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.

By leveraging the parameter-efficient fine-tuning (PEFT) technology, large pre-trained models (LPMs) can effectively capture task-specific PEFT knowledge and generalize to downstream artificial intelligence (AI) tasks emerging in wireless networks. However, the inherent system heterogeneity of wireless networks and data across users brings difficulties in combining the PEFT knowledge of users. This in turn hinders the enhancement of LPM's global generalization capability. In this paper, we propose a distributed fine-tuning (DFT) scheme based on PEFT knowledge sharing, to capture the global PEFT knowledge of downstream users by aggregating heterogeneous PEFT models. In DFT, we use low-rank adaption (LoRA) model to capture the PEFT knowledge of users, where the LoRA models can be heterogeneous for different users with specific resource constraints. Then, we further design an aggregation and iterative training strategy for the heterogeneous LoRA models. The numerical results verify the effectiveness and advantages of the proposed DFT scheme in enhancing the global generalization capability of LPM in resource-heterogeneous wireless networks.

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.

Federated Learning (FL) has been widely recognized as a promising promoter for future intelligent wireless networks, by collaboratively training a global machine learning (ML) model in a privacy-preserving manner. However, the transmission of large-scale models between clients and servers is susceptible to the limitation of available communication resources which deteriorates FL performance. Some recently proposed model quantization techniques can effectively reduce communication costs by compressing the amount of model data to be transmitted. Unfortunately, conventional quantization methods face difficulties in wireless with rapidly changing channels. In this paper, we propose a federated learning scheme with incremental model quantization and uploading mechanism, called Fed_IQ. Specifically, individual clients quantize the gradients of the local model to obtain base gradients as well as incremental gradients and send them to the server. Then the server combines the base and incremental gradients to obtain a more accurate global model where the quantization levels of gradients can be adaptively adjusted according to the instantaneous channel states. Experimental results show our proposed Fed_IQ can significantly reduce transmission delay and improve model accuracy in a wireless network compared with state-of-the-art algorithms.

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.

Federated learning (FL) has been vigorously promoted in wireless edge networks as it fosters collaborative training of machine learning (ML) models while preserving individual user privacy and data security. In conventional FL, user equipments (UEs) and an aggregator can collaboratively train a globally shared ML model by transmitting ML models instead of raw data. In wireless edge networks, the heterogeneity of multidimensional resources (e.g., computing and communication re-sources) used to transmit ML models may introduce stragglers in FL, characterized by a slow update and/or transmission of local models. The stragglers in FL can significantly degrade learning efficiency and accuracy, as the slowest UE participating in the FL can dramatically slow down entire convergence. In this paper, to alleviate the negative impact of stragglers, we propose a dynamic straggler-aware clustering based FL mechanism, called FeDSC, via adaptive UE clustering. Specifically, we first group participating UEs into multiple clusters based on their computing capability and available wireless resources. Then, we propose an adaptive UE selection scheme to synchronously update the cluster aggregation model. Meanwhile, an edge server performs global aggregation of different cluster models in an asynchronous time-triggered manner. Numerical results show that our proposed FeDSC mechanism can achieve significant performance improvement in terms of training time and model accuracy in comparison to classical FL benchmarks.

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.

Federated learning (FL) has been vigorously promoted in wireless edge networks as it fosters collaborative training of machine learning (ML) models while preserving individual user privacy and data security. In conventional FL, user equipment (UE) and an aggregator can collaboratively train shared global ML models by transmitting interactive ML models. In wireless edge networks, heterogeneity of multi-dimensional resources (e.g., computing and communication resources) used to train and transmit FL models may introduce stragglers, characterized by a slow update and/or transmission of local models. The stragglers can significantly degrade learning performance of FL, as the slowest participating UE can dramatically slow down the entire convergence. In this paper, to alleviate the negative impact of stragglers, we propose a dynamic straggler-aware clustering based FL (FeDSC) mechanism via adaptive UE clustering. Specifically, we first group participating UEs into multiple clusters based on their available computing and wireless resources. Then, we propose an adaptive clustering scheme to synchronously update the cluster aggregation model. Meanwhile, an edge server performs global aggregation of different cluster models in an asynchronous manner. Finally, we theoretically demonstrate the convergence of our proposed mechanism via numerical results. Numerical results show that our proposed mechanism can effectively reduce training time and wireless bandwidth consumption, while improving training efficiency and guaranteeing learning accuracy.

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.

Federated learning (FL) can be used in mobile-edge networks to train machine learning models in a distributed manner. Recently, FL has been interpreted within a model-agnostic meta-learning (MAML) framework, which brings FL significant advantages in fast adaptation and convergence over heterogeneous data sets. However, existing research simply combines MAML and FL without explicitly addressing how much benefit MAML brings to FL and how to maximize such benefit over mobile-edge networks. In this article, we quantify the benefit from two aspects: 1) optimizing FL hyperparameters (i.e., sampled data size and the number of communication rounds) and 2) resource allocation (i.e., transmit power) in mobile-edge networks. Specifically, we formulate the MAML-based FL design as an overall learning time minimization problem, under the constraints of model accuracy and energy consumption. Facilitated by the convergence analysis of MAML-based FL, we decompose the formulated problem and then solve it using analytical solutions and the coordinate descent method. With the obtained FL hyperparameters and resource allocation, we design an MAML-based FL algorithm, called automated FL (AutoFL), that is able to conduct fast adaptation and convergence. Extensive experimental results verify that AutoFL outperforms other benchmark algorithms regarding the learning time and convergence performance.

Data collaboration enables multiple parties to pool data for deriving meaningful data insights. However, data misuse and unlawful data collection have led to precautionary measures being imposed by individual organizations to guide against data leakage and abuse. As a response, decentralized federated learning (DFL) has emerged as an attractive paradigm to facilitate data collaboration while being amenable to privacy-preserving data and knowledge sharing, cost reduction, and prediction accuracy improvement. Unfortunately, the participating parties in DFL tend to be heterogeneous with skew datasets and uneven capabilities. Inevitably, training and transmission costs, and the presence of free-riders pose challenges to the adoption and participation of DFL. The absence of centralized parameter servers further exacerbates the problem of evaluating the contribution of each individual party. Therefore, an effective incentive mechanism is essential to promote data collaboration. In this paper, we propose a novel Incentive-aware Decentralized fEderated leArning (IDEA) framework for facilitating data collaboration. Specifically, we first design a customizable reward scheme for heterogeneous parties to optimize their respective objectives such as higher model accuracy, communication efficiency, and computational efficiency. To reward fairly to deserving parties while offering flexibility, we propose a novel multi-agent reinforcement learning (MARL) incentive mechanism, which enables heterogeneous parties to learn their own optimal collaboration policy. We then design an efficient decentralized data collaboration algorithm that supports the customizable reward scheme based on individual objective-specific collaboration policy. We theoretically prove that the algorithm achieves a Nash equilibrium, which ensures the fairness of the corresponding rewards for parties. We conduct extensive experiments to evaluate the performance of our proposed framework against four baselines on five real-world datasets. The results show that IDEA outperforms state-of-the-art methods in terms of effectiveness, efficiency, and accumulated reward.

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.

Various middleboxes are ubiquitously deployed in networks to perform packet processing functions, such as firewalling, proxy, scheduling, etc., for the flows passing through them. With the explosion of network traffic and the demand for multiple types of network resources, it has never been more challenging on a middlebox to provide Quality-of-Service (QoS) guarantees to grouped flows. Unfortunately, all currently existing fair queueing algorithms fail in supporting hierarchical scheduling, which is necessary to provide QoS guarantee to the grouped flows of multiple service classes. In this paper, we present two new multi-resource fair queueing algorithms to support hierarchical scheduling, collapsed Hierarchical Dominant Resource Fair Queueing (collapsed H-DRFQ) and dove-tailing H-DRFQ. Particularly, collapsed H-DRFQ transforms the hierarchy of grouped flows into a flat structure for flat scheduling while dove-tailing H-DRFQ iteratively performs flat scheduling to sibling nodes on the original hierarchy. Through rigorous theoretical analysis, we find that both algorithms can provide hierarchical share guarantees to individual flows, while the upper bound of packet delay in dove-tailing H-DRFQ is smaller than that of collapsed H-DRFQ. We implement the proposed algorithms on Click modular router and the experimental results verify our analytical results.

Computation offloading via device-to-device communications can improve the performance of mobile edge computing by exploiting the computing resources of user devices. However, most proposed optimization-based computation offloading schemes lack self-adaptive abilities in dynamic environments due to time-varying wireless environment, continuous-discrete mixed actions, and coordination among devices. The conventional reinforcement learning based approaches are not effective for solving an optimal sequential decision problem with continuous-discrete mixed actions. In this paper, we propose a hierarchical deep reinforcement learning (HDRL) framework to solve the joint computation offloading and resource allocation problem. The proposed HDRL framework has a hierarchical actor-critic architecture with a meta critic, multiple basic critics and actors. Specifically, a combination of deep Q-network (DQN) and deep deterministic policy gradient (DDPG) is exploited to cope with the continuous-discrete mixed action spaces. Furthermore, to handle the coordination among devices, the meta critic acts as a DQN to output the joint discrete action of all devices and each basic critic acts as the critic part of DDPG to evaluate the output of the corresponding actor. Simulation results show that the proposed HDRL algorithm can significantly reduce the task computation latency compared with baseline offloading schemes.

