite onboard processing with federated learning has propelled a promising paradigm: satellite federated learning (SFL), by empowering onboard machine learning (ML) to provide various intelligent services. Especially, the decentralized satellite federated learning (DSFL), where each LEO satellite serving as a client exploits one-hop inter-satellite links (ISLs) to exchange local models, could alleviate the reliance on the centralized ground server, and reduce multi-hop model transmissions. In a DSFL system, the scheduling of model training and transmission significantly affects the learning performance. Thus it is crucial yet challenging to design an efficient scheduling strategy for the dynamic LEO satellite networks with heterogeneous onboard datasets. In this paper, we propose a contact-based DSFL framework, where each contact between a pair of satellites is regarded as a collaboration opportunity to exchange local models. Under this framework, we formulate a problem of optimizing the scheduling strategy with the aim of maximizing the DSFL model accuracy. To solve this problem, we design a Double deep$Q$learning (DDQN) based scheduling strategy, which schedules the local model training and transmission upon each contact by leveraging the instantaneous environmental information, such as model accuracy, the neighbor's model accuracy, and available training time. Simulation results demonstrate the effectiveness and efficiency of the proposed DDQN-based scheduling strategy over three baselines.

With flexible antenna deployment, the Cell-Free Massive MIMO (CF-mMIMO) system can reduce wireless communication distance between access antennas and users, and provide multi-antenna access services for mobile users. In this paper, we consider introducing directional antennas in Cell-Free Massive MIMO system (CF-mMIMO-DA) to improve the network coverage and transmission capacity. In CF-mMIMO-DA systems, access control, which specifies the serving antennas, subcarriers, as well as the tilt angle and allocated transmit power, plays a crucial role for system performance. In this paper, we propose an access control optimization model in CF-mMIMO-DA systems with objective of maximizing the network throughput. Considering that the problem is NP-hard, we decompose the original problem into two subproblems, antenna tilt angle adjustment and user association. Then, to solve the two subproblems, we propose an antenna tilt angle adjustment algorithm based on the particle swarm optimization, and a user association algorithm based on the combination of concave-convex procedure and alternating direction of method of multipliers. In addition, we proposed an optimized joint access control mechanism based on alternating optimization between the two subproblems. Numerical results show that the deployment of directional antennas in CFmMIMO can significantly improve the system throughput, and our proposed algorithm outperforms benchmarks.

Satellite-terrestrial edge computing network (STECN) is emerging as a novel computation paradigm that enables a fashion of on-orbit computation, accommodating real-time processing of various types of computation tasks within a wider area. However, STECNs are incapable of meeting the diverse Quality-of-Service (QoS) requirements of various computational tasks without deploying dedicated infrastructures tailored to each type of task. Therefore, we studied the problem of joint network slicing and task offloading, which is modeled as a problem with a two-layer structure. At the higher level, slice tenants optimize their profits by determining resource allocations from the STECN, while at the lower layer, the users within each network slice maximize their utilities by deciding their offloading policies. In light of the complexity and the intricate interplay of these two problems, a multileader-disjoint-follower bi-level game is proposed. We show that both the leader’s game and the followers’ game admit at least one Nash equilibrium (NE). We then proposed two distributed algorithms that could prove to converge to the NE of these two games, respectively, without revealing any private information of all stakeholders. We evaluate the performance of our algorithms through extensive simulations, and the results demonstrate that our algorithms converge to the NE rapidly and can achieve superior performance gains compared with some known benchmarks.

Federated learning (FL) is integral to advancing edge intelligence by enabling collaborative machine learning. In FL-empowered edge networks, computing nodes first train local models and then send them to an or multiple aggregation node(s) for global model collaboration. However, the trustworthiness of both local and global models in conventional FL frameworks is compromised due to inadequate model security and transparency. Distributed ledger technique (DLT) can address this issue by leveraging multi-nodes trust capabilities to support distributed consensus. However, model training and consensus performance of DLT may significantly degrade due to instability and resource constraints of edge networks. Sharding technique provides an effective approach by dividing the ledger into smaller and manageable shards. In this paper, to improve model training and consensus performance, we propose a trusted FL framework by incorporating sharding DLT into FL frameworks. We construct a theoretical model to investigate the relationship between model training performance, consensus efficiency, and capacity of edge nodes regarding storage, computing and communications. Based on the theoretical model, we propose a trusted clustering scheme to aggregate local models. Numerical results show that our proposed scheme significantly improves network throughput for transmitting models while guaranteeing model learning performance in comparison with some classical baselines.

Unmanned aerial vehicle (UAV) has been recognized as a key supplement for terrestrial networks to meet the stringent requirements of the forthcoming 6G networks. However, a significant challenge lies in the provisioning of differentiated services through a common UAV network without deploying individual networks for each service type. In this paper, we consider the problem of joint network slicing and UAV placement under dynamic wireless environment as well as the uncertain traffic demands. To overcome the difficulties brought by the network dynamics, we propose an intelligent hierarchical UAV slicing framework that operates at two different time-scales. At the large time-scale, we formulate the problem of inter-slice resource slicing and UAV placement as a mixed integer nonlinear program, which is solved by a decomposition algorithm. At the small time-scale, the problem of intra-slice resource adjustment is modeled as a stochastic game and a distributed learning algorithm is proposed to find the expected Nash Equilibrium. Simulation results demonstrate that the proposed framework is lightweight and outperforms a number of known benchmark algorithms in terms of throughput and transmission delay.

One of the key challenges faced by 5G-Advanced and the forthcoming 6G networks is the provisioning of delay-critical services. Recently, the integration of network slicing and Multi-access Edge Computing (MEC) is regarded as a promising solution for this challenge. However, existing proposals for the integration are far from perfect with various drawbacks, such as rigid slicing, privacy leakage, and high signaling costs. In this paper, we investigate the problem of joint network slicing and computation offloading, which is formulated as a multi-leader-disjoint-follower Stackelberg game. We prove that the game is a potential game which has at least one global Nash Equilibrium (gNE). Then we propose a distributed algorithm that provably converges to a gNE of the game without revealing any private information of all stakeholders. The performance of our proposed algorithm is evaluated through simulations, which demonstrate that the algorithm converges to the gNE rapidly and outperforms a number of benchmark algorithms.

Hierarchical clustering learning (HCL) extends traditional parameter server-based distributed learning by clustering heterogeneous user equipments (UEs) via cluster nodes (CN s) located at the edge of the network. Currently, most vanilla model dissemination strategies in distributed learning rely on one-to-many transmissions, inevitably consuming excessive precious bandwidth resources. Consequently, communication-efficiency becomes crucial for HCL in resource-constrained edge networks. In this paper, we propose a multistage cooperative model dissemination strategy to sequentially determine the subsets of CNs that can concurrently transmit models during individual scheduling stages, thereby improving communication efficiency in HCL. First, we formulate the strategy design as an optimization problem to minimize the maximum completion time of the slowest straggler in a communication round of HCL. Then, we design an online learning algorithm, called sequential combinatorial multiarmed bandit (SCMAB) to make sequential and combinatorial decisions in individual stages. Numerical results demonstrate the superiority of our proposed strategy over some benchmarks in terms of communication efficiency.

Unmanned aerial vehicle (UAV) has been recognized as a key supplement for terrestrial networks to meet the stringent requirements of the forthcoming 6G networks. However, a significant challenge lies in providing differentiated services through a common UAV network, without the need to deploy individual networks for each service type. In this paper, we consider the problem of joint network slicing and UAV deployment under dynamic wireless environments as well as the uncertain traffic demands. To overcome the challenges posed by the network dynamics, we propose an intelligent hierarchical UAV slicing framework that operates at two different time-scales. At the large time-scale, the problem of inter-slice resource slicing and UAV deployment is formulated as a mixed integer nonlinear program, and a decomposition technique is applied to resolve it. At the small time-scale, the problem of intra-slice resource adjustment is modeled as a stochastic game and a distributed learning algorithm is proposed to find its Nash Equilibrium. Simulation results demonstrate that the proposed framework is lightweight and outperforms a number of known benchmark algorithms in terms of system utility, throughput and transmission delay.

Wireless localization with ultra-wideband technology or 5G/6G cellular networks is a major contributor to addressing satellite signal-denied positioning. The accuracy of localization, however, suffers from non-line-of-sight (NLOS) propagation. Literature has highlighted several approaches to improve precision, such as channel-based, map-based, and statistical feature-based. More attention has focused on the linear growth trend of NLOS error with distance at lower prior information acquisition costs. However, no previous study explores the uncertainty in the trend arising from a dynamic NLOS environment. Accordingly, this article intends to comprehensively utilize the linear trend and uncertainty to find the optimal location solution. First, we propose a distance-dependent uncertain model for NLOS error and construct an uncertain second-order cone programming. We then convert the nonconvex problem into a solvable positive semidefinite programming by Schur complement, Cauchy–Schwarz inequality, S-lemma, and constraint relaxation/tightening techniques. Simulations and experiments show that the resulting optimal and robust solution can obtain remarkable positioning accuracy in densely cluttered environments. The importance and originality of this study are that it fully uses the linear growth trend of NLOS error while incorporating the uncertainty for the trend.

High frequency directional communication is considered as a key technology to improve the performance of mobile Ad Hoc networks owing to its advantages in terms of communication distance and interference. Neighbor discovery plays a key role for efficient routing and topology control in mobile Ad Hoc networks. It is also a very challenging issue due to the use of directional antennas and movement of mobile nodes. Beam configuration is the key step of neighbor discovery in mobile Ad Hoc networks with directional antennas. Therefore, it is imperative to develop an efficient beam configuration algorithm to reduce the neighbor discovery latency. In this paper, we propose a novel beam configuration algorithm based on personalized federated learning. Considering the characteristics of mobile Ad Hoc networks (e.g., dynamic topology and directional communication), we use Deep Deterministic Policy Gradient (DDPG) as the local model of federated learning. Since the local data of ad hoc network nodes is heterogeneous, Model Agnostic Meta Learning (MAML) is applied to personalize the federated learning. Numerical results demonstrate that our proposed algorithm has better performance than some baseline algorithms.

