Nowadays, network technologies are developing very rapidly. The growing volume of transmitted information (video, data, VoIP, etc.), the physical growth of networks, and inter-network traffic are ...forcing manufacturers to produce more powerful and "smart" devices that use new methods of transferring and sorting data. Such connected smart devices (IoT) are used in intelligently controlled traffic for self-driving vehicles in Vehicle Adhoc Networks (VANET), in electricity and water in smart cities, and in-home automation in smart homes. These types of connected Internet of Things (IoT) devices are used to leverage different types of network structures. Such IoT sensor devices can be deployed as a wireless sensor network (WSN) in a mesh topology. Both WSNs and Wireless Mesh Networks (WMNs) are easy to organize as well as to deploy. In this case, there are many reasons for combining these different types of networks. In particular, the detailed sensory capabilities of sensor networks may be improved by increasing bandwidth, reliability and power consumption in the mesh topology. However, there are currently only a handful of studies devoting to integrate these two different types of networks. In addition, there is no systematic review of existing interconnection methods. That is why in this article we explore the existing methods of these two networks and provide an analytical basis for their relationship. We introduce the definition of WSN and WMN and then look at some case studies. Afterward, we present several challenges and opportunities in the area of combined Wireless Mesh Sensor Network (WMSN) followed by a discussion on this interconnection through literature review and hope that this document will attract the attention of the community and inspire further research in this direction.
The digital environment is constantly evolving with a growing diversity of network access technologies, such as ADSL, WiFi, 5G, LiFi, Zigbee, and the deployment of innovative services such as ...mobility, location, and telemetric services, as well as new applications such as smart parking, smart cities, machine-to-machine communication, and pervasive gaming. A few years ago, the services offered were dependent on the type of network, such as voice for telecommunications networks, data for computer networks, and audio/video for broadcast networks. However, service providers now need to adapt and anticipate changing consumption patterns, such as user-centric services, in their offerings. The challenge lies in how to quickly and efficiently deploy new services in this rapidly evolving technological landscape. The primary aim of this paper is to examine the impact of virtualization on the network deployment process in this new landscape. We concentrate on the integration of virtualization into the Network Deployment Process (called Virtual Network Virtual Deployment-VNVD). VNVD considers the properties of flexibility, adaptability, and dynamicity, which are crucial for Network-as-a-Service. In this context, Software-Defined Networking and Network Function Virtualization play a significant role in the design of new network architectures.
In the last few years, huge amounts of progress have been made regarding remote sensing in the field of computer vision. This success and progress is mostly due to the effectiveness of deep learning ...(DL) algorithms. In addition, the remote sensing community has shifted its attention to DL, and DL algorithms have been used to achieve significant success in many image analysis tasks. However, with regard to remote sensing, a number of challenges caused by difficulties in data acquisition and annotation have not been fully solved yet. This reprint is a collection of novel developments in the field of remote sensing using computer vision, deep learning, and artificial intelligence. The articles published involve fundamental theoretical analyses as well as those demonstrating their application to real-world problems.
Unmanned aerial vehicles (UAVs) will be an integral part of the next generation wireless communication networks. Their adoption in various communication-based applications is expected to improve ...coverage and spectral efficiency, as compared to traditional ground-based solutions. However, this new degree of freedom that will be included in the network will also add new challenges. In this context, the machine-learning (ML) framework is expected to provide solutions for the various problems that have already been identified when UAVs are used for communication purposes. In this article, we provide a detailed survey of all relevant research works, in which ML techniques have been used on UAV-based communications for improving various design and functional aspects such as channel modeling, resource management, positioning, and security.
The provision of high data rate services to mobile users combined with improved quality of experience (i.e., zero latency multimedia content) drives technological evolution towards the design and ...implementation of fifth generation (5G) broadband wireless networks. To this end, a dynamic network design approach is adopted whereby network topology is configured according to service demands. In parallel, many private companies are interested in developing their own 5G networks, also referred to as non-public networks (NPNs), since this deployment is expected to leverage holistic production monitoring and support critical applications. In this context, this paper introduces a 5G NPN architectural approach, supporting among others various key enabling technologies, such as cell densification, disaggregated RAN with open interfaces, edge computing, and AI/ML-based network optimization. In the same framework, potential applications of our proposed approach in real world scenarios (e.g., support of mission critical services and computer vision analytics for emergencies) are described. Finally, scalability issues are also highlighted since a deployment framework of our architectural design in an additional real-world scenario related to Industry 4.0 (smart manufacturing) is also analyzed.