Mobile edge computing (MEC) enables users to offload computing tasks to edge servers for provisioning low-latency and computation-intensive services. To manage heterogeneous resources and improve service flexibility, MEC is entailed by new technologies, \textit{i.e.}, software defined networking (SDN) and network function virtualization (NFV), which allow services running on common commodity hardware instead of proprietary hardware. However, data processing via software on commodity servers may induce high latency due to limited processing capacity, which impedes the quality of service. Meanwhile, MEC is a resource-sharing system and thus fairness should be considered. In this paper, we propose a network function parallelism (NFP)-enabled MEC (NFPMec) framework for supporting low-latency services. To reap the potential benefits of the NFPMec, we formulate the fairness-aware throughput maximization problem (FTMP) with aim of maximizing the fairness-aware system throughput while satisfying the QoS requirements. We propose a relaxation-based generalized benders algorithm (RGBA) to decouple the FTMP into two sub-problems based on the non-linear convex duality theory. After relaxation, the sub-problems are solved by the Karush-Kuhn-Tucker (KKT) approach. The convergence of the RGBA is theoretically proved. The simulation results demonstrate that the proposed NFPMec outperforms SDN-enabled MEC networks in terms of resource utilization, service latency and system throughput.

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.

The recently emerging blockchain technology provides a promising tool to enable endogenous security in Internet-of-Things (IoT) systems. However, when applying the legacy blockchain technology to the existing IoT systems, some technical bottlenecks due to resource constraints, such as storage resource, should be carefully addressed. In this article, we propose an optimal blockchain deployment mechanism for wireless IoT systems, where IoT devices have limited resources and the wireless links connection IoT devices are vulnerable, to improve the storage efficiency of massive blockchain data and realize the organic integration of blockchain technology and the communication process. We propose to maintain a complete blockchain by a set of proximity IoT nodes in a collaborative way on the premise of ensuring that each node can check every transaction. Through dynamically adjusting optimal block assignment, the tradeoff between the length of the blockchain to be stored and the security level provided can be well made. Moreover, a chaotic-based genetic algorithm is developed to obtain the near-optimal block assignment solution efficiently. Simulation results show that our proposed blockchain-based mechanism can effectively address the security issue in wireless IoT systems.

Dense deployment of small cells operating on different frequency bands based on multiple technologies provides a fundamental way to face the imminent thousand-fold traffic augmentation. This heterogeneous network (HetNet) architecture enables efficient traffic offloading among different tiers and technologies. However, research on multi-tier HetNets where various tiers share the same microwave spectrum has been well-addressed over the past years. Therefore, our work is targeted towards novel multi-tier HetNets with disparate spectrum (microwave and millimeter wave). In fact, despite the huge capacity brought by millimeter-wave technology, the latter will fail to provide universal coverage, especially indoor, and so mmWave will inevitably co-exist with a traditional sub-6GHz cellular network. In this work, we propose a coordinated user association and spectrum allocation by resorting to non-cooperative game theory. In fact, in such an arduous context, efficient distributed solutions are imperative. Extensive simulation results show the precedence of our coordinated approach in comparison with state-of-the-art heuristics. Moreover, we evaluate the impact of various network parameters, such as mmWave density, cell load, and user distribution and density, offering valuable guidelines into practical 5G HetNet design. Finally, we assess the benefit brought by massive MIMO for mmWave in such a highly heterogeneous setting.

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.

Service migration, determining when, where and how to migrate the ongoing service, is of paramount importance in mobile edge computing (MEC) for provisioning high quality of service to mobile users. With respect to high network dynamics and stringent delay requirements, service migration is a rather challenging issue in MEC. In this paper, we formulate service migration as a partially observable Markov decision process (POMDP) based on the fact that an edge server can only obtain partial users' information, or the information of its own serving users. A learning-based intelligent service migration algorithm, named iSMA, is proposed to minimize the long-term service delay of all users. iSMA consists of two function modules, a latent space model and a cross-entropy planning algorithm, where the latent space model is used to infer the full state of the environment based on the partial information observed, and the cross-entropy planning algorithm is used to search the best service migration strategy. Numerical results show that our proposed iSMA reduces the service delay by about 58% when compared with a well-known deep learning-based solution.

Millimeter wave (mmWave) communication is one of the key technologies in 5G and beyond systems to address the tremendous growth in mobile data traffic owing to the abundant spectrum resources. Ultra-dense network deployment is a promising solution to combat the limited coverage, high propagation loss and attenuation of mmWave signals. This study investigates the beam management, with focus on beam configuration of mmWave base stations, in the ultra-dense mmWave network. To fulfill adaptive and intelligent beam management while protecting user privacy, we employ a double deep Q-network under a federated learning to tackle the beam management problem which is formulated to maximize the long-term system throughput. Simulation results demonstrate the performance gain of our proposed scheme.

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.

To meet low latency and real-time monitoring demands of IoT-eHealth, fog computing is envisioned as a key technology to offer elastic computing resource at the edge of networks. In this context, eHealth devices can offload collected healthcare data or computational expensive tasks to a nearby fog server. However, the mobility of the eHealth devices may make the connection between them to fog servers uncertain, resulting in possible migration between fog servers. In order to evaluate the impact of this uncertainty on decision-making for offloading and resource allocation, we formulate the task offloading problem as a Multi-Stage Stochastic Programming (MSSP), with aim of minimizing the total latency of offloading to determine whether to offload or not, how much workload to offload, how much computing resource to allocate, as well as whether to migrate or not. Different from the previous MSSP based work focusing on the workload assignment only, the proposed MSSP examines joint decisions of offloading, resource allocation, and migration, advancing the understanding of the interactions among these decisions. Furthermore, to reduce the computational complexity of MSSP, we design an efficient sub-optimal offloading policy based on Sample Average Approximation, called SAA-MSSP. We conduct extensive simulation experiments to validate the effectiveness of SAA-MSSP. The results show that SAA-MSSP can converge to a near-optimal solution quickly.

Cognitive radio (CR) is an effective solution to improve the spectral efficiency (SE) of wireless communications by allowing the secondary users (SUs) to share spectrum with primary users (PUs). Meanwhile, intelligent reflecting surface (IRS), also known as reconfigurable intelligent surface (RIS), has been recently proposed as a promising approach to enhance energy efficiency (EE) of wireless communication systems through intelligently reconfiguring the channel environment. To improve both SE and EE, in this paper, we introduce multiple IRSs to a downlink multiple-input single-output (MISO) CR system, in which a single SU coexists with a primary network with multiple PU receivers (PU-RXs). Our design objective is to maximize the achievable rate of SU subject to a total transmit power constraint on the SU transmitter (SU-TX) and interference temperature constraints on the PU-RXs, by jointly optimizing the beamforming at SU-TX and the reflecting coefficients at each IRS. Both perfect and imperfect channel state information (CSI) cases are considered in the optimization. Numerical results demonstrate that IRS can significantly improve the achievable rate of SU under both perfect and imperfect CSI cases.

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.

Recently, mobile operators have been shifting to an intelligent autonomous network paradigm, where the mobile networks are automated in a plug-and-play manner to reduce the manual intervention. Under this circumstance, serious inter-cell interference becomes inevitable which may severely deteriorate system throughput performance and users’ quality of service (QoS), especially for dense residential small base station (SBS) deployment. This paper proposes an intelligent inter-cell interference coordination (ICIC) scheme for autonomous heterogeneous networks (HetNets), where the SBSs agilely schedule sub-channels to individual users at each Transmit Time Interval (TTI) with aim of mitigating interferences and maximizing long-term throughput by sensing the environment. Since the reward function is inexplicit and only few samples can be used for prior-training, we formulate the ICIC problem as a distributed inverse reinforcement learning (IRL) problem following the POMDP games. We propose a non-prior knowledge based self-imitating learning (SIL) algorithm which incorporates Wasserstein Generative Adversarial Networks (WGANs) and Double Deep Q Network (Double DQN) algorithms for performing behavior imitation and few-shot learning in solving the IRL problem from both thepolicyandvalue. Numerical results reveal that SIL is able to implement TTI level’s decision-making to solve the ICIC problem, and the overall network throughput of SIL can be improved by up to 19.8% when compared with other known benchmark algorithms.

Device-to-device (D2D) technology, which allows direct communications between proximal devices, is widely acknowledged as a promising candidate to alleviate the mobile traffic explosion problem. In this paper, we consider an overlay D2D network, in which multiple D2D pairs coexist on several orthogonal spectrum bands, i.e., channels. Due to spectrum scarcity, the number of D2D pairs is typically more than that of available channels, and thus multiple D2D pairs may use a single channel simultaneously. This may lead to severe co-channel interference and degrade network performance. To deal with this issue, we formulate a joint channel selection and power control optimization problem, with the aim to maximize the weighted-sum-rate (WSR) of the D2D network. Unfortunately, this problem is non-convex and NP-hard. To solve this problem, we first adopt the state-of-art fractional programming (FP) technique and develop an FP-based algorithm to obtain a near-optimal solution. However, the FP-based algorithm requires instantaneous global channel state information (CSI) for centralized processing, resulting in poor scalability and prohibitively high signalling overheads. Therefore, we further propose a distributed deep reinforcement learning (DRL)-based scheme, with which D2D pairs can autonomously optimize channel selection and transmit power by only exploiting local information and outdated nonlocal information. Compared with the FP-based algorithm, the DRL-based scheme can achieve better scalability and reduce signalling overheads significantly. Simulation results demonstrate that even without instantaneous global CSI, the performance of the DRL-based scheme can approach closely to that of the FP-based algorithm.