Unmanned aerial vehicles (UAVs) are capable of serving as aerial base stations (BSs) for providing dynamic coverage and connectivity extension for the sixth-generation (6G) wireless networks. While flexibility is provided, the deployment of the UAV swarms and the associated resource allocation bring challenging issues due to dynamic nature of UAVs and difficulty in obtaining global user information. In this paper, we propose an adaptive and flexible joint UAV deployment and resource allocation scheme by exploiting a personalized federated deep reinforcement learning framework, called PFRL, with aim to maximize the long-term network throughput while enforcing user privacy and adapting to time-varying network states. To allow UAVs to make real-time decisions on resource allocation and position adjustment based on local observations while achieving a global optimal solution, we incorporate deep reinforcement learning (DRL) into federated learning framework. Specifically, we use DRL to train a local model and a personalized model on UAVs, and employ a two-level parameter aggregation scheme on a leading UAV to form a global model. The personalized model can adapt to specific environments, while exploiting the generalization of global model to accelerate the learning convergence. Numerical results show that the proposed PFRL scheme can achieve significant performance gain in terms of network throughput and convergence in comparison with some state-of-art solutions.

Various gradient compression algorithms have been proposed to alleviate the communication bottleneck in distributed learning, and they have demonstrated effectiveness in terms of high compression ratios and theoretical low communication complexity. However, when it comes to practically training modern deep neural networks (DNNs), these algorithms have yet to match the inference performance of uncompressed SGD-momentum (SGDM) and adaptive optimizers (e.g.,Adam). More importantly, recent studies suggest that these algorithms actually offer no speed advantages over SGDM/Adam when used with common distributed DNN training frameworks ( e.g., DistributedDataParallel (DDP)) in the typical settings, due to heavy compression/decompression computation or incompatibility with the efficient All-Reduce or the requirement of uncompressed warmup at the early stage. For these reasons, we propose a novel 1-bit adaptive optimizer, dubbed *Bi*nary *r*andomization a*d*aptive optimiz*er* (**Birder**). The quantization of Birder can be easily and lightly computed, and it does not require warmup with its uncompressed version in the beginning. Also, we devise Hierarchical-1-bit-All-Reduce to further lower the communication volume. We theoretically prove that it promises the same convergence rate as the Adam. Extensive experiments, conducted on 8 to 64 GPUs (1 to 8 nodes) using DDP, demonstrate that Birder achieves comparable inference performance to uncompressed SGDM/Adam, with up to ${2.5 \times}$ speedup for training ResNet-50 and ${6.3\times}$ speedup for training BERT-Base. Code is publicly available at https://openi.pcl.ac.cn/c2net_optim/Birder.

Gaussian process regression (GPR) is a non-parametric model that has been used in many real-world applications that involve sensitive personal data (e.g., healthcare, finance, etc.) from multiple data owners. To fully and securely exploit the value of different data sources, this paper proposes a privacy-preserving GPR method based on secret sharing (SS), a secure multi-party computation (SMPC) technique. In contrast to existing studies that protect the data privacy of GPR via homomorphic encryption, differential privacy, or federated learning, our proposed method is more practical and can be used to preserve the data privacy of both the model inputs and outputs for various data-sharing scenarios (e.g., horizontally/vertically-partitioned data). However, it is non-trivial to directly apply SS on the conventional GPR algorithm, as it includes some operations whose accuracy and/or efficiency have not been well-enhanced in the current SMPC protocol. To address this issue, we derive a new SS-based exponentiation operation through the idea of “confusion-correction” and construct an SS-based matrix inversion algorithm based on Cholesky decomposition. More importantly, we theoretically analyze the communication cost and the security of the proposed SS-based operations. Empirical results show that our proposed method can achieve reasonable accuracy and efficiency under the premise of preserving data privacy.

Source localization within wireless sensor networks (WSNs) is one of the critical technologies in the Internet of Things (IoT). As the number of network nodes increases, so does the amount of data and computational requirement. It is imperative to introduce edge computing. However, there are still two issues when running existing wireless location algorithms on edge nodes: 1) conventional low-complexity approaches are easily affected by the bias generated in complex environments, leading to low locating accuracy and 2) the optimization algorithms considering the bias have good performances, but they are calculation-efficiency low on edge nodes. This study proposes a computationally efficient and high-precision location method to tackle the troubles. Precisely, we first introduce our previous research to construct a bias-considered nonconvex problem with a linear objective. Then, we propose an angle-assisted Taylor series with zero truncation error to linearize the second-order cone (SOC) constraint in the established problem. Next, we resort to the mini-max criterion to eliminate the angular uncertainty and get a robust linear programming (LP) problem with an optimal solution. So far, we have obtained a convex problem of low complexity. To ensure the calculated efficiency of the proposed problem on edge nodes, we proceed to give the solving process of the problem. Moreover, we provide a constraints tracking mechanism to reduce the number of iterations in the solution procedure, improving computational efficiency. Simulations and experiments demonstrate that the proposed method with similar locating accuracy to state-of-the-art optimization algorithms exhibits much higher computing efficiency on edge nodes.

Blockchain is envisioned as one of the promising technologies to address trust concern brought by mobile crowdsensing (MCS), due to its auditability, immutability and decentralization. Nevertheless, blockchain cannot fundamentally guarantee that the valuable sensed data outside the chain can enter the chain, although data integrity and consistency can be ensured once it is confirmed inside the chain. In addition, simply applying blockchain in MCS while ignoring possible abnormal saboteurs hidden in numerous devices may mislead the normal operation of blockchain, resulting in untrustworthy interactions. Consequently, it is highly desirable to build a trust-preserving mechanism (TPM) to fully enjoy the benefits of using blockchain in MCS. To this end, we first resort to a probabilistic trust assessment inferred from the interaction outcomes in blockchain, to incentivize participants to maintain the trustworthiness of interactions. By inferring trust to aid decision-making, trust decision is further made, including leader election and transaction data generation, to filter untrusted nodes from participating in blockchain process. Finally, extensive simulations are conducted to validate the effectiveness and efficiency of TPM, and improve the performance in terms of contribution rate, consensus accuracy and system stability.

Mobile crowd sensing (MCS) is a promising paradigm which leverages sensor-embedded mobile devices to collect and share data. The key challenging issues in designing an MCS system include selecting appropriate users to participate in a specific sensing task and designing efficient data sensing and transmission policies for data aggregation. In mobile edge networks, the limitation on network resources including bandwidth and energy affects the design of MCS significantly. Specifically, the limited resources affect whether and how to select users for a sensing task, and the bandwidth allocated to a user affects its data sensing and transmission policies. Since user selection, bandwidth allocation, data sensing and transmission are closely coupled issues in MCS, we focus on designing a unified framework for joint sensing and communication in this paper, by jointly optimizing the aforementioned four policies under resource constraints. Simulation results show that the proposed unified framework significantly outperforms several baseline solutions without considering wireless link vulnerability and/or resource limitations.

Network softwarization is a paradigm shift for the next generation of network. Network Function Virtualization (NFV) softwarizes network functions as virtual network function (VNF) instances on top of a network infrastructure. Along with the merits of flexibility, programmability and reduced function provisioning cost, softwarization of network functions introduces new challenges of service’s reliability due to possible hardware failures, software bugs and hacker attacks. Currently reliable service provisioning schemes based on first-order statistics fails in accounting for the ultra-reliable needs of mission-critical services. In this paper, we propose a dynamic service chaining (DSC) framework to provision ultra-reliable services where the reliability is characterized by the probability distribution using extreme value theory. Our design objective is to minimize the number of backup VNF modules subject to reliability and resource constraints. Due to the dynamic nature of network, primary and backup VNFs are re-mapped to higher reliable physical machines in order to provide ultra-reliable services. Using Lyapunov stochastic optimization, primary VNF mapping and backup VNF selection are performed in the large and small timescales respectively. Numerical results show that the proposed DSC framework can guarantee ultra-reliable network services efficiently.

Mobile crowdsensing (MCS) is a promising paradigm where sensor-embedded mobile devices are exploited for collecting and sharing environmental data. In MCS, the participating mobile devices sense the environment, collect the data, (pre-)process the data and transmit the data or pre-processing results to the server for further processing. In wireless edge networks, transmission and/or processing of sensed data may be unsuccessful due to the unstable wireless channels, limited bandwidth, energy and computation resources. To optimize the MCS performance, it is imperative to jointly consider the data sensing, processing and transmission for MCS system design. In this paper, we propose a joint sensing, communication and computation (JSCC) framework for multi-dimensional resource constrained MCS systems. We formulate the JSCC design as an optimization problem, by jointly controlling the data sensing, transmission and computation offloading schemes in the system. Simulation results show that the proposed JSCC framework significantly outperforms several baseline solutions without jointly considering data sensing-transmission-computation and/or multi-dimensional resource limitations.

Federated learning (FL) has become a promising technique for developing intelligent wireless networks. In traditional FL paradigms, local models are usually required to be homogeneous for aggregation. However, due to heterogeneous models coming with wireless sysTem heterogeneity, it is preferable for user equipments (UEs) to undertake appropriate amount of computing and/or data transmission work based on sysTem constraints. Meanwhile, considerable communication costs are incurred by model training, when a large number of UEs participate in FL and/or the transmitted models are large. Therefore, resource-efficient training schemes for heterogeneous models are essential for enabling FL-based intelligent wireless networks. In this paper, we propose an adaptive quantization scheme based on ensemble distillation (AQeD), to facilitate heterogeneous model training. We first partition and group the participating UEs into clusters, where the local models in specific clusters are homogeneous with different quantization levels. Then we propose an augmented loss function by jointly considering ensemble distillation loss, quantization levels and wireless resources constraints. In AQeD, model aggregations are performed at two levels: model aggregation for individual clusters and distillation loss aggregation for cluster ensembles. Numerical results show that the AQeD scheme can significantly reduce communication costs and training time in comparison with some state-of-the-art solutions.

