Search

Drone cell (DC) is envisioned to enable the dynamic service provisioning for radio access networks (RANs), in response to the spatial and temporal unevenness of user traffic. In this article, we propose a hierarchical deep reinforcement learning (DRL)-based multi-DC trajectory planning and resource allocation (HDRLTPRA) scheme for high-mobility users. The objective is to maximize the accumulative network throughput while satisfying user fairness, DC power consumption, and DC-to-ground link quality constraints. To address the high uncertainties of the environment, we decouple the multi-DC TPRA problem into two hierarchical subproblems, i.e., the higher level global trajectory planning (GTP) subproblem and the lower level local TPRA (LTPRA) subproblem. First, the GTP subproblem is to address trajectory planning for multiple DCs in the RAN over a long time period. To solve the subproblem, we propose a multiagent DRL-based GTP (MARL-GTP) algorithm in which the nonstationary state space caused by the multi-DC environment is addressed by the multiagent fingerprint technique. Second, based on the GTP results, each DC solves the LTPRA subproblem independently to control the movement and transmit power allocation based on the real-time user traffic variations. A deep deterministic policy gradient (DEP)-based LTPRA (DEP-LTPRA) algorithm is then proposed to solve the LTPRA subproblem. With the two algorithms addressing both subproblems at different decision granularities, the multi-DC TPRA problem can be resolved by the HDRLTPRA scheme. Simulation results show that 40% network throughput improvement can be achieved by the proposed HDRLTPRA scheme over the nonlearning-based TPRA scheme.

In this article, we investigate the UAV-aided edge caching to assist terrestrial vehicular networks in delivering high-bandwidth content files. Aiming at maximizing the overall network throughput, we formulate a joint caching and trajectory optimization (JCTO) problem to make decisions on content placement, content delivery, and UAV trajectory simultaneously. As the decisions interact with each other and the UAV energy is limited, the formulated JCTO problem is intractable directly and timely. To this end, we propose a deep supervised learning scheme to enable intelligent edge for real-time decision-making in the highly dynamic vehicular networks. In specific, we first propose a clustering-based two-layered (CBTL) algorithm to solve the JCTO problem offline. With a given content placement strategy, we devise a time-based graph decomposition method to jointly optimize the content delivery and trajectory design, with which we then leverage the particle swarm optimization (PSO) algorithm to further optimize the content placement. We then design a deep supervised learning architecture of the convolutional neural network (CNN) to make fast decisions online. The network density and content request distribution with spatio-temporal dimensions are labeled as channeled images and input to the CNN-based model, and the results achieved by the CBTL algorithm are labeled as model outputs. With the CNN-based model, a function which maps the input network information to the output decision can be intelligently learnt to make timely inference and facilitate online decisions. We conduct extensive trace-driven experiments, and our results demonstrate both the efficiency of CBTL in solving the JCTO problem and the superior learning performance with the CNN-based model.

With its potential versatility and reliability, the space-air-ground integrated vehicular network (SAGVN) is envisioned as a promising solution to deliver quality vehicular services anywhere at any time. This article proposes a software defined framework for SAGVN to achieve flexible, reliable, and scalable network resource management. First, key applications and research challenges in resource management are identified. Then we propose a hybrid and hierarchical SAGVN control architecture to balance the trade-off between system status acquisition and signaling overhead in different scenarios. Considering the dynamic networking environment with multi-dimensional resources and diverse services, it is challenging to make optimal resource management decisions in real time; thus, artificial intelligence (AI)-based engineering solutions are investigated to facilitate efficient network slicing, mobility management, and cooperative content caching and delivery. A trace-driven case study is presented to demonstrate the effectiveness of the proposed SAGVN framework with AI-based methods in increasing the SAGVN throughput performance.

To enable ever-increasing vehicular applications, heterogeneous vehicular networks (HetVNets) are recently emerged to provide enhanced and cost-effective wireless network access. Meanwhile, edge caching is imperative to future vehicular content delivery to reduce the delivery delay and alleviate the unprecedented backhaul pressure. This work investigates content caching in HetVNets where Wi-Fi roadside units (RSUs), TV white space (TVWS) stations, and cellular base stations are considered to cache contents and provide content delivery. Particularly, to characterize the intermittent network connection provided by Wi-Fi RSUs and TVWS stations, we establish an on-off model with service interruptions to describe the content delivery process. Content coding then is leveraged to resist the impact of unstable network connections with optimized coding parameters. By jointly considering file characteristics and network conditions, we minimize the average delivery delay by optimizing the content placement, which is formulated as an integer linear programming (ILP) problem. Adopting the idea of student admission model, the ILP problem is then transformed into a many-to-one matching problem and solved by our proposed stable-matching-based caching scheme. Simulation results demonstrate that the proposed scheme can achieve near-optimal performances in terms of delivery delay and offloading ratio with low complexity.