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.

It is widely acknowledged that network slicing can tackle the diverse usage scenarios and connectivity services that the 5G-and-beyond systems need to support. To guarantee performance isolation while maximizing network resource utilization under traffic uncertainty, 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 the numerous variables. In this paper, we investigate network slice reconfiguration with aim of minimizing long-term resource consumption by exploiting Deep Reinforcement Learning (DRL). To address the curse of dimensionality of the problem, we propose to incorporate the Branching Dueling Q-network (BDQ) into DRL, to avoid some unnecessary calculations of Q-value by separating the Q-network into a shared value branch and a number of distributed advantage branches. Furthermore, the value branch and the advantage branch of each dimension are aggregated to derive the corresponding dimension's sub-Q-value. Then the best reconfiguration action is composed of the subactions in individual dimensions which are selected by €-greedy policy. Finally, we design an intelligent online network slice reconfiguration policy based on BDQ and extensive simulation experiments are conducted to validate the effectiveness of the proposed slice reconfiguration policy.

Cognitive radio (CR) is an effective solution to increase the spectral efficiency (SE) of wireless communications by allowing the secondary users (SUs) to share the spectrum with primary users (PUs). On the other hand, intelligent reflecting surface (IRS) is a promising approach to enhance the energy efficiency (EE) of wireless communication systems through passively reconfiguring the channel environments. In this paper, we propose an IRS enhanced downlink multiple-input single-output (MISO) CR systems to improve both SE and EE, where a single SU coexists with a primary network with multiple primary user receivers (PU-RXs). Specifically, for the MISO-CR system, we maximize the achievable rate of SU subject to a total power constraint on an SU transmitter (SU-TX) and an interference temperature (IT) constraint on PU-RXs, by jointly optimizing the beamforming vector at SU-TX and the phase shifts at the IRS. Furthermore, both perfect channel state information (CSI) and imperfect CSI are considered in the optimization. Numerical results demonstrate that the IRS can significantly improve the achievable rate of SU-RX under both the perfect and imperfect CSI conditions.

In legacy blockchain based systems, each involved node has to store a complete blockchain to ensure the system security without any central authoritative controller. However, it is usually impossible for a wireless IoT node to store a complete blockchain, especially for those simple sensor nodes without sufficient storage and computing resources. In this paper, we propose a block assignment scheme for blockchain based wireless IoT systems with aim to tackle the blockchain storage problem. Specifically, we propose to maintain a complete blockchain by a set of IoT nodes in a collaborative way on the premise of ensuring that each node can check every transaction. On the other hand, we should save the storage space of IoT nodes to the greatest extent for saving more blocks so as to maximize the lifetime of IoT nodes. We formulate this optimal block assignment problem as a 0-1 mixed integer-programming problem. We propose to incorporate Chaotic optimized algorithm into Genetic algorithm to provide an efficient near-optimal solution. Compared with the brute-force and conventional Genetic algorithms, our proposed algorithm can achieve the minimum storage occupancy to store blocks. Meanwhile, the proposed algorithm has the lowest computational complexity.

Blockchain-enabled wireless network has been recognized as an emerging network architecture to be widely employed into the Internet of Things (IoT) ecosystems for establishing trust and consensus mechanisms without the involvement of a third party. However, the uncertainty and vulnerability of wireless channels among the IoT nodes may pose a serious challenge to facilitate the deployment of blockchain in wireless networks. In this paper, we first present a generic system model for blockchain enabled wireless networks with multiple communication connections, where the number of communication connections between a client IoT node and the blockchain full nodes can be any arbitrary positive integer to satisfy different security requirements. Based on the proposed spatial-temporal network model, we theoretically calculate the transmission successful probability and the required communication throughput to support a wireless blockchain network. Finally, simulation results validate the accuracy of our theoretical analysis.

This paper considers a problem of estimation of the Fisher information for location from a random sample of size n. First, an estimator proposed by Bhattacharya is revisited and improved convergence rates are derived. Second, a new estimator, termed clipped estimator, is proposed. The new estimator is shown to have superior rates of convergence as compared to the Bhattacharya estimator, albeit with different regularity conditions. Third, both of the estimators are evaluated for the practically relevant case of a random variable contaminated by Gaussian noise. Moreover, using Brown's identity, which relates the Fisher information to the minimum mean squared error (MMSE) in Gaussian noise, a consistent estimator for the MMSE is proposed.

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.

Network slicing is identified as a fundamental architectural technology for future mobile networks since it can logically separate networks into multiple slices and provide tailored quality of service (QoS). However, the introduction of network slicing into radio access networks (RAN) can greatly increase user handover complexity in cellular networks. Specifically, both physical resource constraints on base stations (BSs) and logical connection constraints on network slices (NSs) should be considered when making a handover decision. Moreover, various service types call for an intelligent handover scheme to guarantee the diversified QoS requirements. As such, in this article, a multiagent reinforcement LEarning based Smart handover Scheme, named LESS, is proposed, with the purpose of minimizing handover cost while maintaining user QoS. Due to the large action space introduced by multiple users and the data sparsity caused by user mobility, conventional reinforcement learning algorithms cannot be applied directly. To solve these difficulties, LESS exploits the unique characteristics of slicing in designing two algorithms: 1) LESS-DL, a distributed Q-learning algorithm to make handover decisions with reduced action space but without compromising handover performance; 2) LESS-QVU, a modified Q-value update algorithm which exploits slice traffic similarity to improve the accuracy of Q-value evaluation with limited data. Thus, LESS uses LESS-DL to choose the target BS and NS when a handover occurs, while Q-values are updated by using LESS-QVU. The convergence of LESS is theoretically proved in this article. Simulation results show that LESS can significantly improve network performance. In more detail, the number of handovers, handover cost and outage probability are reduced by around 50%, 65%, and 45%, respectively, when compared with traditional methods.

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.

In both wired and wireless communication networks, power allocation is an important technique to improve system performance. This paper investigates the power allocation problem for parallel Gaussian channels from an information-theoretic perspective with the aim of maximizing the sum of mutual informations (i.e., an achievable data rate). If all the inputs are Gaussian, it is well-known that the waterfilling policy provides an optimal solution. For arbitrary input distributions, a generalization of waterfilling, so-called mercury/waterfilling, provides an optimal solution in terms of the minimum mean square errors (MMSEs). However, the difficulty of obtaining closed-form analytical expressions of the MMSE often makes computing the mercury/waterfilling solution challenging. This paper proposes a robust waterfilling power allocation (RPA) policy for parallel Gaussian channels when the input distributions are close to Gaussian distributions in the Kullback-Leibler (KL) divergence (relative entropy). First, it is shown that the proposed policy results in water-levels that are close to the optimal ones in a well-defined sense. Second, tight bounds for the loss in mutual information (data rate) are given. This bounded loss property makes the proposed power allocation policy robust and approximately optimal, which is illustrated by means of various simulation setups. Moreover, the RPA policy provides a general framework for solving the power allocation problem for parallel channels, with the classical waterfilling being included as a special case. Finally, the RPA policy is argued to be scalable with the number of users since it inherently uses the classical low complexity waterfilling.

This paper investigates the power allocation problem for parallel Gaussian channels from an information-theoretic perspective with the aim of maximizing the sum of mutual informations (i.e., an achievable data rate). If all the inputs are Gaussian, it is well-known that the waterfilling policy provides an optimal solution. For arbitrary input distributions, a generalization of waterfilling, so-called mercury/waterfilling, provides an optimal power allocation in terms of the minimum mean square errors (MMSEs). However, the difficulty of obtaining closed-form analytical expression of the MMSE often makes the computation of mercury/waterfilling solution challenging. This paper proposes a robust waterfilling power allocation (RPA) policy for parallel Gaussian channels when the input distributions are close to Gaussian distributions in the Kullback-Leibler divergence (relative entropy). First, it is shown that the proposed policy results in water levels that are close to the optimum in a well-defined sense. Second, tight bounds for the loss in achievable rate are given. This bounded loss property makes the proposed power allocation policy robust and approximately optimal. Both aspects are illustrated by means of different simulation setups. Finally, the RPA is argued to be scalable with the number of users on the account of the fact that it inherently uses the classical low complexity waterfilling.