Unmanned aerial vehicle (UAV) assisted wireless network has been recognized as an effective technology to facilitate the formation of a super flexible low-altitude platform for relieving the strain on traditional ground cellular systems. However, the on-demand deployment of the UAV-assisted wireless networks (OWN) becomes an essential yet challenging issue, as the constraints of UAVs’ location, resource provisioning, and demand distribution should be jointly considered. In this work, we investigate the OWN problem by proposing an autonomous learning framework (ALF) consisting of three sequential stages: demand prediction, proactive deployment, and resource allocation fine-tuning, which can be capable of autonomous network planning without reliance on manual operations in an extremely dynamic environment. In the demand prediction stage, we first design a dual transformer network (DTN) to capture the temporal and spatial dependencies of wireless traffic. We further reduce the computational complexity of DTN from quadratic time complexity to log-linear time complexity. In the proactive deployment stage, we jointly optimize the UAVs’ location and resource provisioning by proposing a modified general benders decomposition algorithm with a$\Gamma $-optimal convergence, where a learning-based discerning module is designed to accelerate the algorithm. In the resource allocation fine-tuning stage, we propose a simulated annealing-based algorithm to minimize the transmission rate degradation of users to reduce the bias caused by traffic demand prediction. Extensive numerical results based on an open source dataset demonstrate the effectiveness of the proposed methods in comparison with existing baselines.

Mobile crowd sensing (MCS) is a promising paradigm which leverages sensor-embedded mobile devices to collect and share data. To perform a sensing task in MCS, appropriate participating users are selected first, and efficient data sensing and transmission policies are then designed for data aggregation. In mobile edge networks, network resource availability affects how to select the participating users, and the bandwidth allocated to a user affects its process of data sensing and transmission. Since user selection, bandwidth allocation, data sensing and transmission are closely coupled issues in a resource constrained MCS system, we focus on designing a joint sensing and communication framework in this paper, by jointly optimizing the aforementioned four policies under resource constraints. Specifically, the optimal data sensing and transmission policies are first derived under a given user selection and bandwidth allocation scheme. Then the user selection and bandwidth allocation are optimized based on dynamic programming. Simulation results show that the proposed mechanism significantly outperforms several baseline solutions without considering wireless link vulnerability and/or resource limitations.

Mobile crowdsensing (MCS) is a promising paradigm where sensor-embedded mobile devices are exploited for collecting and sharing environmental data. In MCS, the participating mobile devices collect the required data, (pre-)process the data and transmit the data and/or pre-processing results to the server for further processing. In wireless edge networks, transmission and/or processing of sensed data may be unsuccessful due to unstable wireless channels, limited bandwidth, energy and computation resources. To optimize MCS performance, it is imperative to jointly design the data sensing, processing and transmission policies under resource constraints. In this paper, we propose a joint sensing, communication and computation (JSCC) framework for multi-dimensional resource constrained MCS systems. We formulate the JSCC design as an optimization problem, by jointly controlling the data sensing, transmission and computation offloading processes in the system. Simulation results show that the proposed JSCC framework significantly outperforms several baseline solutions without jointly considering data sensing-transmission-computation and/or multi-dimensional resource limitations.

Federated learning (FL) has recently become one of the most acknowledged technologies in promoting the development of intelligent edge networks with the ever-increasing computing capability of user equipment (UE). In traditional FL paradigm, local models are usually required to be homogeneous for aggregation to achieve an accurate global model. Moreover, considerable communication cost and training time may be incurred in resource-constrained edge networks due to a large number of UEs participating in model transmission and the large size of transmitted models. Therefore, it is imperative to develop effective training schemes for heterogeneous FL models, while reducing communication cost as well as training time. In this paper, we propose an adaptive quantization scheme based on ensemble distillation (AQeD) for FL to facilitate personalized quantized model training over heterogeneous local models with different size, structure, and quantization level, etc. Specifically, we design an augmented loss function by jointly considering distillation loss function, quantization values and available wireless resources, where UEs train their local personalized machine learning models and send the quantized models to a server. Based on local quantized models, the server first performs global aggregation for cluster ensembles and then sends the aggregated model of the cluster back to the participating UEs. Numerical results show that our proposed AQeD scheme can significantly reduce communication cost as well as training time in comparison with some known state-of-the-art solutions.

With space, air and ground multiple layers, space-air-ground integrated networks (SAGINs) have been emerging as a promising technology to improve coverage and quality of service (QoS) for mobile users. With inhomogeneous access technologies at different layers in SAGINs, the joint gateway selection and user scheduling (GSUS) plays a crucial role to improve QoS and system performance. However, the moving aerial access point leads to highly dynamic inter-layer links, and it is challenging to capture the dynamics when solving the GSUS problem. In this paper, we resort to a non-stationary Markov Decision Process (MDP) formulation to make intelligent GSUS decisions in dynamic SAGINs. Unfortunately, conventional reinforcement learning (RL) is not applicable to solving the non-stationary MDP problem. To this end, we use the Dynamic Parameter Markov Decision Process (DP-MDP) to decompose the non-stationary MDP into a sequence of stationary MDPs, and then encode them with latent parameters, facilitating policy transfer between similar MDPs. Finally, the GSUS problem is solved by using an online learning framework including representation learning and RL. Simulation results demonstrate that the proposed framework outperforms a known benchmark scheme in terms of network throughput and packet drop rate.

Unmanned aerial vehicle (UAV) assisted wireless network is emerging as a promising technology to address the extremely high and dynamic traffic demands in future communication systems. In this paper, we investigate the on-demand deployment of UAV assisted wireless networks (OWN) problem. We propose an efficient autonomous learning framework (ALF), for learning a proactive and optimal on-demand deployment policy to complement terrestrial networks. In ALF, the OWN problem is solved in two co-related stages: the demand prediction stage and the proactive deployment stage. We first design a dual transformer network (DTN) to forecast the wireless traffic in the demand prediction stage. To decrease the complexity of DTN, we employ a patch embedding method and a modified self-attention scheme to improve the efficiency. With the predicted traffic demands, we jointly optimize the UAVs' location and wireless resource allocation by formulating it as a non-convex mixed integer nonlinear programming (MINLP) problem in the proactive deployment stage. To provide an efficient guaranteed solution to the MINLP problem, a multi-cut general benders decomposition algorithm is proposed to decompose the optimization problem into two subproblems. We theoretically prove that the proposed algorithm can achieve a T-optimal convergence. Extensive simulation results show the proposed solution outperforms existing baselines.

Blockchain has been regarded as one of the promising technologies to address trust concern in data-driven mobile crowdsensing (MCS), due to its auditability, immutability and decentralization. However, simply applying blockchain in MCS while ignoring possible abnormal saboteurs hidden in numerous devices may mislead the normal operation of blockchain, resulting in untrustworthy interactions. Consequently, it is highly desirable to build a trust-preserving mechanism (TPM) to bridge the gap between MCS and blockchain. To this end, we first resort to a probabilistic trust assessment inferred from the interaction outcomes in blockchain, to incentivize normal nodes to maintain trustworthiness of interactions. Assisted by the trust assessment, trust decision is further made to filter untrusted nodes from participating in blockchain process. Simulation experiments are conducted to validate the effectiveness and efficiency of the proposed TPM-enabled blockchain in terms of contribution rate and consensus accuracy.

Satellite edge computing (SEC) has become a promising technology for future wireless networks to provide anywhere and anytime computing services. Different from terrestrial edge computing, the computing capacity at Low-Earth-Orbit (LEO) satellites is usually unstable, due to the limited and consistently changing energy supply of fast-orbiting LEO satellites. To well exploit the potentials of SEC, an optimal computation offloading strategy becomes imperative to determine when and how to offload computing tasks with respect to high dynamics of satellites. In this paper, we propose a dynamic offloading strategy to minimize the overall delay of tasks from terrestrial users in a SEC network, subject to the energy and computing capacity constraints of the LEO satellite. Based on Lyapunov optimization theory, a long-term stochastic problem with a time-varying energy constraint is converted into multiple deterministic one-slot problems parameterized by the current system state, where task offloading decisions, computing resource allocation and transmit power control are jointly optimized. Numerical results show that our algorithm achieves asymptotic optimality efficiently while maintaining the mean rate stable of the LEO satellite’s energy queue, and has a lower delay compared with the other two comparison approaches with acceptable energy consumption.

Space-air-ground integrated network (SAGIN) is an emerging architecture for future wireless communication systems, by exploiting the advantages of combined satellite, aerial and terrestrial communications. In such an integrated system, there may exist intra-cell, inter-cell and inter-system interferences, leading to unsatisfactory system performance. On the other hand, it is very challenging to optimize the system performance due to the unique characteristics of SAGINs, such as time-varying links, heterogeneous resources, and three-dimensional network architecture. In this paper, we propose a deep reinforcement learning based intelligent adaptive transmission strategy. We first formulate the adaptive transmission strategy problem (ATSP) with the aim to maximize the system throughput while meeting the delay and reliability requirements of packets. The re-parameterization method based deep deterministic policy gradient (RPDDPG) algorithm is proposed for achieving better performance compared with the relaxation-based DDPG algorithm. Numerical results demonstrate the performance improvement of the RPDDPG algorithm compared with the conventional relaxation-based DDPG algorithm and a heuristic algorithm.