Space-air-ground integrated network (SAGIN) is envisioned as a promising solution to provide cost-effective, large-scale, and flexible wireless coverage and communication services. Since realworld deployment for testing of SAGIN is difficult and prohibitive, an efficient SAGIN simulation platform is requisite. In this article, we present our developed SAGIN simulation platform which supports various mobility traces and protocols of space, aerial, and terrestrial networks. Centralized and decentrallized controllers are implemented to optimize the network functions such as access control and resource orchestration. In addition, various interfaces extend the functionality of the platform to facilitate user-defined mobility traces and control algorithms. We also present a case study where highly mobile vehicular users dynamically choose different radio access networks according to their quality of service (QoS) requirements.

In this paper, we propose an online control frame-work to dynamically slice the network resource for isolated service provisioning in Space-Air-Ground integrated Vehicular Network (SAGVN). In particular, at a given time slot, the system makes online decisions on the request admission and scheduling, UAV dispatching, and resource slicing for different services. To characterize the impact of those parameters, we construct a time-averaged queue stability criteria by taking queue backlogs of all services into consideration, and formulate a system revenue function which incorporates the time-averaged system throughput and UAV dispatching cost. The objective is to maximize the system revenue while stabilizing the time-averaged queue, which can be achieved via the Lyapunov optimization theory. By bounding the drift-plus-penalty, the problem then can be decoupled into four independent subproblems, which are readily solved. The merits of our control framework are three-fold: 1) the system can admit and process as many requests as possible; 2) the time-averaged UAV dispatching cost is minimized; and 3) service queues can be stabilized over time. Extensive simulations are carried out, and the results demonstrate that the control framework can effectively achieve the system revenue maximization and queueing stabilization. Moreover, it can balance the trade-off among system throughput, UAV dispatching cost, and queueing states via parameter tuning.

It is envisioned that the Internet of Things (IoT) will provide promising opportunities to users, manufacturers, and service providers with a wide applicability in many fields. By employing social networking and device-to-device (D2D) communications in the IoT, the resulting social IoT can potentially provide services more effectively and efficiently. This paper focuses on content sharing among smart objects (devices) in the social IoT with D2D-based cooperative coded caching. Generally, complete content items or coded fragments are allowed to be delivered via multi-hop cooperative D2D communications. First, aiming at maximizing the overall success rate of multi-hop-based content sharing, the interplay between coding parameter optimization and wireless resource allocation is investigated by considering both physical and social characteristics. Moreover, a Roth and Vande Vate-based distributed scheme is proposed to solve the dynamic matching problem between the content helpers and content requesters. Numerical results demonstrate that the proposed scheme can achieve a good tradeoff between system performance and computational complexity.

This work considers the problem of reliability and secrecy enhancement for wireless content sharing between a content source node and a content requester. By exploiting the social characteristics of multiple nodes in the presence of multiple independent eavesdroppers, this paper first investigates the impact of mobility for source node selection for transmission reliability, within a cooperative wireless network. Furthermore, trustworthiness and social-tie-based jammer node selections are explored for cooperative jamming to provide secrecy, while allocating power appropriately to the source node and the cooperative jammer node to maximize the worst-case ergodic secrecy rate. Specifically, the source transmitter is selected by first narrowing the potential link set to provide the desired transmission success rate while considering the physical channel and social characteristics jointly. Moreover, the effect of jammer dependability based on its social interactive behavior is also investigated. Instead of focusing on full channel state information (CSI), this paper also investigates the more practical case in which only statistical CSI knowledge is known. Our optimization is based on the upper and lower bounds to the secrecy rate to simplify the power optimization problem without noticeable performance loss. Additional performance analysis for the impact of social characteristics is given. Finally, a one-dimensional search is proposed to further reduce the computational complexity of the power optimization.

Device-to-device (D2D) communication has attracted substantial research attention recently, due to its potential to improve coverage, spectrum efficiency, and energy efficiency within the existing cellular infrastructure. One major challenge for spectrum resource sharing in D2D underlay lies in the mutual interference between cellular user equipments (CUEs) and D2D user equipments (DUEs). Considering this mutual interference constraint, this work investigates the problem of optimal matching of D2D links and CUEs to form spectrum-sharing partners to maximize ergodic sum rates under transmit power and outage constraints. Unlike previous works, full channel-state information (CSI) is not required. To solve the resulting high-complexity problem, candidate DUE sets are first narrowed down according to required outage probability constraints, which are used to construct a simplified bipartite graph. The weight of the bipartite graph is characterized as the maximization of ergodic sum rate of the associated D2D and cellular links under outage constraints for which a low-complexity algorithm is proposed to solve the nonconvex problem. After constructing the bipartite graph, the Hungarian algorithm is used to determine the optimal pairing between D2D links and CUEs. Numerical results demonstrate that the proposed algorithm can improve the outage-constrained spectrum efficiency of D2D networks with practical complexity.