Providing massive connectivity is one of the key challenges for the next generation of wireless communication networks, and hence the capacity limits of massive connectivity need to be thoroughly studied. The uplink in the regime of massive connectivity is captured by the many-access channel (MnAC) model, assuming the number of users to be extremely large and comparable to the blocklength. This work investigates a generalized MnAC, in which the transmitters and/or the receiver can be equipped with multiple antennas, and the channel gain of each user is allowed to be different. This work characterizes the sum-message-length capacity of the multiple-input and multiple-output Gaussian MnAC in the regime where the number of users increases sub-linearly in the blocklength (i.e., Kn= o(n)).

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.

Network slicing (NS) has been identified as a fundamental technology for future mobile networks to meet extremely diverse communication requirements by providing tailored quality of service (QoS). However, due to the introduction of NS into radio access networks (RAN) forming a UE-BS-NS three-layer association, handoff becomes very complicated and cannot be resolved by conventional policies. In this paper, we propose a multi-agent reinforcement LEarning based Smart handoff policy with data Sharing, named LESS, to reduce handoff cost while maintaining user QoS requirements in RAN slicing. Considering the large action space introduced by multiple users and the data sparsity problem due to user mobility, LESS is designed to have two components: 1) LESS-DL, a modified distributed Q-learning algorithm with small action space to make handoff decisions; 2) LESS-DS, a data sharing mechanism using limited data to improve the accuracy of handoff decisions made by LESS-DL. The proposed LESS mechanism uses LESS-DL to choose both the target base station and NS when a handoff occurs, and then updates the Q-values of each user according to LESS-DS. Numerical results show that in typical scenarios, LESS can significantly reduce the handoff cost when compared with traditional handoff policies without learning.

We study a cognitive heterogeneous network (HetNet), in which multiple pairs of secondary users coexist with a pair of primary users on a certain spectrum band. To protect primary transmissions, secondary transmitters (STs) adopt a sensing-based approach to access the spectrum band. Nevertheless, STs may cause uncertain interference to the primary receiver (PR) due to imperfect spectrum sensing, which is particularly significant when the wireless links between the primary transmitter (PT) and STs are extremely weak and the wireless links between STs and the PR are non-ignorable. This makes it difficult for the PR to select a proper modulation and/or coding scheme (MCS). To deal with the issue, we propose an intelligent deep reinforcement learning (DRL) based MCS selection algorithm for the primary transmission. With the proposed algorithm, the DRL agent at the PR is able to learn the pattern of the interference from the STs and predict the interference in the future. Simulation results show that the transmission rate of the proposed algorithm can converge to 90% ^ 100% transmission rate of the optimal MCS selection algorithm, which assumes that the interference from the STs is perfectly known at the PR as prior information. Meanwhile, the transmission rate of the proposed algorithm is around 100% higher than the transmission rate of the benchmark algorithm, which selects the MCS without the information about interference.

Recently, as the development of artificial intelligence (AI), data-driven AI methods have shown amazing performance in solving complex problems to support the Internet of Things (IoT) world with massive resource-consuming and delay-sensitive services. In this paper, we propose an intelligent resource allocation framework (iRAF) to solve the complex resource allocation problem for the collaborative mobile edge computing (CoMEC) network. The core of iRAF is a multitask deep reinforcement learning algorithm for making resource allocation decisions based on network states and task characteristics, such as the computing capability of edge servers and devices, communication channel quality, resource utilization, and latency requirement of the services, etc. The proposed iRAF can automatically learn the network environment and generate resource allocation decision to maximize the performance over latency and power consumption with self-play training. iRAF becomes its own teacher: a deep neural network (DNN) is trained to predict iRAF's resource allocation action in a self-supervised learning manner, where the training data is generated from the searching process of Monte Carlo tree search (MCTS) algorithm. A major advantage of MCTS is that it will simulate trajectories into the future, starting from a root state, to obtain a best action by evaluating the reward value. Numerical results show that our proposed iRAF achieves 59.27% and 51.71% improvement on service latency performance compared with the greedy-search and the deep Q-learning-based methods, respectively.

Blockchain has shown a great potential in Internet of Things (IoT) ecosystems for establishing trust and consensus mechanisms without involvement of any third party. Understanding the relationship between communication and blockchain as well as the performance constraints posing on the counterparts can facilitate designing a dedicated blockchain-enabled IoT systems. In this paper, we establish an analytical model for the blockchain-enabled wireless IoT system. By considering spatio-temporal domain Poisson distribution, i.e., node geographical distribution in spatial domain and transaction arrival rate in time domain are both modeled as Poisson point process (PPP), we first derive the distribution of signal-to-interference-plus-noise ratio (SINR), blockchain transaction successful rate as well as overall throughput. Based on the system model and performance analysis, we design an algorithm to determine the optimal full function node deployment for blockchain system under the criterion of maximizing transaction throughput. Finally, the security performance is analyzed in the proposed networks with three typical attacks. Solutions such as physical layer security are presented and discussed to keep the system secure under these attacks. Numerical results validate the accuracy of our theoretical analysis and optimal node deployment algorithm.

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.

Providing massive connectivity is one of the key challenges for the next generation of wireless communication networks, and hence the capacity limits of massive connectivity need to be thoroughly studied. The uplink in the regime of massive connectivity is captured by the many-access channel (MnAC) model, assuming the number of users to be extremely large and comparable to the blocklength. This work investigates a generalized MnAC, in which the transmitters and/or the receiver can be equipped with multiple antennas, and the channel gain of each user is allowed to be different. This model is referred to as the multiple-input and multiple-output (MIMO) MnAC model. In the MnAC paradigm, the message length (i.e., the number of bits communicated) is not necessarily linear in the blocklength. Therefore, instead of the conventional code rate, the message length is studied and defined as a function of the blocklength. This work characterizes the sum-message-length capacity (SMC) of the MIMO Gaussian MnAC in the regime where the number of users increases sub-linearly in the blocklength (i.e., Kn= o(n)). The SMC is numerically compared to lower bounds on achievable rate at finite blocklengths and is shown to be a good approximation for system performance. The impact of the number of antennas per user on SMC is also investigated. While in the single antenna MnAC model the conventional code rate is always zero, it is shown that in the MIMO MnAC it is possible to achieve positive rate by increasing the number of antennas per user. Furthermore, the antenna-user index is defined and the SMC is characterized for different antenna-user joint regimes. This provides useful insights for future MIMO MnAC system design.

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.

We consider a cognitive heterogeneous network (HetNet), in which multiple pairs of secondary users adopt sensing-based approaches to coexist with a pair of primary users on a certain spectrum band. Due to imperfect spectrum sensing, secondary transmitters (STs) may cause interference to the primary receiver (PR) and make it difficult for the PR to select a proper modulation and/or coding scheme (MCS). To deal with this issue, we exploit deep reinforcement learning (DRL) and propose an intelligent MCS selection algorithm for the primary transmission. To reduce the system overhead caused by the MCS switchings, we further introduce a switching cost factor in the proposed algorithm. The simulation results show that the primary transmission rate of the proposed algorithm without the switching cost factor is 90% ~ 100% of the optimal MCS selection scheme, which assumes that the interference from the STs is perfectly known at the PR as prior information, is 30% higher than that of the upper confidence bandit (UCB) algorithm, and is 100% higher than that of the signal-to-noise ratio (SNR)-based algorithm. Meanwhile, the proposed algorithm with the switching cost factor can achieve a higher primary transmission rate than those of the benchmark algorithms without increasing system overheads.

Massive machine-type communication (mMTC) has been identified as one of the three generic 5G services, with the aim of providing connectivity to a large number of devices. The concurrent massive access may lead to congestions due to limited access resources. Group paging (GP) has emerged as one of the promising solutions to alleviate network congestion by controlling access load. However, the performance of GP deteriorates drastically with the number of devices per paging group. This paper explores GP with pre-backoff strategy for a general mMTC scenario in which devices are allowed to have diverse access success probability (ASP) requirements, and proposes an ASP requirement guaranteed GP scheme with specific pre-backoff times (GPSP), with the aim of maximizing the total access rate. To fully adapt to mMTC applications, an efficient heuristic algorithm is designed. Numerical results demonstrate that the proposed GPSP scheme can effectively improve system performance in terms of average ASP, average access delay, and the average number of preamble transmissions.

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.

Massive machine-type communication (mMTC) has been identified as one of the three generic 5G services, with the aim of providing connectivity to a large number of devices. The concurrent massive access in mMTC may lead to congestion due to limited access resources. Group paging (GP) is emerging as one of the promising solutions to alleviate network congestion by controlling access load. However, the performance of GP deteriorates drastically with the number of devices per paging group. This paper explores GP with a pre-backoff strategy for a general mMTC scenario in which devices are allowed to have diverse access success probability (ASP) requirements, and proposes a differentiated service-aware GP scheme with specific pre-backoff times (GPSP), with the aim of maximizing the total access rate while guaranteeing the ASP requirements for individual devices. An optimal solution to the GPSP problem is derived to provide a performance upper bound. As low-complexity algorithms are of key importance for mMTC applications, an efficient heuristic algorithm is further designed. Numerical results demonstrate that the proposed GPSP scheme can effectively improve the system performance in terms of average ASP, average access delay, and the average number of preamble transmissions.

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.