Virtual network embedding arranges virtual network services onto substrate network components. The performance of embedding algorithms determines the effectiveness and efficiency of a virtualized ...network, making it a critical part of the network virtualization technology. To achieve better performance, the algorithm needs to automatically detect the network status which is complicated and changes in a time-varying manner, and to dynamically provide solutions that can best fit the current network status. However, most existing algorithms fail to provide automatic embedding solutions in an acceptable running time. In this paper, we combine deep reinforcement learning with a novel neural network structure based on graph convolutional networks, and propose a new and efficient algorithm for automatic virtual network embedding. In addition, a parallel reinforcement learning framework is used in training along with a newly-designed multi-objective reward function, which has proven beneficial to the proposed algorithm for automatic embedding of virtual networks. Extensive simulation results under different scenarios show that our algorithm achieves best performance on most metrics compared with the existing state-of-the-art solutions, with upto 39.6% and 70.6% improvement on acceptance ratio and average revenue, respectively. Moreover, the results also demonstrate that the proposed solution possesses good robustness.
In recent years, survivability of optical communication networks against large-scale disaster failures has been studied. The survivability analyses done by most of the studies are based on arbitrary ...simplified disaster areas under the assumption of uniform disaster occurrence in a given area, and short-term evaluation of network robustness. However, for assessing the generic applicability and evaluating the performance of any protection, recovery, and/or topology design scheme irrespective of the varying geographical region and network topology, a stochastic model for disaster occurrence and optical network topology would be useful. In this paper, we propose a stochastic model to estimate the impact of earthquake disasters on a backbone optical network, namely, earthquake risk and backbone optical network (ERBON) model. We consider various stochastic distributions, real statistics, stochastic geometry, and graph theory to model seismic zonation, epicenter location and density, earthquake magnitudes, link/node failures, and network topology/connectivity. Furthermore, we propose an earthquake risk minimized node relocation (ERMNR) scheme that can improve the optical network's survivability. Performance of the proposed ERMNR scheme is evaluated under the proposed ERBON model and for real-world earthquake risk data from the U.S. and India.
Abstract Many biological research areas such as drug design require gene regulatory networks to provide clear insight and understanding of the cellular process in living cells. This is because ...interactions among the genes and their products play an important role in many molecular processes. A gene regulatory network can act as a blueprint for the researchers to observe the relationships among genes. Due to its importance, several computational approaches have been proposed to infer gene regulatory networks from gene expression data. In this review, six inference approaches are discussed: Boolean network, probabilistic Boolean network, ordinary differential equation, neural network, Bayesian network, and dynamic Bayesian network. These approaches are discussed in terms of introduction, methodology and recent applications of these approaches in gene regulatory network construction. These approaches are also compared in the discussion section. Furthermore, the strengths and weaknesses of these computational approaches are described.
Today’s networks are filled with a massive and ever-growing variety of network functions that coupled with proprietary devices, which leads to network ossification and difficulty in network ...management and service provision. Network Function Virtualization (NFV) is a promising paradigm to change such situation by decoupling network functions from the underlying dedicated hardware and realizing them in the form of software, which are referred to as Virtual Network Functions (VNFs). Such decoupling introduces many benefits which include reduction of Capital Expenditure (CAPEX) and Operation Expense (OPEX), improved flexibility of service provision, etc. In this paper, we intend to present a comprehensive survey on NFV, which starts from the introduction of NFV motivations. Then, we explain the main concepts of NFV in terms of terminology, standardization and history, and how NFV differs from traditional middle-box based network. After that, the standard NFV architecture is introduced using a bottom up approach, based on which the corresponding use cases and solutions are also illustrated. In addition, due to the decoupling of network functionalities and hardware, people’s attention is gradually shifted to the VNFs. Next, we provide an extensive and in-depth discussion on state-of-the-art VNF algorithms including VNF placement, scheduling, migration, chaining and multicast. Finally, to accelerate the NFV deployment and avoid pitfalls as far as possible, we survey the challenges faced by NFV and the trend for future directions. In particular, the challenges are discussed from bottom up, which include hardware design, VNF deployment, VNF life cycle control, service chaining, performance evaluation, policy enforcement, energy efficiency, reliability and security, and the future directions are discussed around the current trend towards network softwarization.