Radio Access Network (RAN) slicing is a promising architectural technology to address extremely diversified service demands and provide profitable business models for future mobile networks. In RAN slicing architecture, self-healing is an important functional module to minimize the impact of network failings on the performance of RAN slices. However, self-healing of burgeoning sliced RAN is vastly different from that of traditional RAN and has been rarely investigated. In this paper, we address the Self-healing of RAN Slice (SRANS) problem by modeling it as a Pareto optimization problem with the aim of maximizing the self-healing utilities of individual RAN slices. To deal with the weakness of diversity maintenance in traditional Pareto optimization methods, we propose a Generative Adversarial Network (GAN) based Pareto Optimization (GPO) framework. Specifically, we employ self-conditioned GANs to replace the offspring reproduction module in the traditional Evolutionary Algorithm (EA), where the insufficiency of diversity maintenance in EAs is effectively overcome. Furthermore, we theoretically prove that GPO framework is guaranteed to converge to the optimal Pareto solution set. Numerical results demonstrate that the convergence of proposed GPO framework can be expedited by enhancing the diversity of solution sets in solving the SRANS problem. Compared with traditional schemes, GPO can achieve significant performance gain in terms of the utilities and isolation level of repaired RAN slices.

Proactive reconfiguration of network slices according to uncertain traffic demands is essential to improve network resource utilization while ensuring service quality in 5G-and-beyond systems. Existing researches on network slice reconfiguration are either model-driven or data-driven methods. However, model-driven methods may cause resource over-provisioning due to a lack of prediction mechanism, while data-driven methods are unrealistic in inter-slice reconfiguration that involves costly and time-consuming operations such as VNF migration. To address these issues, in this paper, we propose a Hybrid Model-Data driven (HMD) framework that intelligently performs inter-slice reconfiguration by leveraging prediction interval and robust optimization. We design a Prediction Interval-oriented Predictor (PIP) to produce a prediction interval that can bracket the future traffic demand with a prespecified probability. Based on the prediction interval, we design an inter-slice reconfiguration scheme (named box optimizer) to perform fast inter-slice reconfigurations. To tackle the over-conservativeness of the box optimizer, we further design the ellipsoid optimizer with better optimality at a cost of increased complexity. Numerical results demonstrate that the proposed framework can provide high robustness with low power consumption. Meanwhile, the trade-off between the power consumption and the realized robustness can be flexibly adjusted according to the type of slice and the level of traffic demand fluctuations.

Federated learning (FL) has recently become one of the hottest focuses in wireless edge networks with the ever-increasing computing capability of user equipment (UE). In FL, UEs train local machine learning models and transmit them to an aggregator, where a global model is formed and then sent back to UEs. In wireless networks, local training and model transmission can be unsuccessful due to constrained computing resources, wireless channel impairments, bandwidth limitations, etc., which degrades FL performance in model accuracy and/or training time. Moreover, we need to quantify the benefits and cost of deploying edge intelligence, as model training and transmission consume certain amount of resources. Therefore, it is imperative to deeply understand the relationship between FL performance and multiple-dimensional resources. In this paper, we construct an analytical model to investigate the relationship between the FL model accuracy and consumed resources in FL empowered wireless edge networks. Based on the analytical model, we explicitly quantify the model accuracy, available computing resources and communication resources. Numerical results validate the effectiveness of our theoretical modeling and analysis, and demonstrate the trade-off between the communication and computing resources for achieving a certain model accuracy.

Beyond fifth-generation (B5G) and future networks face the challenges of spectral, energy and cost efficiency for large-scale machine-type communications. Recently, emerging ambient backscatter communication (AmBC) technology provides a promising paradigm for the development of green Internet of Things (IoT) networks in B5G era. Unlike existing work on AmBC which mostly focuses on physical layer with relatively ideal model, i.e., classic three-nodes model composed of radio frequency (RF), backscatter device (BD) and IoT device, this paper studies the access control strategy, including coefficient design and device association, from the perspective of networking. Assuming whether channel information is available a-priori, we propose online and offline access control strategies respectively. For offline access control strategy, we leverage the difference of two convex functions approximation (DCA) and dual decomposition to transform the non-concave optimization problem into the concave one, and design a distributed access control strategy called DCA-S. Furthermore, for the case that channel information is assumed to be unknown in advance due to the dynamics of primary and backscatter networks, we design a combinatorial multi-armed bandit (CMAB) access control strategy (CMAB-S). Numerical results show that the proposed DCA-S and CMAB-S can achieve significant performance improvement of the system in both cases of available and unavailable channel information compared with benchmark schemes.

Network Slicing (NS) has been widely identified as a key architectural technology for 5G-and-beyond systems by supporting divergent requirements sustainably. With the widespread of emerging smart devices, access control becomes an essential yet challenging issue in NS-based wireless networks due to the device-base station (BS)-NS three-layer association relationship. Meanwhile, stringent data security and device privacy concerns are increasing dramatically. In this paper, we propose an efficient access control scheme for radio access network (RAN) slicing by exploiting a federated deep reinforcement learning framework, called FDRL-AC, to improve network throughput and communication efficiency while enforcing the data security and device privacy. Specifically, we use deep reinforcement learning to train local model on devices, where horizontally federated learning (FL) is employed for parameter aggregation on BS, while vertically FL is employed for feature aggregation on the encrypted party. Numerical results show that the proposed FDRL-AC scheme can achieve significant performance gain in terms of network throughput and communication efficiency in comparison with some state-of-art solutions.

Radio Access Network (RAN) slicing is a promising architectural technology to address extremely diversified service demands for future mobile networks. As an essential requirement for RAN slicing, self-healing is to provide services with certain quality requirements by minimizing the impact of mobile network failings. In this paper, we propose a Multi-objective Pareto Optimization based Self-healing (MPOS) scheme to solve the SRANS problem. We model the SRANS problem as a multi-objective optimization problem with aim of maximizing the self-healing profits of individual RAN slices and demonstrate the NP-hardness. In proposed MPOS scheme, we employ self-conditioned GANs to replace the offspring reproduction module in the traditional Multi-Objective Evolutionary Algorithm (MOEA), where the insufficiency of diversity maintenance in MOEA is effectively overcome. Furthermore, we theoretically prove that MPOS framework is guaranteed to converge to the optimal Pareto solution set with probability 1. Numerical results demonstrate that our MPOS scheme is effective in reducing the inverted generational distance of optimal Pareto solutions and achieving high profit and isolation level of RAN slices.

The beyond fifth-generation (B5G) and future wireless networks face the challenges of spectral, energy and cost efficiency for large scale machine-type communications. Recently, emerging ambient backscatter communication (AmBC) technology provides a promising paradigm for the development of green Internet of Things (IoT) networks in beyond B5G era. In this paper, we consider a multi-nodes scenario where a backscatter network is symbiotic with primary network consisting of multiple ambient radio frequency (RF) sources, thereby allowing the system to use the appropriate RF to support high throughput and wide coverage for IoT devices. Unlike existing work on AmBC, which focuses on physical layer with relatively ideal model, i.e., classic three-nodes model composed of RF, backscatter device (BD) and IoT device, this paper studies the access control strategy, including coefficient design and device association of BDs and IoT devices, for multi-RF backscatter network from the perspective of maximizing device transmission rate. Under the guarantee of quality of service (QoS), we develop an access control strategy with aim of maximizing the weighted sum of primary and backscatter transmission rates, and design a distributed access control strategy called DCA-S, by using the difference of two convex functions approximation (DCA) and dual decomposition to transform the non-concave optimization problem into the solvable concave subproblems. Numerical results show that the proposed DCA-S can achieve significantly performance improvement of the system compared with benchmark schemes.

Network slicing (NS) has been identified as one of the most promising architectural technologies for future mobile network systems to meet the extremely diversified service requirements of users. In radio access networks (RAN) slicing, service provisioning for slice users becomes much more complicated than that in traditional mobile networks, as the constraints of both user physical association with base station (BS) and logical association with NS should be considered. In other words, the user-BS-NS three layer association relationship should be addressed in provisioning tailored service for diversified use cases with various quality of service (QoS) requirements. Therefore, service provisioning in RAN slicing becomes an essential yet challenging issue for 5G and beyond systems. In this paper, we propose a unified framework for service provisioning in RAN slicing with aim of maximizing resource utilization while guaranteeing QoS of users. The framework consists of two steps. The first step is to identify a set of slice users whose QoS can be satisfied simultaneously; while the second step performs joint slice association and bandwidth allocation with aim to minimize bandwidth consumption. Numerical results show that in typical scenarios, our proposed service provisioning framework can achieve significant performance gain in terms of the number of serving users and wireless bandwidth utilization compared with traditional schemes.

It is widely acknowledged that the agile reconfiguration of network slice according to traffic demand is of vital importance in 5G-and-beyond systems. Existing relevant works make reconfiguration decisions based either on point prediction of the uncertain demand, which lacks indications on how accurate it is, or on handcrafted uncertainty set with robust optimization, which may lead to resource over-provisioning due to the lack of prediction mechanism. To overcome these drawbacks, in this paper, we propose a predictor-optimizer framework that intelligently performs inter-slice reconfiguration with the aim of minimizing the energy consumption of serving these slices. Specifically, the predictor produces a prediction interval comprised of lower and upper bounds that bracket the future traffic demands with a prespecified probability. Then by regarding the prediction interval as the uncertainty set, we formulate the network slice reconfiguration problem as a Robust Mixed Integer Programming (RMIP). We solve this RMIP by using linearization technique and robust optimization. Numerical results demonstrate that the proposed framework outperforms traditional methods in terms of robustness and energy consumption. Meanwhile, the tradeoff between robustness and the energy consumption can be automatically adjusted according to the type of slice and traffic demands.