Network slicing is an emerging terminology that enables operators to partition a shared substrate network into multiple logically isolated and on- demand virtual networks to support diverse communication cases. However, the performance of network slices can be heavily deteriorated due to unexpected software or hardware malfunctions in the substrate network. Furthermore, the traffic demand is usually considered as a deterministic parameter during the network slice deployment, while it could be stochastically varied in reality, and such stochasticality may invalidate some network slices. Therefore, it is imperative to develop a robust network slicing algorithm. In this paper, we first formulate the failure recovery problem of network slicing as a mixed integer programming (MIP) and then model the robust MIP (RMIP) to capture the stochastic traffic demand. We solve the RMIP by using the robust optimization approach. Numerical results reveal that the proposed the robust network slicing algorithm can provide adjustable tolerance of traffic uncertainty in comparison with the nonrobust algorithm. In the meanwhile, the trade-off between robustness of requests and the load of substrate links can be hence efficiently managed and controlled.

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.

Traditional design of wireless networks mainly focuses on system capacity and spectral efficiency. As green networking is an inevitable trend, energy-efficient design for future wireless networks becomes paramount. In this paper, we address energy-efficient resource management in downlink orthogonal frequency division multiple access networks. The focus is targeted toward multi-cell networks, which are composed of multiple base stations (BSs) sharing the available radio resources. Consequently, greater emphasis is given to techniques that take inter-cell interference into account. Resource management in our context refers to the task of allocating the radio resources in order to maximize energy efficiency. We devise resource management techniques that jointly tackle the problems of scheduling and power control. Accordingly, we adopt two different approaches: a centralized approach, where BSs coordinate in order to reach a globally optimal energy-efficient solution, and a distributed approach, where BSs selfishly strive to maximize their own energy efficiency. We portray the centralized approach as a convex optimization problem, whereas we have recourse to non-cooperative game theory to model the distributed approach. In particular, we show that the non-cooperative game converges to a unique Nash equilibrium in low- and high-interference scenarios. We perform thorough numerical simulations to quantify the discrepancy between the centralized and distributed approaches, and identify the conditions where they have precedence over the state of the art. Moreover, the simulation results highlight the fast convergence of our algorithms, which is a precious asset for realistic deployments.

Peer-to-peer (P2P) systems and online social network (OSN) both have achieved tremendous success. Recent studies suggest that the cooperation of P2P and OSN can achieve better efficiency and security. Unfortunately, novel security problems are emerging as the mutual cooperation and dependence contributes to forming the interdependent networks which are more vulnerable for malicious attack as well as rumor propagation. In this paper, we examined the security environment for P2P and OSN, respectively, and analyzed the security problem derived from the cooperation and interdependence of two networks. The spreader-ignorant-recaller-stifler (SICR) is leveraged to model the rumor spreading in the interdependent networks. In order to enhance the security, we proposed two security schemes named authentication intervening and splitting target and their performance summaries indicate to be effective, simple, and potentially transformative way to guarantee the security for interdependent networks of P2P and OSN.

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.

Space shift keying (SSK) modulation is an emerging transmission technique for multiple-input multiple-output (MIMO) wireless channels that exploits spatial domain to convey information. In this paper, we present a layered space shift keying (LSSK) modulation scheme to fully exploit spatial domain to transmit information bits, where a layered architecture is developed to achieve spatial multiplexing transmission in SSK system. With the layered structure, LSSK can achieve much higher spectrum efficiency than the conventional SSK modulation system. The proposed LSSK scheme introduces layer mapping and bit-mapping operations at the transmitter to achieve layered SSK modulation directly with low computation overhead. More precisely, leveraging the phase shift keying (PSK) modulation symbols previously known at the transceiver to identify different layers, multiple antennas are activated simultaneously to emit layered signals. The theoretical bit error probability of LSSK with optimal maximum likelihood (ML) detection is also derived in this paper. Results demonstrate that the proposed LSSK scheme substantially improves the spectrum efficiency of SSK system and outperforms other existing MIMO schemes.

This paper investigates energy-efficient device-to-device (D2D) communications in cellular networks. We aim to maximize the overall energy-efficiency (EE) of D2D users and regular cellular users (RCUs) while considering the circuit power consumption and the quality-of-service (QoS) requirements for both types of users as well as power constraints. Three transmission modes, namely, dedicated mode, reusing mode, and cellular mode, are considered for D2D users to share spectrum with RCUs. Parametric Dinkelbach method and concave-convex procedure (CCCP) are adopted to transform the original optimization problems into more tractable forms through sequential convex approximations. Then, interior point method is exploited to obtain the optimal solution. Simulation results show that system EE can be improved significantly with the proposed mode switching algorithm compared with the single mode transmission. Besides, it is also shown that the reusing mode is more preferred in the EE based mode switching while it is the dedicated mode in the spectrum-efficiency (SE) based mode switching in most situations.

Abstract Cooperative communications can obtain spatial diversity, high channel capacity, and reliable transmission without multiple antennas, and thus, it has become a hot topic in recent years. Different from existing research, this paper pays attention on cooperative media access control (MAC) mechanism, which considers both physical gain and MAC overhead caused by cooperation. To this end, a dynamic cooperative MAC mechanism for wireless networks, called DCMAC, is proposed. DCMAC can obtain the useful channel state information through broadcasting characteristic of wireless channel, choose the suitable helpers to relay data with our proposed helpers selection algorithm, and reserve wireless channel efficiently and dynamically. Numerical results show the effectiveness of DCMAC to improve the system performance.

The performance gain of cooperative communications depends heavily on the selection of relay. Most of existing relay selection methods aim at maximizing cooperative gain by selecting appropriate relay, without taking into account the adverse effect brought by cooperative communications: extra interferences introduced by relay transmission (called cooperation interference). Thus the derived performance gain could be inaccurate and/or the selected relay may be not optimal. In this paper, we address the assignment of relays for multiple communication sessions using cooperative communications in a wireless network. We first thoroughly investigate the adverse effect brought by using relays, and derive the cooperation gain with consideration of cooperation interference. Based on the insights of our investigation, we propose a method of assigning relays to individual transmission flows while taking into account cooperation interference in cooperative communications. In order to tradeoff the advantage and adverse effect caused by relay transmissions, we use an auction approach to address relay assignment of cooperative communications. Specifically, we propose a Single round double Auction Scheme (SAS) for centralized wireless network and a Multiple rounds sequential Auction Scheme (MAS) for decentralized wireless network for relay assignment. We conduct extensive simulation experiments to validate the effectiveness of SAS and MAS. The significance of the impact of cooperation interference, improvement of system throughput and energy efficiency are demonstrated by numerical results.

In 3GPP LTE-A, Coordinated Multi-Point (CoMP) is adopted to enhance the transmission rates of edge users. To maximize the total downlink throughput of all edge users, it is crucial to properly determine the set of simultaneously served users in each physical resource block (PRB) and the cooperative base stations (BSs) for each scheduled user, as well as the transmit power of the BSs. Based on the reference signal receiving power (RSRP) of each edge user, we first propose two simple and integrated transmission scheduling algorithms, one distributed and the other centralized, to choose cell-edge users and cooperative BSs in each PRB. With the scheduling results, the classic Water-Filling (WF) algorithm is carried out over all PRBs at each BS to get an initial single cell power allocation. To take the interference among different cooperative BS sets into account, we further formulate a non-cooperative power allocation game to adjust the initial power allocation for interference coordination, where the initial power allocation provides the strategy space of the game for each BS. This increases the total downlink throughput of edge users over all BSs. We prove that the game has a unique Nash Equilibrium (NE), and design an algorithm to find the NE. Performance gain is then demonstrated through extensive simulation studies.

In this paper, we investigate optimal resource allocation for device-to-device (D2D) communication underlaying cellular network in fading channels. We consider a scenario that the instantaneous channel power gain of interference links from regular cellular users (CUs) to D2D users are unknown at base station (BS) since obtaining the channel-state-information (CSI) in this case is difficult and requires high overhead. We assume that BS provides guaranteed quality-of-service (QoS) in terms of signal-to-interference-plus-noise-ratio (SINR) for CUs and outage probability for D2D pairs, respectively. Based on the assumptions, we first propose a probabilistic access control for D2D pairs to satisfy all the QoS requirements and power constraints. We then derive joint power and channel allocation to maximize the overall throughput of the CUs and admissible D2D pairs. Through simulation, we show the effectiveness of the proposed probabilistic strategy and there exists an optimal threshold of the targeted outage probability with respect to D2D access rate and overall network throughput.

Due to the merits of lower bandwidth consumption at streaming server and higher scalability, P2P streaming systems have been widely developed and deployed. However, the heterogeneity of bandwidth resource and playback position at peers may easily lead to load unbalancing problem, especially in the era of emerging booming if mobile Internet applications. This may severely deteriorate video playback quality at peers. In this paper we study bandwidth request allocation strategy, aiming at balancing the traffic load at peers and thus improving peers' playback quality in P2P streaming networks. We formulate a non-cooperative game model to analysis the bandwidth resource competition between multiple requesting peers and service peers, through searching the Nash Equilibrium of this game, the optimal bandwidth requesting strategy can be obtained. Then an distributed algorithm is proposed, called Game based Bandwidth Request Allocation strategy (GBRA). We conduct simulation experiments to validate the effectiveness of GBRA, and numerical results show that the proposed strategy can significantly improve the load unbalancing problem in P2P streaming system and decrease the latency of streaming data retrieval at peers in P2P streaming networks, compared with the classical bandwidth request allocation strategies: proportional strategy and greedy strategy.