In this paper, we investigate the pilot spoofing attack (PSA) detection and downlink precoding schemes in massive MIMO systems with spatially correlated channels. During the uplink channel training phase, we conduct channel estimation by using two different expected covariance matrices with a minimum mean square error (MMSE) based estimator, and the PSA is detected by comparing the power of the channel estimations' difference with a predetermined threshold. Once the PSA is detected, the BS transmits some confidential parameters with beamforming aided physical layer security to the legitimate users for the second channel training. In this case, the subspace of the eavesdropping channel can be estimated by combining the estimations of the two training phases. We then propose a MMSE based precoding scheme to improve the downlink secrecy performance, which can achieve unbounded secrecy rate as long as the channel covariance matrices are linearly independent.

The flourishing vehicular applications require vehicles to download huge amount of Internet data, which consumes significant backhaul bandwidth and considerable time for data content delivery. Caching the popular data at network edge station can alleviate the congestion at backhaul network and reduce the data delivery delay. In this paper, we propose a dynamic edge caching policy for Heterogeneous Vehicular Network via Reinforcement Learning on adaptive traffic intensity and hot content popularity. We aim to enhance the download rate of vehicles adapting to dynamic vehicle velocity and hot file pool by caching the popular content on heterogeneous network edge stations. The proposed policy makes use of real time information and jointly considers download rate for each file and utility for edge stations to improve overall download performance. Simulation results show that our proposed policy can achieve better download rate than random and fixed caching policies.

To cope with the explosive vehicular content demands from various applications and services, it is imperative to cache the content files close to end users to reduce both the core network traffic load and the delivery delay. The heterogeneous vehicular networks provide multiple data pipes to access to the Internet for vehicles, and thus can be leveraged to cache the required content files on different access network edges and further improve the caching effectiveness. This paper focuses on the content delivery in heterogeneous vehicular networks that allow content caching in roadside WiFi APs, TV White Space Stations, and Cellular Base Stations. With the objective of minimizing the content delivery delay, a Student Admission matching- based content caching scheme is proposed by considering the file popularity, vehicle mobility and cache capacity of the edge infrastructure in heterogeneous vehicular networks, whereby a stable result is further obtained via the Gale-Shapley algorithm. Our simulation results demonstrate the advantages of the proposed caching scheme.

Offloading vehicular data traffic from cellular networks to roadside WiFi networks is a very interesting issue since it can not only alleviate the traffic congestion for cellular networks, but also reduce the communication cost for vehicle users. In this paper, we study the vehicle-to-vehicle (V2V) assisted WiFi offloading, where nearby vehicles that associate to different access points (APs) can use their idle WiFi resource to offload part of peer's data traffic. We also consider the Internet access delay introduced by the network detection, user authentication and network address assignment between the vehicle and the AP prior to actual data transmission, which has impact on the WiFi cell sojourn duration of the vehicle. The offloading efficiency, which is the traffic offloaded from cellular network, is analyzed by modeling an M/G/1/K queueing process under various conditions. The accuracy of our analysis is validated through the conducted simulation.

Distributed storage that leverages cellular device-to-device (D2D) underlay has attracted rising research interest due to its potential to offload cellular traffic, improve spectral efficiency and energy efficiency, and reduce transmission delay. This paper investigates the overall transmission cost minimization problem based on a content encoding strategy to download a new content item or repair a lost content item in D2D-based distributed storage systems while guaranteeing users’ quality of service. In addition to the optimization of the coding parameters, the cost minimization problem also considers the distribution of content items, the selection of content helpers for each content requester, and the spectrum reuse for establishing D2D links in between. Formulating a hypergraph-based three-dimensional matching problem among content helpers, requesters, and cellular user resources, we present a local search based algorithm with low complexity for optimization. Numerical results demonstrate the performance and the effectiveness of our proposed approach.

Wireless distributed storage systems can potentially relieve the centralized traffic burden of base stations (BSs), and further improve system reliability for content sharing in device-to-device (D2D) communications. Mobile devices [i.e., content requesters (CRs)] can not only download their desired contents from serving BSs, but can also get them from neighboring devices [i.e., content helpers (CHs)] with possession of the contents. However, D2D links between CRs and CHs are not necessarily stable, due to user mobility and the time-varying property of wireless links. This paper focuses on the utilization of socially enabled D2D links to deliver the desired contents based on distributed storage. We evaluate the success rate for downloading and repairing in D2D-assisted networks accordingly, by analyzing statistic social interaction information for potential D2D links. Thus, it is necessary to maintain or assign enough qualified D2D links to afford content downloading and repairing from neighboring devices. To reduce the overall system transmission cost, this paper further proposes a hierarchical bi-partite method to guarantee at least $k$ admissible D2D links according to their statistical channel state information, by considering one type of erasure correcting codes, the maximum distance separable code. Simulation results demonstrate the performance and advantage of our proposed scheme.