Network Function Virtualization has been widely acknowledged as one of the fundamental technologies for 5G and beyond by consolidating network functions into general-purpose hardware. To support a specific type of service, a virtualized network topology, such as Service Function Chain, is constructed by logically connecting a set of virtual network functions (VNFs). Meanwhile, Mobile Edge Computing (MEC) provides cloud resources at the edge of networks, meeting the stringent service requirements of many emerging mobile applications. With the widespread of new compute-intensive and Internet of Things applications, the amount of service flows in edge networks is rapidly increasing, causing network congestion easily because of the sinking of the computing capabilities. Moreover, due to the limited coverage of edge servers and erratic user mobility, it is difficult to maintain satisfactory service performance. Therefore, in order to support diverse services with various Quality of Service requirements, an online dynamic VNF migration is imperative in mobile networks. In this paper, we investigate the NF migration in softwarization based mobile networks with MEC, with the aim to minimize the number of link congestion in the networks. We first formulate the link congestion problem as a multidimensional knapsack problem, which is proved NP-hard. Then we resort to deep reinforcement learning to solve the online migration problem. Numerical results show that the proposed migration strategy can significantly reduce the number of link congestion and end-to-end service delay in comparison with the state-of-the-art solutions.

Driven by an explosive increase in the number of users and data usage, energy consumption becomes a significant concern for information and communication technology industry. In softwarization based networks, energy-efficient Network Function (NF) resource allocation is imperative yet challenging for service provisioning. In this paper, we investigate dynamic NF resource allocation (NFRA) problem for service function chains (SFCs) with aim to minimize the long-term energy consumption, while guaranteeing the end-to-end delay requirements for the packets traversing the SFCs. We formulate the problem as an infinite horizon Markov Decision Process (MDP) problem and obtain the global optimal solution based on the value iteration algorithm which has high computational complexity. The global optimal solution serves as a performance upper bound due to its high computational complexity. To cater for efficient on-line NFRA decisions, we further design a suboptimal distributed value iteration based dynamic NF resource allocation (DDRA) algorithm. The numerical results based on real-world data traces demonstrate the proposed DDRA algorithm achieves a close-to-optimal performance and a significant performance improvement compared with two known NF resource allocation algorithms.

Due to the explosive growth of data traffic and poor indoor coverage, ultra-dense network has been introduced as a fundamental architectural technology for the 5G-and-beyond systems. As the telecom operator is shifting to the plug-and-play manner in mobile networks, network planning and optimization become difficult, especially in residential small-cell base stations (SBSs) deployment. Under this circumstance, severe inter-cell interference becomes inevitable which deteriorates network performance and the quality of service (QoS) of user equipments (UEs). In this paper, we propose a fully distributed self-learning interference mitigation (SLIM) scheme for autonomous networks under a model-free multi-agent reinforcement learning (MARL) framework. In SLIM, SBSs autonomously perceive surrounding interferences and determine downlink transmit power without necessity of signaling interaction between SBSs for mitigating interferences. To tackle the dimensional disaster of joint action in MARL model, we employ the Mean Field Theory to approximate the action value function, thus to greatly decrease the computational complexity. Simulation results based on 3GPP dual-stripe urban model demonstrate that SLIM outperforms conventional interference coordination schemes in mitigating interference while guaranteeing UEs'QoS.

Software Defined Networking (SDN) and Network Function Virtualization (NFV) have been widely acknowledged as the fundamental architectural technologies for 5G and beyond networks by consolidating network functions into general-purpose hardware. Meanwhile, emerging Mobile Edge Computing (MEC) technology provides a promising solution to fulfill service requirements on high reliability and low latency, by extending cloud computing to the edge of networks. To provision a specific type of service, a virtualized network topology, such as Service Function Chain or Service Function Graph is constructed by logically connecting a set of virtual network functions (VNFs). In SDN/NFV-based mobile networks with the MEC cluster, it is imperative to develop an effective VNF deployment strategy to support various services with diverse Quality of Service requirements. In this paper, we propose a VNF deployment strategy for clustered MEC, including VNF placement and routing schemes, with the aim to minimize the average delay of service flows. We first formulate the problem as a two-dimensional knapsack problem, which is NP-Hard. To provide an efficient solution, we develop an improved genetic simulated annealing algorithm. Numerical results show that the proposed strategy can significantly reduce the end-to-end service delay in comparison with the state-of-the-art solutions.

Unmanned aerial vehicles (UAVs) have shown enormous potential in both public and civil domains. Although multi-UAV systems can collaboratively accomplish missions efficiently, UAV network(UAVNET) design faces many challenging issues, such as high mobility, dynamic topology, power constraints, and varying quality of communication links. Topology control plays a key role for providing high network connectivity while conserving power in UAVNETs. In this paper, we propose a distributed topology control algorithm based on discrete particle swarm optimization with articulation points(AP-DPSO). To reduce signaling overhead and facilitate distributed control, we first identify a set of articulation points (APs) to partition the network into multiple segments. The local topology control problem for individual segments is formulated as a degree-constrained minimum spanning tree problem. Each node collects local topology information and adjusts its transmit power to minimize power consumption. We conduct simulation experiments to evaluate the performance of the proposed AP-DPSO algorithm. Numerical results show that AP-DPSO outperforms some known algorithms including LMST and LSP, in terms of network connectivity, average link length and network robustness for a dynamic UAVNET.

It is widely acknowledged that network slicing can tackle the diverse usage scenarios and connectivity services that the 5G-and-beyond system needs to support. To guarantee performance isolation while maximizing network resource utilization under dynamic traffic load, network slice needs to be reconfigured adaptively. However, it is commonly believed that the fine-grained resource reconfiguration problem is intractable due to the extremely high computational complexity caused by numerous variables. In this article, we investigate the reconfiguration within a core network slice with aim of minimizing long-term resource consumption by exploiting Deep Reinforcement Learning (DRL). This problem is also intractable by using conventional Deep Q Network (DQN), as it has a multi-dimensional discrete action space which is difficult to explore efficiently. To address the curse of dimensionality, we propose to exploit Branching Dueling Q-network which incorporates the action branching architecture into DQN to drastically decrease the number of estimated actions. Based on the discrete BDQ network, we develop an intelligent network slice reconfiguration algorithm (INSRA). Extensive simulation experiments are conducted to evaluate the performance of INSRA and the numerical results reveal that INSRA can minimize the long-term resource consumption and achieve high resource efficiency compared with several benchmark algorithms.

To address the drastic increase of multimedia traffic dominated by streaming videos, mobile edge computing (MEC) can be exploited to accelerate the development of intelligent caching at mobile network edges to reduce redundant data transmissions and improve content delivery performance. Under the MEC architecture, content providers (CPs) can access MEC servers to deploy popular content items to improve users' quality of experience. Designing an efficient caching policy is crucial for CPs due to the content dynamics, unknown spatial-temporal traffic demands and limited storage capacity. The knowledge of users' preference is important for efficient caching, but is also often unavailable in advance. Machine learning can be used to learn the users' preference based on historical demand information and decide the content items to be cached at the MEC servers. In this paper, we propose a learning based cooperative content caching policy for the MEC architecture, when the users' preference is unknown and only the historical content demands can be observed. We model the cooperative content caching problem as a multi-agent multi-armed bandit problem and propose a multiagent reinforcement learning (MARL)-based algorithm to solve the problem. Simulation experiments are conducted based on the real dataset from MovieLens and the numerical results show that the proposed MARL-based caching policy can significantly improve content cache hit rate and reduce content downloading latency in comparison with other popular caching strategies.

In this paper, we investigate the resource management for radio access network slicing from user access control and wireless bandwidth allocation perspectives. First, to guarantee users' QoS, we propose two admission control (AC) policies to select admissible users from the perspective of optimizing the QoS and the number of serving users respectively. Then, to optimize the bandwidth utilization for the selected admissible users, we investigate the slice association and bandwidth allocation (SABA) problem and propose network centric and UE centric SABA policies respectively. Numerical results show that in typical scenarios, our proposed AC and SABA policies can significantly outperform traditional policies in terms of wireless bandwidth utilization and number of admissible users.

Answer selection is an important method to achieve better user experience in question answering (QA) systems and it is essential in ensuring better QA matching performance. Improving mutual information between QA pairs is a useful way to obtain the matching degree improvement and question rewriting has been proven a helpful way in utilizing mutual interaction between questions and answers. In this research, we focus on syntax tree aware question rewriting inspired by the thought of integrating syntactic information into question answering. Besides, to improve the quality of rewriting, we employ the generative adversarial network for rewriting optimization, which consists of a syntax tree aware rewriting model and a discriminator. The quality information given by the discriminator guides the optimizing of the rewriting model in the training phase. The experimental study has shown the effectiveness of syntax tree aware question rewriting and utilizing the generative adversarial network for rewriting.

4G systems employ discontinuous reception (DRX) mechanism to conserve energy by intermittently suspending network connections. Moving to 5G, a wide range of applications with diverse characteristics need to be supported. Especially, machine-type communication (MTC) has been identified as one of the three generic 5G services. Compared with that of human-type communication (HTC), the traffic patterns of MTC could be very bursty and even nonstationary. Thus, using the legacy DRX mechanism will cause longer access delay and/or higher power consumption. In this paper, we propose a new online learning-based DRX mechanism, called AC-DRX, with aim to improve device energy efficiency for MTC services by adapting to varying traffic pattern. In AC-DRX, the time is slotted into intervals and actor-critic (AC) algorithm is used for adjusting DRX cycles by learning the traffic statistics at the beginning of every time interval. To accelerate the learning process, we propose a symmetric sampling method in the AC algorithm. Numerical results show that our proposed AC-DRX mechanism significantly outperforms the legacy DRX and extended DRX mechanisms in terms of both delay and energy efficiency. The performance is fairly close to the upper bound where perfect traffic knowledge is assumed known.