Inter-user interference degrades the reliability of data delivery in Wireless Body Sensor Networks (WBSNs) in dense deployments when multiple users wearing WBSNs are in close proximity to one another. The impact of such interference in realistic WBSN systems is significant but has not been well explored. To this end, we investigate and analyze the impact of inter-user interference in practical WBSN systems based on TelosB platform. We capture packet delivery ratio (PDR) and throughput considering unslotted carrier sense multiple access with collision avoidance (unslotted CSMA/CA) and slotted CSMA/CA modes in IEEE 802.15.4 MAC. Our experimental results show that the unslotted CSMA/CA is only effective in light inter-user interference scenarios. Comparably, the slotted CSMA/CA can provide dramatic performance improvement (2.7 times higher in PDR and 1.7 times higher in throughput on average), when severe inter-user interference occurs in WBSN deployment.

In device-to-device (D2D) communications underlaying uplink (UP) cellular networks, the channel state information (CSI) of interference links between regular cellular users (CUs) and D2D receivers is necessary to provide guaranteed quality-of-service (QoS) to D2D users. However, getting the CSI is very difficult and requires high overhead. In this paper, we propose a selected-K maximum distance ratio (MDR) feedback scheme (KMDR) to reduce feedback overhead, in which each D2D receivers only needs to feedback CSI of K CUs with the largest MDR metric. Simulation results show that up to 80% feedback can be reduced at D2D receivers by KMDR while still providing a near optimal performance. We also study the effect of side information at the D2D receivers. It is shown that it is possible to further reduce the feedback information when full side information is known at the D2D receivers.

In Peer-to-Peer (P2P) streaming systems, media data may be lost since peers could join and leave the overlay network randomly, deteriorating the video playback quality and continuity. In this paper we develop a hybrid mesh and DHT based P2P streaming system, called HQMedia, to provide high playback quality to users by maintaining high data dissemination resilience with a low overhead. In HQMedia, peers are classified into super peers(SP) and common peers(CP) according to their online time. SPs and CPs form a mesh structure, while SPs along form a new Streaming DHT (SDHT) structure. In this hybrid architecture, we design a joint scheduling and compensation mechanism. If any frames cannot be obtained during the scheduling phase, SDHT based compensation mechanism is invoked to retrieve those missing frames near the playback point. We evaluate the performance of HQMedia by both theoretical analysis and intensive simulation experiments on large scale networks to demonstrate the effectiveness and scalability of our system. Numerical results show that HQMedia significantly outperforms existing mesh-based P2P live streaming systems by improving playback quality and continuity with only less than 1% extra maintenance overhead.

Macro-femto networks, which comprise a macrocell underlaid with multiple femtocells, have attracted much research attention due to its benefits for capacity increase and coverage extension. However, the mass deployment of femtocells with universal frequency reuse may cause severe interferences, and thus greatly deteriorate system performance. In this kind of systems, access control is an effective mechanism for interference management. In this paper, we investigate the case where the macro users may suffer severe interferences from femto base stations (FBS), and propose an access control based interference coordination scheme. By introducing auction model, FBSs decide the asking price for reserving their resources for macro users. Macro base station (MBS) bids for the access permission of macro users and selects a candidate FBS with the maximum access utility as the access point for a macro user. If an agreement for the transaction price of a macro user is reached, this user can change access point and thus the suffered interferences can be reduced. We conduct extensive simulations to validate the effectiveness of our scheme. Numerical results show that the proposed interference coordination approach operated in hybrid access mode can effectively mitigate interferences and improve system performance compared with the closed access mode.

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.

In cellular networks, proximity users may communicate directly without going through the base station, which is called Device-to-device (D2D) communications and it can improve spectral efficiency. However, D2D communications may generate interference to the existing cellular networks if not designed properly. In this paper, we study a resource allocation problem to maximize the overall network throughput while guaranteeing the quality-of-service (QoS) requirements for both D2D users and regular cellular users (CUs). A three-step scheme is proposed. It first performs admission control and then allocates powers for each admissible D2D pair and its potential CU partners. Next, a maximum weight bipartite matching based scheme is developed to select a suitable CU partner for each admissible D2D pair to maximize the overall network throughput. Numerical results show that the proposed scheme can significantly improve the performance of the hybrid system in terms of D2D access rate and the overall network throughput. The performance of D2D communications depends on D2D user locations, cell radius, the numbers of active CUs and D2D pairs, and the maximum power constraint for the D2D pairs.

Cooperative transmission (CT) is a promising technique to improve transmission rate and throughput in wireless networks, and relay node (RN) which could provide a good two-hop channel plays a key role in CT mode. As a result, most of existing work take the advantage of benefit of RN in CT mode, but do not fully recognize its potential adverse effect. In this paper, we investigate the adverse impact called flow-level cooperation interference (FCI) incurred by RN in CT mode, therefore, CT mode may not be beneficial as expected. To this end, we describe our insight and analyze the reason of FCI in wireless networks. To understand and solve FCI, we formulate this problem with a game-theoretic approach, and thus two methods which are named Nash equilibrium cooperative transmission strategy (NECTS) and Bayesian Nash equilibrium cooperative transmission strategy (BNECTS) are proposed, respectively. Our numerical results validate our analytical approach and demonstrate the effectiveness of our proposed NECTS and BNECTS.

Data transmission reliability and energy efficiency are most crucial for Wireless Body Area Network (WBAN) to perform healthcare monitoring. In this paper, we jointly consider adaptive power control and routing in multi-hop WBANs, and develop a low overhead energy-efficient routing scheme (EERS). The proposed EERS can establish an energy-efficient end-to-end path as well as adaptively choose transmission power for sensor nodes. We conduct extensive experiments on a MicaZ platform to compare the performance of the proposed EERS and the collection tree protocol (CTP) in terms of packet reception ratio (PRR), collection delay, energy consumption, and energy balancing. Experimental results show that EERS outperforms CTP in terms of reliability, delay and energy consumption. In particular, EERS reduces nearly 30% mean delay as compared to CTP, and saves 10% energy consumed by CTP at the default power (0dBm) while achieving at least 0.95 PRR.

Existing opportunistic network coding architectures relies on pseudobroadcast to deliver a coded packet to multiple receivers in a single transmission. In such situation, there is only one primary receiver who acknowledges the reception by synchronous MAC-layer acknowledgements (ACKs) and the other receivers receive it by overhearing and acknowledge the reception by asynchronous ACKs, which are usually piggybacked in outgoing data packets. This may cause a large amount of unnecessary retransmissions if asynchronous ACKs are dropped due to packet losses or they arrive late. Moreover, a large number of redundant retransmissions in IP layer easily cause congestion losses, especially under heavy traffic and thus compromise the throughput gain brought by network coding. In this paper, we propose a framework of joint optimal rate control and code selection (ORC) to mitigate the impact brought by asynchronous ACKs on opportunistic network coding in lossy wireless networks. The operation of ORC consists of two phases. In the first phase, we try to select a suitable transmission rate for the transmission of a coded packet. We formulate this rate control process as a Finite Horizon Markov Decision Process (FH-MDP). We define a metric, called coded packet transmission efficiency (CPTE), to measure the expected cumulative rewards and search the optimal rate control policy. In the second phase, based on the CPTE for a given coded packet, we propose a code selection policy to optimize the performance of opportunistic network coding. We demonstrate the effectiveness and advantages of the proposed ORC framework by computer simulations.

Relay enhanced cellular system is a promising infrastructure redesign to enhance the performance of next generation mobile networks. The use of intermediate nodes to relay information from source to destination is efficient in eliminating black spots, extending coverage region, prolonging battery lifetime of users. Recently, energy efficiency of mobile networks has drawn research attentions. Relay deployment from the perspective of energy efficiency is an interesting issue which has not been deeply addressed. In this paper, we investigate energy-efficient relay deployment by determining the optimal number and location of relays in next generation cellular networks. We establish a mathematic model for analyzing energy efficiency measured by `Joule per bit' in relay aided cellular networks, where the pathloss status related to the cell traffic busy level is considered. We conduct intensive simulation experiments based on the model with realistic broadband channel propagation conditions. Our findings suggest that introducing appropriate number of relay nodes with proper locations into the cellular system can improve system energy efficiency without compromising system throughput.

Deployment of relay nodes (RNs) in cellular orthogonal frequency division multiple access (OFDMA) systems provides an effective solution to increase high data rate coverage and improve cell throughput. However, a challenging issue is that additional interferences caused by RNs may substantially compromise the performance gain if no measure is taken. In this study, the authors address the problem of interference coordination in relay-aided cellular OFDMA systems, aiming at exploiting the benefits of RNs while minimising the negative effects of interferences introduced. The authors first analyse the possible interference scenarios in multi-cell systems. Based on the insights into their analysis, the authors propose resource allocation with interference coordination (RAIC) scheme for cellular OFDMA systems. RAIC selectively perform one of three resource allocation algorithms according to the offered traffic load in the system, to mitigate interferences and thus enhance system throughput. The authors conduct intensive simulation experiments based on the model with realistic broadband channel propagation conditions. Numerical results demonstrate that their proposed RAIC can effectively improve system throughput compared with the resource allocation schemes without appropriate interference coordination.