Coded caching systems can facilitate traffic offloading from base stations and content sharing between content providers and content requesters via device- to-device (D2D) communications. In particular, dividing content items into mul-tiple pieces not only can enable the possibility of decreasing transmission delay and energy consumption, but also can contribute to secrecy enhancement since potential social outcasts can decode the content item only if they can obtain enough pieces. In this work, the tradeoff problem between content sharing efficiency and secure transmission in coded caching systems is investigated. First, to maximize the caching hit ratio with secrecy outage constraints, a joint optimization problem considering coding parameters, content placement, and power allocation is formulated. Further, a lower bound on the caching hit ratio and a upper bound on the secrecy outage probability are derived to simplify the original optimization problem. Numerical results demonstrate the effectiveness of the proposed scheme.

This work investigates content sharing among smart objects (devices) via device-to-device (D2D) communications in the social Internet of Things (IoT) by exploiting distributed content coding schemes. Aiming at minimizing the overall transmission cost, the resource matching between content transmitters and content receivers is optimized by applying matching theory. Particularly, the dynamic distributed Roth and Vande Vate algorithm is employed to optimize the matching problem, achieving a lower computational complexity and a higher system stability. In addition, social characteristics among mobile users are also exploited in the optimization problem to further increase system reliability and robustness. Numerical results demonstrate the effectiveness of the proposed scheme.

This work investigates the performance for D2D enabled wireless caching in distributed storage system by taking the typical erasure correcting code namely maximum distance separable (MDS) into consideration. Targeting on the minimization of the transmission cost for content sharing, the spectrum resource allocation is optimized based on their statistical channel state information (CSI). To evaluate the quality of D2D links, two cases are considered with different assumptions for whether those physical links are stable or not regarding to mobility impacted user behaviors. Numerical results demonstrate the effectiveness of the proposed scheme.

This work investigates content sharing in cellular device-to-device underlay based wireless distributed storage systems by exploiting an (n, k, d) distributed content coding scheme. To guarantee that content requesters (CRs) can rely on enough eligible content helpers (CHs) for content download, the selection of CH5 and the determination of the coding parameter k are optimized by evaluating the physical conditions of mobile users and analyzing the outage probability of data transmission. Targeting the minimization of the overall transmission cost, the assignment of CHs for each CR and spectrum allocation for each CH-CR link, are jointly formulated as a three-dimensional matching problem, and are optimized by using a hierarchical bipartite matching algorithm. Numerical results demonstrate clear performance advantages of our proposed scheme.

Wireless caching using device-to-device (D2D) communications is a promising approach for reducing delivery delay and improving spectrum efficiency and energy efficiency. In addition to the physical link condition, social behaviors are also of great importance for effectiveness enhancement of the D2D-based wireless caching schemes. In this work, we focus on resource allocation including power and spectrum to improve the system efficiency in terms of jointly considered spectrum efficiency and energy efficiency, by leveraging both physical and social characteristics. Furthermore, a heuristic-based mixed integer nonlinear programming algorithm is proposed to solve the joint optimization problem, including the establishment of D2D links, spectrum allocation and power optimization. Numerical results demonstrate the effectiveness of the proposed scheme in terms of different pairing algorithms.

This work studies secrecy enhancement for socially enabled communications in cellular device-to-device (D2D) underlay through resource allocation. By analyzing the impact of social characteristics of those involved D2D users (DUs), proper selection of transmitters and friendly jammer nodes with appropriate power and spectrum allocation can facilitate secrecy transmission. First, we select D2D transmitter by characterizing the link to guarantee the desired success rate without downgrading the service requirement for impacted cellular users (CUs). Furthermore, jammers' trustiness based on their own social interaction is considered for secrecy enhancement. Numerical results verify the performance of our proposed scheme.

Device-to-device (D2D) communications have recently attracted broad attention, owing to its potential ability to improve spectrum and energy efficiency within the existing cellular infrastructure. Without sophisticated control, D2D users themselves are not powerful enough to resist eavesdropping or fight against security attacks. This work investigates how to select jamming partners for D2D users to thwart eavesdroppers by exploiting social relationship with the help of full channel state information (CSI) and partial CSI, respectively. We aim to maximise the worst-case eavesdropping by selecting jammer node and allocating transmit power for both source and jammer nodes. We first present a heuristic genetic algorithm-based solution to address the problem. We then propose low-complexity optimisation solutions by considering the upper and lower bounds of power allocation. Numerical results show that the proposed schemes can achieve better performance through finding an appropriate partner. Copyright © 2015 John Wiley & Sons, Ltd.