Network slicing is a fundamental architectural technology for the fifth generation mobile network. It is challenging to design a robust end-to-end network slice spanning overall networks, where a slice is constituted by a set of virtual network functions (VNFs) and links. Bugs may accidentally occur in some VNFs, invalidating some slices, and triggering slice recovery processes. Besides, the traffic demands in each slice can be stochastic, and drastic changes of traffic demands may trigger slice reconfiguration. In this paper, we investigate robust network slicing mechanisms by addressing the slice recovery and reconfiguration in a unified framework. We first develop an optimal slice recovery mechanism for deterministic traffic demands. This optimal solution is used as a benchmark for evaluating other robust slicing algorithms. Then, we design an optimal joint slice recovery and reconfiguration algorithm for stochastic traffic demands by exploiting robust optimization. To tackle the slow convergence issue in the robust optimization algorithm, we propose a heuristic algorithm based on variable neighborhood search. Numerical results reveal that our proposed robust network slicing algorithms can provide adjustable tolerance of traffic uncertainties compared with the deterministic algorithm.

As network function virtualization (NFV) is realized based on general-purpose processors for avoiding proprietary hardware, its benefits of flexibility and agility could be compromised by the increased packet latency and reduced throughput. An effective approach for improving the latency and throughput performance is to exploit new network function (NF) processing framework on general purpose processors. In this paper, we propose a new joint two-tier NF parallelization (TNP) framework, which can agilely and flexibly organize parallel NF processing to greatly improve the latency and throughput performance of service function chain (SFC) which is constituted by a set of NFs. In TNP, we jointly organize the parallelization of multiple NFs at the service tier and perform multicore mapping of individual NFs at the substrate network tier. We formulate the optimal TNP design problem as minimizing link bandwidth consumption subject to end-to-end latency and computing resource constraints. We solve the problem by decomposing it into two easier subproblems: 1) subproblem 1 (SP1) is to solve the optimal SFC parallelization graph design in conjunction with link mapping problem and 2) subproblem 2 (SP2) is to jointly solve computing resource allocation in conjunction with node mapping problem. The global optimal solution is accomplished by searching in a set of feasible regions in sequence. Numerical results demonstrate that our proposed TNP can significantly decrease service latency and improve network throughput compared with known single layer NF parallelization schemes. Moreover, the link bandwidth utilization and SFC request acceptance rate in the substrate network can also be greatly improved.

Network slicing enables diversified services to be accommodated by isolated slices in network function virtualization-enabled software-defined networks. To maintain satisfactory user experience and high profit for service providers in a dynamic environment, a slice may need to be reconfigured according to the varying traffic demand and resource availability. However, frequent reconfigurations incur certain cost and might cause service interruption. In this paper, we propose a hybrid slice reconfiguration (HSR) framework, where a fast slice reconfiguration (FSR) scheme reconfigures flows for individual slices at the time scale of flow arrival/departure, while a dimensioning slices with reconfiguration (DSR) scheme is occasionally performed to adjust allocated resources according to the time-varying traffic demand. In order to optimize the slice’s profit, i.e., the total utility minus the resource consumption and reconfiguration cost, we formulate the problems for FSR and DSR, which are difficult to solve due to the discontinuity and non-convexity of the reconfiguration cost function. Hence, we approximate the reconfiguration cost function with${L} _{1}$norm, which preserves the sparsity of the solution, thus facilitating restricting reconfigurations. Besides, we design an algorithm to schedule FSR and DSR, so that DSR is timely triggered according to the traffic dynamics and resource availability to improve the profit of slice. Furthermore, we extend HSR with a resource reservation mechanism, which reserves partial resources for near future traffic to reduce potential reconfigurations. Numerical results validate that our reconfiguration framework is effective in reducing reconfiguration overhead and achieving high profit for slices.

To address the increase of multimedia traffic dominated by streaming videos, user equipment (UE) can collaboratively cache and share contents to alleviate the burden of base stations. Prior work on device-to-device (D2D) caching policies assumes perfect knowledge of the content popularity distribution. Since the content popularity distribution is usually unavailable in advance, a machine learning-based caching strategy that exploits the knowledge of content demand history would be highly promising. Thus, we design D2D caching strategies using multi-agent reinforcement learning in this paper. Specifically, we model the D2D caching problem as a multi-agent multi-armed bandit problem and use Q-learning to learn how to coordinate the caching decisions. The UEs can be independent learners (ILs) if they learn the Q-values of their own actions, and joint action learners (JALs) if they learn the Q-values of their own actions in conjunction with those of the other UEs. As the action space is very vast leading to high computational complexity, a modified combinatorial upper confidence bound algorithm is proposed to reduce the action space for both IL and JAL. The simulation results show that the proposed JAL-based caching scheme outperforms the IL-based caching scheme and other popular caching schemes in terms of average downloading latency and cache hit rate.

As Network Function Virtualization (NFV) is based on general purpose processors for avoiding any proprietary hardware, the benefits of NFV could be compromised by increased packet latency and reduced throughput. One feasible solution is to exploit new network function (NF) framework with aim of reducing the processing latency in NFs. In this paper, we propose a new joint Two-Tier NF Parallelization (TNP) framework, which can agilely and flexibly organize parallel NF processing and map individual NFs to one or multiple processing core(s). In TNP, we jointly design the parallelization of multiple NFs at service tier and the multicore mapping of individual NF at substrate network tier. We formulate the optimal TNP design problem as maximizing link bandwidth utilization subject to end-to-end latency and computing resource constraints. The global optimal solution is accomplished by searching in a set of feasible regions in sequence. Numerical results demonstrate that our proposed TNP can significantly decrease the latency in NF processing and improve network throughput compared with single layer parallelization SFC framework.

Network slicing enables diversified services to be carried in isolated slices. To maintain the quality of service and achieve high profit of a slice in dynamic environments, it is vital to agilely reconfigure the resource allocation for the slice. However, frequent reconfigurations also incur certain cost and might cause service interruption. To maximize the slice's profit and reduce the reconfiguration overhead, we propose a fast slice reconfiguration (FSR) scheme to cope with small traffic variations of individual slices at the time scale of flow arrival/departure. Due to small traffic variations, the FSR only reconfigures bandwidth and VNF capacity allocation for partial flows. We formulate the optimization problem for FSR, which is difficult to solve due to the discontinuity and non-convexity of the reconfiguration cost function. We propose to approximate the reconfiguration cost function with L1 norm, which preserves the sparsity of solution, thus avoiding unnecessary reconfigurations. Besides, the FSR problem should be solved efficiently, so that slices could be reconfigured timely. Hence, we exploit the dual-ADMM method to solve the problem in a distributed manner for large slices. Numerical results validate the effectiveness of the proposed FSR scheme and the distributed computing method for FSR problem.

Recently network slicing has been introduced as a key enabler to accommodate diversified services in NFV- enabled software-defined mobile networks. Although there has been some research work on network slice deployment and configuration, how user equipments (UEs) select the most appropriate network slice is still an essential yet challenging issue, as slice selection may substantially affect the resource utilization and user quality of service. In this paper, we investigate the optimal selection of end-to-end slices with aim of improving network resources utilization while guaranteeing the quality of service (QoS) of users. We formulate the optimal slice selection problem as maximizing the users' satisfaction degree, and prove it is NP-hard. We thus resort to genetic algorithm (GA) to find a sub-optimal solution, and develop a heuristic algorithm based on GA algorithm. The effectiveness of our proposed NS selection algorithm is validated via simulation experiments.

4G systems employ Discontinuous Reception (DRX) mechanism to conserve energy by intermittently suspend network connections. Moving to 5G, using the same DRX will cause longer access delay and higher power consumption for Machine-Type traffic. To address this problem, we propose to use actor- critic algorithm for choosing DRX cycles based on traffic statistics and to use symmetric sampling to accelerate online learning. Numerical results show that the new AC-DRX mechanism performs significantly better than DRX in both delay and energy efficiency. The performance is actually fairly close to the upper bound where perfect traffic knowledge is known.

The millimeter wave (mmWave) radio band is promising for the next-generation heterogeneous cellular networks (HetNets) due to its large bandwidth available for meeting the increasing demand of mobile traffic. However, the unique propagation characteristics at mmWave band cause huge redundant handoffs in mmWave HetNets that brings heavy signaling overhead, low energy efficiency and increased user equipment (UE) outage probability if conventional Reference Signal Received Power (RSRP) based handoff mechanism is used. In this paper, we propose a reinforcement learning based handoff policy named SMART to reduce the number of handoffs while maintaining user Quality of Service (QoS) requirements in mmWave HetNets. In SMART, we determine handoff trigger conditions by taking into account both mmWave channel characteristics and QoS requirements of UEs. Furthermore, we propose reinforcement-learning based BS selection algorithms for different UE densities. Numerical results show that in typical scenarios, SMART can significantly reduce the number of handoffs when compared with traditional handoff policies without learning.

In this paper, we propose software-defined protocol (SDP) technique to facilitate flexible service-oriented protocol stack deployment for providing high-throughput, low-latency and elastic mobile services based on platform virtualization and functionality modularization. We first elaborate the principle of SDP and then address one of the most important issues in SDP, namely SDP request mapping (SDPM), where an SDP request is fulfilled by mapping a set of required SDP function blocks and virtual links onto underlying SDP servers. We formulate the SDPM problem as a mixed integer programming (MIP). To address the NP-hardness and scalability of SDPM problem, we propose a decomposition algorithm which breaks down the SDPM problem into inter-block link and block mapping problems to accomplish the upper bound (UB) and lower bound (LB) of the MIP solution, respectively. The optimality can be achieved when the UB and the LB converges by using iterations. We employ LTE Layer-2 data-plane processing as a benchmark for validating the effectiveness of the SDP technique and evaluate the performance of SDPM algorithm. Numerical results show that SDP is effective to provide elastic low-latency mobile services and the proposed SDPM algorithm significantly outperforms the benchmark in stack processing delay, mapping cost, and resource utilization.