Relay node (RN) plays a key role in cooperative communications and RN selection may substantially affects the performance gain. In this paper we address the issue of RN selection while taking into account Medium Access Control (MAC) overhead, which is incurred by not only handshake signaling but also frame retransmissions due to transmission error. We use a theoretical model to analyze the cooperation performance gains of cooperative MAC mechanism, and are thus able to select the optimal relay node. We derive the network saturation throughput of the designed MAC with our RN selection algorithm. Numerical results validate the effectiveness of our analytical model and show that our designed MAC significantly outperforms existing cooperative MAC mechanisms which do not consider retransmission MAC overhead.

This paper addresses the problem of interference coordination in relay-aided cellular OFDMA systems, aiming at exploiting the benefits of RNs while minimizing the negative effects of interferences introduced. We first analyze the possible interference scenarios in multi-cell OFDMA systems. Based on the insights in our analysis, we propose an Integrated Interference Coordination Scheme (IICS) for cellular OFDMA systems. IICS consists of two phases, each performing a resource allocation algorithm, to mitigate interferences and thus enhance system throughput. We conduct simulation experiments based on the model with realistic broadband channel propagation conditions. Numerical results show that our proposed IICS can effectively improve system throughput compared with the resource allocation schemes without adequate interference coordination.

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.

Relay is used in LTE-Advanced cellular networks to assist eNB(evolved Node Base-station) for coverage extension and throughput enhancement. Compared to eNB, relay is advantageous on both equipment cost and site cost. How to deploy relays to maximize the performance gain with a reasonable cost subject to a number of system constraints such as interference caused and backhaul subframe allocation is an important yet challenging issue. In this paper, we provide a solution for cost-efficient deployment of relays in LTE-A cellular networks. We establish a mathematical model to analyze the tradeoff between the deployment cost and the cell performance gain, and the tradeoff between overall cell performance and satisfaction level for individual users. Our interesting findings in this paper include: (1) the best cost-efficient number of relays in a cell is limited to a reasonable range between 7 and 11 for static relay deployment; (2) when progressive deployment is considered, the optimal number of relays decreases to 4 to achieve tradeoff gain between overall cell capacity and average user satisfaction level.

Due to the mass-market of file sharing, majority of existing P2P systems are based on unstructured overlay networks, where P2P search still remains challenging issues. In this paper, we propose a small-world based semantic search architecture in P2P Networks, called CommuSearch, which has three distinguished features: 1) grouping peers into hierarchical class by exploiting heterogeneity; 2) constructing overlapped semantic communities according to small-world characteristics; and 3) parallel and hierarchical routing based on results caching. We conduct extensive simulation experiments and the numerical results show that the performance of CommuSearch substantially outperforms existing architectures in terms of average search latency, search success ratio and recall ratio, while the overhead incurred for maintaining the community is reasonably low.

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.

The integration of Wireless mesh networks (WMNs) with other networks (e.g. Internet, cellular, IEEE 802.11, sensor networks, etc.) requires an effective and robust congestion control algorithm to maintain network stability and achieve a high network resource utilization. In this paper, we address the problem of congestion control for WMNs with multi-channel MAC. We formulate the design of congestion control mechanism in such a system as a optimization problem of utilization maximization subject to time constraint. We first derive an end-to-end algorithm as the solution. Based on that, we develop a distributed adaptive algorithm with hop-by-hop congestion information feedback and prove its convergence. The numerical results based on ns-2 simulations validate the stability and demonstrate that the hop-by-hop congestion control algorithm significantly outperforms the end-to-end algorithm in terms of queue length.

In this paper we address the issue of cross-layer design in transport layer enhancement mechanisms, where the data-link and transport layer information is shared with each other, in order to provide improved system throughput of the wireless cellular network. We propose a Cross-layer Transport Layer Enhancement mechanism with name of XST (Cross-layer Snoop protocol for TCP), which is based on Snoop protocol combined with the forced duplicate acknowledgement congestion control strategy in wireless cellular networks. XST employs the cross-layer design, working at the data-link layer but using the transport layer information as operating criteria. We conduct a comparative study between the XST mechanism and Active Queue Management (AQM) mechanism in the literature, such as Random Early Detection (RED) in wireless environments with varying link characteristics. Simulation results demonstrate that the proposed XST significantly outperforms RED in wireless cellular network, especially under high-error-rate which is a major characteristic of wireless links.

On the uplink of a DS-CDMA system, successive interference cancellation (SIC) technique can be employed to reduce multiple access interference and improve system capacity. In such a system with K active users, there are K possible decoding orders of SIC and not every decoding order is feasible due to some constraints. It is highly time-consuming to examine the system feasibility directly by using the exhaustive search method (ESM) for a system with even a moderate number of users. In this paper, we propose an efficient approach for examining the feasibility of DS-CDMA systems with imperfect SIC. The proposed approach has significantly less computational complexity than that of ESM, thus benefits the quick decision of admission control and/or scheduling in DS-CDMA systems. Furthermore, under the decoding order obtained by the proposed approach, we prove that the system is able to achieve the lowest outage probability among all possible decoding orders. Simulation experiments and numerical results validate our analysis and demonstrate the effectiveness of our approach.

This paper addresses when and how to adjust bandwidth allocation on uplink and downlink in a multi-service mobile wireless network under dynamic traffic load conditions. Our design objective is to improve system bandwidth utilization while satisfying call level QoS requirements of various call classes. We first develop a new threshold-based multi-service admission control scheme (DMS-AC) as the study base for bandwidth re-allocation. When the traffic load brought by some specific classes under dynamic traffic conditions in a system exceeds the control range of DMS-AC, the QoS of some call classes may not be guaranteed. In such a situation, bandwidth re-allocation process is activated and the admission control scheme will try to meet the QoS requirements under the adjusted bandwidth allocation. We explore the relationship between admission thresholds and bandwidth allocation by identifying certain constraints for verifying the feasibility of the adjusted bandwidth allocation. We conduct extensive simulation experiments to validate the effectiveness of the proposed bandwidth re-allocation scheme. Numerical results show that when traffic pattern with certain bandwidth asymmetry between uplink and downlink changes, the system can re-allocate the bandwidth on uplink and downlink adaptively and at the same time improve the system performance significantly.

This paper addresses when and how to adjust bandwidth allocations between uplink and downlink in a multi-service wireless network with bandwidth asymmetry under dynamic traffic load conditions. A new distributed multi-service admission control policy is developed first to guarantee the call level QoS requirements. When the traffic load brought by the calls of some specific classes in a cell exceeds the control range of the admission control, bandwidth re-allocation process could be activated and the admission control policy will try to meet the QoS requirements under the adjusted bandwidth allocation. The numerical results show that the QoS requirements of different call classes can be guaranteed under the dynamic traffic conditions while the system resources are utilized efficiently by using the proposed bandwidth re-allocation strategy.

We propose a fair and simple high-performance scheduling algorithm for combined input-crosspoint-queued switches, which is called tracking fair quota allocation (TFQA). Our algorithm is based on low-cost round-Robin scheme, which prioritizes the ports lagging behind our fair quota allocation scheme. Simulation shows that our algorithm could maintain over 99% throughput and achieve relatively low mean delay under almost all typical test traffic patterns, outperforming all known algorithms with the same implementation complexity, especially under heavy load scenarios. Moreover, our algorithm could provide max-min fairness under inadmissible traffic, better than many other typical algorithms proposed before.

For the design of call admission control (CAC) policy in wireless networks, how to decrease the average system cost is a key issue. In this paper, we study the optimal admission policy for minimizing the system cost. By modeling the admission control problem into a Markov decision process (MDP) and analyzing the corresponding value function, we obtain some monotonicity properties of the optimal policy. These properties suggest that the optimal admission control policy for the bandwidth asymmetry wireless networks should have a threshold structure and the threshold specified for a class of calls may change with the system state. Due to the prohibitively high complexity for computing the thresholds in a system with large state space, we propose a heuristic CAC policy called call-rate- based dynamic threshold (CRDT) policy to approximate the theoretical optimal policy based on the insights we obtain from the modeling and the analytical study on the properties of the optimal policy. The CRDT policy is efficient and can be easily implemented. The numerical results show that the performance of average system cost of the proposed CRDT policy is close to that of the optimal policy from the MDP model and is better than that of some known existing CAC schemes, including those performing well in bandwidth asymmetry wireless networks.