Machine type communication (MTC) is deemed as one of the killer applications in 5G mobile communication networks, for which power saving is an important yet challenging issue. In current cellular networks, most proposed power-saving mechanisms are designed for human-to-human (H2H) communications, and thus not applicable to MTC. Hence, it is imperative to design effective power-saving mechanisms for MTC in 5G networks. 3GPP has proposed Discontinuous Reception (DRX) mechanism to allow users receive data at specified time slots and turn off the radio module at other time slots, aiming at reducing power consumption. In this paper we design an energy efficient coercive sleep mode (CSM) to reduce power consumption, based on the idea of DRX. In CSM, a metric “NUMBER” is introduced to record the number of packets in addition to inactivity timer in DRX. We use a semi-Markov process to model mechanism, for evaluating the power saving factor and wake up latency. We also employ simulation to examine the impact of DRX parameters on system performance. Numerical results show that CSM achieves significantly higher energy efficiency and is thus appropriate for low cost MTC, compared with standard DRX.

Recently network slicing has been identified as a promising network architectural technology for the next generation mobile cellular networks (5G) to address the challenges stemming from a wide range of applications. Especially, for machine type communication (MTC) application, it is widely recognized that traditional cellular network architecture is not adequate to meet the requirements in terms of massive connectivity and low latency. For exploiting network slicing, data aggregation (DA) can be adopted to effectively address the massive connectivity and latency requirement. In this paper, we propose an efficient network slicing data aggregation (NSDA) scheme for MTC applications. Different from conventional DA scheme where data aggregation is performed based on device locations, we perform DA according to latency requirement for MTC devices (MTCDs), with aim to exploit the benefits of network slicing and thus improve network access capacity and decrease access latency. We formulate the DA problem as a 0-1 Linear Programming and propose an efficient two-step algorithm to aggregate the MTC data for accessing a specific network slice. We examine the performance of our proposed NSDA in typical MTC scenarios via simulations. Numerical results reveal that NSDA significantly outperforms traditional MTC access schemes (without network slicing) in terms of network capacity, access congestion degree, latency, etc.

To address the vast multimedia traffic volume and requirements of user Quality of Experience (QoE) in the next generation mobile communication system (5G), it is imperative to develop efficient content caching strategy at mobile network edges, which is deemed as a key technique for 5G. Recent advances in edge/cloud computing and machine learning facilitate efficient content caching for 5G, where mobile edge computing (MEC) can be exploited to reduce service latency by equipping computation and storage capacity at the edge network. In this paper, we propose a proactive caching mechanism named Learning based Cooperative Caching (LECC) strategy based on MEC architecture to reduce transmission cost while improving user QoE for future mobile networks. In LECC, we exploit a Transfer Learning (TL)-based approach for estimating content popularity, and then formulate the proactive caching optimization model. As the optimization problem is NP- hard, we resort to a greedy algorithm for solving the cache content placement problem. Performance evaluation reveals that LECC can apparently improve content cache hit rate, decrease content transmission cost in comparison with known existing caching strategies.

The millimeter wave (mmWave) radio band is promising for the next-generation heterogeneous cellular networks (HetNets) due to its large bandwidth available for meeting the increasing demand of mobile traffic. However, the unique propagation characteristics at mmWave band cause huge redundant handoffs in mmWave HetNets if conventional Reference Signal Received Power (RSRP) based handoff mechanism is used. In this paper, we propose a reinforcement learning based handoff policy named LESH to reduce the number of handoffs while maintaining user Quality of Service (QoS) requirements in mmWave HetNets. In LESH, we determine handoff trigger conditions by taking into account both mmWave channel characteristics and QoS requirements of UEs. Furthermore, we propose reinforcement-learning based BS selection algorithms for different UE densities. Numerical results show that in typical scenarios, LESH can significantly reduce the number of handoffs when compared with traditional handoff policies.

End-to-end network slicing has been viewed as a key enabler for the next generation mobile network (5G), where a Slice Provider (SP) creates various network slices for Slice Customers (SCs) to accommodate diverse services. Due to resource isolation, effective resource allocation for coexisted multiple network slices, \textit{i.e.} network slice dimensioning, is essential to maximize network resource efficiency. From the perspective of operators, both SP and SC pursue a profit-earning business model. However, the relationship between resource efficiency and profit maximization is not clear so far. In this paper, we study network slice dimensioning with resource pricing policy, by exploring this relationship. We first develop an optimization framework for network slice dimensioning, in which the Slice Customer's Problem (SCP) maximizes the SC's profit and the Slice Provider's Problem (SPP) maximizes net social welfare (resource efficiency). We find that maximization of net social welfare and SP's profit are two consistent objectives when resources are scarce; otherwise, there is a tradeoff. Based on this finding, we propose a low-complexity distributed algorithm to achieve near-optimal net social welfare with profit guarantee for SP/SCs. Simulations and numerical results verify the effectiveness of our proposed slice dimensioning strategy, which can help fully exploiting the capability of network slicing.

The integration of multiple Radio Access Technologies (RATs) of licensed or unlicensed bands is considered as a cost-efficient way to greatly increase network capacity of mobile networks. In this paper, we propose a Smart Aggregated RAT Access (SARA) strategy with aim to maximize network throughput while meeting diverse traffic Quality of Service (QoS) requirements. We consider a scenario where users with different QoS requirements access to the Heterogeneous Network (HetNet) with coexisting Cellular-WiFi. In order to maximize network resource utilization in such a complex and dynamic environment, we exploit multi-agent reinforcement learning to perform RAT selection in conjunction with resource allocation for individual users based on sensing dynamic channel states and traffic characteristics. We first use Nash Q-learning to provide a set of feasible RAT access strategies, and then employ Monte-Carlo (MCTS) based Q-learning to perform resource allocation which tries to maximize system throughput while meeting traffic QoS requirements. Numerical results reveal that the network access capacity can be maximized while meeting traffic QoS requirements with limited number of searches by using our proposed SARA. Compared with traditional WiFi offloading schemes, SARA can significantly improve system resource utilization and capacity while guaranteeing QoS requirements of UEs.

In heterogeneous cellular networks (HetNets), cell association of User Equipment (UE) affects UE transmit rate and network throughput. Conventional cell association rules are usually based on UE received Signal-to-Interference-and-Noise-Ratio (SINR) without taking into account user behaviors, which can indeed be exploited for improving network performance. In this paper, we investigate UE cell association in HetNets based on individual user behavior characteristics with aim to maximize long- term expected system throughput. We model the problem as a stochastic optimization model Restless Multi-Armed Bandit (RMAB). As it is a PSPACE-hard problem, we develop a primal-dual heuristic index algorithm and the solution specifies the rule that determines which arms in the RMAB model to be selected at each decision time. According to the solution of RMAB, we propose a new cell association strategy called Index Enabled Association (IDEA). We also conduct simulation experiments to compare IDEA with conventional max-SINR cell association strategy and an existing game-based RAT selection scheme. Numerical results demonstrate the advantages of IDEA in typical scenarios.

In dense and heterogeneous networks, the decoupled uplink#x002F;downlink (UL#x002F;DL) access (DUDA) design has drawn great attentions for improving system performance. Energy efficiency (EE) becomes a major concern for densely deployed heterogeneous cellular networks (HetNets). In this paper, we theoretically analyze the energy efficient sleep strategy for DUDA HetNets. Through using stochastic geometry theory, we first examine the applicability of conventional sleep strategy to DUDA networks and design a new DUDA sleep strategy. We then formulate the energy consumption minimization problem and EE optimization problem, and derive the optimal BS sleep probability. Numerical results reveal that conventional sleep strategy may provide inaccurate guidance for sleep design in DUDA networks, which may lead to excessive sleeps and decrease system EE. Meanwhile our DUDA sleep strategy can effectively reduce network energy consumption. We also find that the dense deployment of small cells may generally increase network EE, but this improvement saturates as the BS density further increases.

To address the explosively growing demand for mobile data services in the 5th generation (5G) mobile communication system, it is important to develop efficient content caching and distribution techniques, aiming at significantly reducing redundant data transmissions and improving content delivery efficiency. In heterogeneous cellular network (HetNet), which has been deemed as a promising architectural technique for 5G, caching some popular content items at femto base-stations (FBSs) and even at user equipment (UE) can be exploited to alleviate the burden of backhaul and to reduce the costly transmissions from the macro base-stations to UEs. In this paper, we develop the optimal cooperative content caching and delivery policy, for which FBSs and UEs are all engaged in local content caching. We formulate the cooperative content caching problem as an integer-linear programming problem, and use hierarchical primal-dual decomposition method to decouple the problem into two level optimization problems, which are solved by using the subgradient method. Furthermore, we design the optimal content delivery policy, which is formulated as an unbalanced assignment problem and solved by using Hungarian algorithm. Numerical results have shown that the proposed cooperative content caching and delivery policy can significantly improve content delivery performance in comparison with existing caching strategies.

The next generation mobile communication system (5G) needs to address the challenges stemming from the performance requirements in diverse technical scenarios, such as low power massive connections for machine type communications (MTC). Heterogeneous Network (HetNet) has been identified as a promising network architecture for 5G. In HetNets, traffic offloading can be exploited to effectively improve network capacity by utilizing complementary network communication techniques. In this paper, we propose a new Device-to-Device (D2D) communication assisted mobile traffic offloading (DATO) scheme, with focus on massive connectivity. In DATO, some user equipments (UEs) can be offloaded from macro base stations (MBSs) to small base stations (SBSs) via D2D communications, so as to improve overall network capacity. We formulate the DATO problem as a 0-1 Linear Programming and use dynamic programming to provide the optimal solution for determining the access mode of UEs. Numerical results reveal that DATO significantly outperforms traditional UE access schemes in terms of number of admitted UEs and UE energy consumption, etc.