In reliable multicast, data packets can be cached at some nodes such as repair servers for future possible retransmission in loss recovery schemes. How to cache packets to optimize the performance of loss recovery is an important issue in reliable multicast protocol design. In this paper, we present a general solution which addresses the main design problems of caching policies. We first formulate the caching policy design as an optimization problem by employing caching utility as a uniform measure. Based on caching utility, we propose an algorithm called Optimal Caching Time (OCT) for configuring the caching time of packets and demonstrate that it solves the optimization problem. Furthermore, we analyze the performance improvement of OCT caching policy compared to the existing caching policies such as FIFO, Probabilistic FIFO (P-FIFO), and Timer-Based Caching Policy (TBCP). We use ns-2 simulations to demonstrate the performance gains brought by OCT caching policy. The numerical results show that OCT caching policy improves the performance significantly, especially for heterogeneous groups of receivers. With the inherent generality of the proposed model and the OCT algorithm, they can be easily applied to the general cache design in reliable unicast or multicast applications, and in both wired and wireless networks.

Window-based multicast congestion control protocols such as pgmcc and AER/NCA try to emulate TCP congestion control behaviors for achieving TCP-compatibility. However, they employ NAK-based loss recovery scheme instead of the ACK-based approach, which is used in TCP. The improvement introduced by NAK-based approach on loss recovery capabilities can bring higher throughput for the multicast session under the same network conditions. In this paper, we provide a quantitative evaluation on the influences of NAK-based loss recovery mechanism on the behaviors and throughput properties of window-based multicast congestion control. First, we identify the differences on congestion control behaviors caused by the NAK-based retransmission mechanism. Based on the observations, we mathematically model the throughput of window-based multicast congestion control protocols. Accordingly, the multicast throughput can be expressed as a function of the round-trip time and loss rate experienced by the "worst" receiver. Moreover, selecting the "worst" receiver as the nominee to send congestion control feedbacks are critical to ensure fairness and congestion avoidance in single-rate multicast congestion control schemes. As the TCP throughput equations are used in existing schemes for nominee selection, the obtained multicast throughput equations can be used to enhance the mechanisms since they predict the multicast throughput more accurately than TCP throughput equations.

In reliable multicast, buffer management is an important issue that affects the loss recovery performance. Existing reliable multicast protocols do not explicitly address this issue and there is also little known work on it. We focus on the buffer management for active reliable multicast (ARM) when multiple simultaneous reliable multicast sessions are supported by some common active routers. Motivated by the fact that active routers in ARM can perform customized computation and provide soft-stage storage, we propose a new buffer management scheme, called adaptive cache pool (ACP), for cache resource partitioning and buffer replacement to achieve good loss recovery performance. The proposed ACP scheme is validated using ns-2 simulations to compare its performance with that of the original ARM scheme.

In multi-service mobile networks, asymmetric bandwidth allocation has been proposed to satisfy the requirements of the asymmetric traffic load introduced by some data applications. However, it is difficult to promptly adjust bandwidth allocation on the uplink and downlink according to the traffic load dynamics. Superfluous real-time (RT) calls or non-real-time (NRT) calls might be accepted. This may lead to a low bandwidth utilization. In this paper, we propose and evaluate a new call admission control (CAC) scheme to address the problems caused by the mismatch of bandwidth allocation and traffic changes. By determining the admissible bandwidth region for the NRT calls, the proposed scheme prevents the calls from overusing the bandwidth resources. Thus the bandwidth utilization is improved and the blocking probability of the high priority calls can be guaranteed at a low level. The simulation results demonstrate that the proposed CAC scheme can achieve better performance compared to the existing schemes, even those performing well in multi-service mobile networks with asymmetric bandwidth allocation.

Server-based loss recovery for reliable multicast can provide significant performance improvement in terms of loss recovery latency and bandwidth consumption. Appropriate congestion control mechanisms can provide fairness and maintains a high network throughput and link utilization. Data delivery, including loss recovery, and congestion control in reliable multicast are not independent issues and should be addressed simultaneously. In this paper, we propose to jointly perform local delivery and congestion control (LDCC). Mechanisms including local loss recovery, acknowledgement processing, buffer management, and congestion control are carefully designed. We demonstrate through simulations that the proposed scheme can achieve significantly lower loss recovery latency without sacrificing the network throughput, compared to existing local recovery protocols such as AER/NCA. It is also shown that our scheme conforms to TCP-compatible requirement.

TCP is a reliable transport protocol tuned to perform well in traditional networks made up of links with low bit-error rates. Networks with higher bit-error rates, such as those with wireless links and mobile hosts, violate many of the assumptions made by the transmission control protocol (TCP), causing degraded end-to-end performance. We propose a two-layer hierarchical cache architecture for enhancing TCP performance over heterogeneous networks with both wired and wireless links. A new network-layer protocol, called new snoop (NS), is designed. The main idea is to cache the unacknowledged packets at both the mobile switch center (MSC) and base station (BS), to form a two-layer cache hierarchy. If a packet is lost due to transmission errors in the wireless link, the BS takes the responsibility to recover the loss. When a handoff occurs, the packets cached at the MSC can help to minimize the latency of retransmissions due to temporal disconnection. NS can preserve the end-to-end TCP semantics and is compatible with existing TCP applications. Its implementation only requires code modification at the BS and MSC. Simulation results show that NS is significantly more robust in dealing with unreliable wireless links and handoffs as compared with the original snoop scheme, as well as some other existing TCP enhancements.

In this paper, we propose a scheme for implementing multiparty videoconferencing service on SONET/ATM rings. We focus on the architectural design and bandwidth demand analysis. Different multicasting methods on SONET/ATM rings are discussed and compared. A new multicast virtual path (VP) called "Multidrop VP" which is particularly suitable for SONET/ATM rings is proposed. An add-drop multiplexer (ADM) structure for rings capable of multidropping is also presented. Several VP assignment schemes are proposed and their bandwidth utilizations are compared.

The problem of finding a minimum-cast multicast tree (Steiner tree) is known as NP-complete. Heuristic-based algorithms for this problem to achieve good performance are usually time-consuming. In this paper, we propose a new strategy called tree-caching for efficient setup of multicast connections in connection-oriented networks. In this scheme, the tree topologies that have been computed are cached in a database of the source nodes and can be used for setup of subsequent connection requests which have some common multicast members. This can reduce the connection establishment time by an efficient reuse of cached trees without having to rerun a multicast routing algorithm for the whole group. This gain is obtained by eliminating, whenever possible, the expensive tree computation algorithm that has to be performed in setting up a multicast connection. We first formulate the problem of tree-caching. We then propose a tree-caching algorithm to reduce the complexity of the tree computations when a new connection is to be established. Through simulations, we find that the proposed tree-caching strategy perform well and can significantly reduce the computation complexity for setting up multicast connections.

In this paper, we propose a two-layer hierarchical cache architecture for enhancing TCP performance over heterogeneous networks with both wired and wireless links. A new network-layer protocol, called New Snoop, is designed. The main idea is to cache the unacknowledged packets at both the mobile switch center (MSG) and base station (BS), thus forming a two-layer cache hierarchy. If a packet is lost due to transmission errors in the wireless link, the BS takes the responsibility to recover the loss. When a handoff occurs during a TCP connection session, the packets cached in MSC can help to minimize the latency of retransmissions due to temporal disconnection. Simulation results show that using New Snoop is significantly more robust in dealing with unreliable wireless inks and handoffs as compared with the Snoop scheme (Balakrishnan et al. 1995) as well as other existing TCP enhancements.

Active reliable multicast (ARM) is a newly proposed loss recovery scheme for reliable multicast over the Internet. For a given amount of total cache available at each active router, the performance of ARM depends on how the amount of cache is partitioned to each multicast session. We call it the cache-partitioning problem. Following the approach of minimizing the total loss recovery traffic in the backbone network, an optimal cache-partitioning scheme is proposed and an analytical model is constructed. The performance of using the proposed optimal cache partitioning is compared with that using uniform cache partitioning and proportional partitioning. A significant performance improvement is found.

Local loss recovery for reliable multicast can provide significant performance improvement in terms of loss recovery latency, bandwidth consumption and network throughput. An analytical model for studying the optimal cache allocation for active reliable multicast (ARM) is constructed using standard optimization techniques, the optimal cache allocation pattern can be found. Our numerical results show that using optimal cache allocation yields significantly smaller loss recovery latency than using uniform cache allocation. To further enhance the loss recovery performance when the amount of cache at an active router is limited, we propose a probabilistic caching policy. We derive the optimal caching probabilities for each active router in a given multicast tree with a given cache allocation pattern. We show that with the use of probabilistic caching policy, a further reduction in loss recovery latency can be obtained.

A new push-and-pull hybrid data broadcast scheme is proposed for providing wireless information services to three types of clients, general, pull and priority clients. Only pull and priority clients have the back channel for sending requests to the broadcast server. There is no scalability problem with the hybrid scheme because the amount of pull and priority clients is very small. Based on the requests collected from pull and priority clients, the server estimates the interest pattern changes of the whole client population. Then the broadcast schedule on the push channel for the next broadcast cycle is adjusted. Besides the push channel, a small amount of broadcast bandwidth is allocated to a pull channel. The data to be broadcast on the pull channel is decided by the server in real-time and priority is given to requests from priority clients. Simulations show that with a time-varying client interest pattern, the average data access time for all three types of clients can be minimized. Because of the priority in using the pull channel, priority clients can achieve the lowest access time and pull clients can achieve a lower access time than general clients. To further improve the performance, the hybrid scheme with local client cache is also investigated.