The next generation mobile network (5G) faces enormous challenges with increasing mobile multimedia and data services. To address the vast data traffic volume and minimize transmission cost, it is imperative to develop efficient content caching strategy, which is deemed as a key technique for 5G. In this paper, we exploit cloud computing and network coding techniques in mobile networks, based on a Hierarchical Cloud Service Network (HCSN) architecture, to provision content delivery service on demand. In our proposed content caching framework, cloud service providers deploy a plurality of cloudlets at the edge of network, to fulfill data service requirements by caching and transmission of data content. We design a Network Coding based Caching Policy (NCCP) based on greedy algorithm. Local cloudlets cache data content in advance, update the cache dynamically and transmit data content in a cooperative way. We use simulation experiments to validate the effectiveness of our proposed caching strategy. Numerical results show that the proposed strategy can significantly improve the cache hit rate as well as reduce average transmission cost in HCSN.

Femtocells are widely recognized as a promising technology to meet the requirements of indoor coverage in forthcoming fifth generation cellular networks (5G). As femtocell holders (FHs) can be users themselves or mobile network operators, it makes challenges to holistic network resource utilization. In particular, due to the selfishness nature, FHs are usually unwilling to accommodate extra users without compensation. This inspires us to develop an effective refunding mechanism, with aim to allow competitive network operators to employ truthful refunding policy, and to encourage FHs to make appropriate access permission. In this paper, we first define a refunding strategy function and price-coefficient for the refunding policy. We then formulate the access permission as a Stackelberg game and theoretically prove the existence of unique Nash Equilibrium. Numerical results validate the effectiveness of our proposed mechanism and overall network efficiency is improved significantly as well.

Virtualization of network functions and centralized management are anticipated to provide 5G mobile networks with flexibility, lower end-to-end latency and reduced cost. Based on the concept of emerging Software Defined Network (SDN) and Network Function Virtualization (NFV) techniques, we propose Software Defined Protocol (SDP) technique to facilitate a flexible service-oriented protocol stack deployment under centralized network control. The design objective of SDP is to provide high-throughput, low-latency and elastic mobile services by making data-plane protocol programmable. In this paper, we first elaborate the SDP mechanisms and then address one of the most important issues in SDP, namely protocol stack mapping (PSM). We formulate the PSM problem as a 0-1 quadratic programming for selecting the optimal SDP servers to balance network load. We employ the legacy LTE data-plane processing as a benchmark for validating the effectiveness of the SDP and PSM algorithm. Numerical results show that SDP is effective to provide elastic low-latency mobile services and the proposed PSM algorithm significantly outperforms the benchmark in stack processing delay, mapping cost and resource utilization.

The ever increasing video demands from mobile users have posed great challenges to cellular networks. To address this issue, video caching in radio access networks (RANs) has been recognized as one of the enabling technologies in future 5G mobile networks, which brings contents near the end-users, reducing the transmission cost of duplicate contents, meanwhile increasing the Quality-of-Experience (QoE) of users. Inspired by the emerging software-defined networking technology, recent proposals have employed centralized collaborative caching among cells to further increase the caching capacity of the RAN. In this paper, we explore a new dimension in video caching in software-defined RANs to expand its capacity. We enable the controller with the capability to adaptively select the bitrates of videos received by users, in order to maximize the number and quality of video requests that can be served, meanwhile minimizing the transmission cost. To achieve this, we further incorporate Scalable Video Coding (SVC), which enables caching and serving sliced video layers that can serve different bitrates. We formulate the problem of joint video caching and scheduling as a reward maximization (cost minimization) problem. Based on the formulation, we further propose a 2-stage rounding-based algorithm to address the problem efficiently. Simulation results show that using SVC with collaborative caching greatly improves the cache capacity and the QoE of users.

The rapid evolution of cellular networks has brought great changes to mobile network architecture. One trend is the dense deployment of base stations (BSs) in heterogeneous cellular network (HetNets) architecture. On the other hand, the booming mobile Internet applications introduce increasingly significant imbalance in regard to Signal to Interference and Noise Ratio (SINR) statistics and traffic load between uplink (UL) and downlink (DL) in HetNets. These evolutions inspire us to exploit decoupling of UL and DL in HetNets for improving system performance. In this paper, we conduct a comparison study for the system performance of the decoupled UL/DL access (DUDA) mode and traditional coupled UL/DL access (CUDA) mode based on stochastic geometry theory. Compared to existing related work, we establish an analytical model for CUDA mode as a comparison reference and consider a more realistic system model, where we employ dynamic transmit power control in UL transmission by applying fractional power control (FPC) to model a location-dependent per-mobile power state. Numerical results reveal that DUDA mode significantly outperforms CUDA mode in terms of system rate, spectral efficiency (SE) and energy efficiency (EE) in HetNets. In addition, results also show that DUDA mode can improve load balance and fairness. Simulation results further validate the accuracy of our analytical model.

In Delay Tolerant Networks (DTNs), how to transmit data efficiently is one of the most important issues. Recently, Random Linear Network Coding (RLNC) is proposed as a promising approach to improve data transmission efficiency in DTNs. To facilitate the development of deployment of RLNC based routing protocols, it is imperative to quantify the performance gain brought by RLNC in a rigorous and systematic way. In this paper, we develop an analytical model to evaluate the data transmission performance of RLNC based epidemic routing in DTNs. In the model, we consider that multiple unicast communication sessions compete for limited transmission capacity. Numerical results validate the effectiveness of our analytical model and demonstrate the significant performance improvement for data transmission in DTNs by using RLNC. Our work in this paper provides a general tool for performance evaluation and useful guidelines for designing RLNC based routing protocols in DTNs.

In maritime networks, the communication links are characterized by high dynamics due to ship mobility and fluctuation of the sea surface. Some researchers have considered using Delay Tolerant Network (DTN) to improve the performance of data transmission in maritime environment. Most existing work on maritime DTNs usually uses simulation to evaluate the transmission performance in maritime DTNs. In this paper, we develop a theoretical model to analyze the performance of data transmission in maritime DTNs. We first construct a model to describe the ship encounter probability. Then, we use this model to analyze the data delivery ratio from ships in the seaway to the base station (BS) at coast. Based on the data of tracing the ships navigating in a realistic seaway, we develop a simulator and validate the theoretical models. In addition, by comparing the performance of DTN transmission protocol and traditional end-to-end transmission protocol, we validate that DTN protocol can effectively improve the performance of data transmission in maritime networks.

Traditional wireless communication systems focus on Spectral Efficiency (SE) with excessive energy consumption. With widespread attention on global warming and excessive energy consumption, system designers began focusing on energy efficiency (EE) instead of the traditional spectral efficiency. A system that maximizes either spectral efficiency or energy efficiency without taking into account the variation of traffic load will lead to poor system performance in terms of outage probability, throughput and energy efficiency. To address this issue, in this paper we propose a Dynamic Traffic-aware Reconfiguration (DTR) scheme, aiming at maximizing the average system EE while guaranteeing the required system performance. This is fulfilled by reconfiguring the system to SE, EE or hybrid SE-EE system according to the traffic load. The key criterion for reconfiguring the system is the outage probability, which is estimated through using a queuing model. We implement DTR scheme in 3GPP LTE system level simulator and conduct intensive simulation experiments to validate the effectiveness of our proposed DTR scheme. Numeric results show that DTR can maximize the average EE while guaranteeing the system performance compared to pure SE or EE system.

Mobile station (MS) localisation that plays an important role in the process of target continuous localisation has received considerable attention. In this study, a new framework based on subspace approach for positioning an MS at minimum localisation system with the use of time-of-arrival measurements is introduced. Unlike ordinary multidimensional scaling algorithm using eigendcomposition or inverse computation to estimate the MS position, a computationally simple weighting estimator is proposed by introducing Lagrange multiplier and mean-square error weighting matrix. Computer simulations are included to corroborate the theoretical development and to contrast the estimator performance with several conventional algorithms as well as the Cramér–Rao lower bound (CRLB). It is shown that the new method with low computational complexity attains the CRLB for zero-mean white Gaussian range error at moderate noise level.

Link duration is a main factor in determining the transmission capacity between two encounter nodes in Delay Tolerant Networks (DTNs). Existing research on DTN transmission capacity usually assumes that a node is able to immediately discover the nodes which move into its transmission range. Under this assumption, the link duration in DTNs is determined by the moving speed and transmission distance of encounter nodes. However, this assumption could be invalid in realistic DTNs where the nodes use a contact probing protocol to detect their neighbors. In this paper, we investigate the impact of contact probing mechanisms on link duration, and thus the transmission capacity of DTNs. We first derive the probability distribution of link duration, and analyze the impact of contact probing mechanisms on the total link durations. Based on that, we derive the theoretical node throughput and energy consumption, and explore their tradeoff. In addition, we provide an approach to compute the optimal contact probing frequency under energy limitation and adjust the probing frequency according to the node encountering rate. Simulation experiments based on simulator The ONE validates the correctness and the accuracy of our analytical model.

Mobile station (MS) localisation, which plays an important role in the process of target continuous localisation, has received considerable attention. In this study, a new framework based on subspace approach for positioning an MS at three or more base stations (BSs) with the use of time-of-arrival (TOA) measurements is introduced. It is shown that the proposed approach is a generalisation of the mobile localisation method based on multidimensional scaling (MDS) analysis. Through computer simulations and computational complexity analysis, the authors can see that the proposed algorithm has a comparable performance with conventional MDS localisation method, however, the computational complexity has been greatly reduced.

Cooperative relay has been recognized as a promising approach for improving transmission efficiency and error performance in wireless networks. A number of realizations of cooperative relay communications, such as Amplify-and-Forward (AF), Decode-and-Forward (DF), have been proposed and the capacity gain of these replay approaches has been widely investigated. In this paper, we consider a cooperative relay approach using fountain codes, called Fountain-Coding-and-Forward (FCF) and derive its upper bound of the information theoretic capacity in a general 3-node relay channel model. Numerical results reveal that the upper bound of FCF is higher than that of AF, DF and conventional direct transmission. This result suggests that cooperative relay in conjunction with fountain codes can potentially provides considerable benefits in terms of transmission capacity for reliable data transmission in wireless networks.