检索结果-内蒙古大学图书馆

IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES)

作者： Renya Nath N Hiran V Nath Department of Computer Science and Engineering National Institute of Technology Calicut Kozhikode India

ISBN: (数字)9798350376135

ISBN: (纸本)9798350376142

The expansion of the Internet of Things (IoT) has permeated various sectors, facilitating the integration of IP connectivity into many devices. These devices, also known as Internet of Things devices, are vulnerable to a diverse array of security threats. As a result, there has been a significant increase in the occurrence of IoT malware cases in the past few years. Protecting IoT devices from such assaults has become an urgent and crucial topic. However, conventional peripheral security measures are insufficient to deal with the lightweight security requirements inherent to the IoT landscape. Considering this, we propose a Refined Intrusion Detection Model for IoT networks (RIDM-IoT) that demonstrates similar efficiency in exposing malicious activities compared to the existing computationally expensive methods. The primary strength of the proposed model is that it's capable of efficiently detecting attacks in IoT networks while requiring less computational resources. RIDM-IoT accomplishes this by employing a unique hybrid feature selection strategy that combines filter-based and wrapper-based feature selection methods. As a wrapper-based feature selection approach, we employ the well-known genetic algorithm, Particle Swarm Optimisation (PSO). The suggested feature selection approach decreases the size of the feature space by 93%. Furthermore, we employ simple machine learning algorithms to construct intrusion detection models instead of intricate deep learning models. We conducted tests on RIDM-IoT with unseen attack types to verify its general behaviour. The results demonstrate that the suggested model effectively detects attacks in IoT networks, using a smaller collection of features when compared to state-of-the-art complex models.

关键词： Accuracy Computational modeling Intrusion detection Feature extraction Malware network function virtualization Computational efficiency Internet of Things Security Software defined networking

来源：评论

学校读者我要写书评

暂无评论

The Research and Implementation of network Slices and Resources Scheduling

The Research and Implementation of Network Slices and Resour...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Jinfeng Wang Kun Xie Weiliang Liu Chengcheng Li Yasheng Zhang Dept. Software Engineering Beijing University of Posts and Telecommunications Beijing China Dept. Computer Science and Technology Beijing University of Posts and Telecommunications Beijing China Dept. The 54th Research Institute of CETC China Electronics Technology Group Corporation Limited Shijiazhuang China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

This thesis advocates for the enhancement of network data throughput and service capabilities through the establishment of device identity class isolation underpinned by SDN/NFV technologies. It proposes a network slicing mechanism to segregate devices into dedicated network slices with independently allocated resources. Further, a novel resource scheduling algorithm based on Deep Deterministic Policy Gradient (DDPG) is introduced to ensure efficient resource distribution.

关键词： Scheduling algorithms network slicing Bandwidth Throughput Deep reinforcement learning network function virtualization Resource management Software defined networking Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

State-aware Subscriber Steering in Fiber Access networks for Improved Resilience

State-aware Subscriber Steering in Fiber Access Networks for...

引用

IEEE Conference on network function virtualization and Software Defined networks (NFV-SDN)

作者： Fridolin Siegmund Philip Jonas Franz Bjoern Nagel Maik Rüder Lisa Wernet Matthias Hollick Ralf Kundel Technical University of Darmstadt Deutsche Telekom Technik GmbH

ISBN: (数字)9798350380538

ISBN: (纸本)9798350380545

network softwarization is currently emerging in home and enterprise Internet access networks. Still, the advantages of programmable hardware nodes and virtualized network functions in the access network as resilience enablers should be researched more. Access networks are typically built in a two-layer tree topology with sparse redundancy and limited adaptability. To overcome this, this work investigates how softwarization with redundancy can achieve resilience improvements in such networks. We present an architecture and prototypical implementation of a fiber-based access network and subscriber termination, with a redundant and adaptive design throughout the whole path from subscribers to the Internet. By proactively migrating states and steering subscriber flows, we reached total average downtimes of around 156 milliseconds to restore Internet access after disruption in the case of one subscriber. In comparison, it takes hours to restore Internet access in case of an outage with zero redundancy. Our solution is cost-effective by exploiting the architectural advances of Software Defined networking, allowing the use of virtualized network functions and hardware-based functions simultaneously.

关键词： network topology Redundancy Computer architecture Optical fiber networks Hardware Internet Topology network function virtualization Software defined networking Resilience

来源：评论

学校读者我要写书评

暂无评论

VNF Migration with Fast Defragmentation: A GAT-Based Deep Learning Method

arXiv

引用

arXiv 2024年

作者： Zhang, Fangyu Chen, Yuang Lu, Hancheng Lu, Chengdi CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China Hefei230027 China

network function virtualization (NFV) enhances service flexibility by decoupling network functions from dedicated hardware. To handle time-varying traffic in NFV network, virtualized network function (VNF) migration has been involved to dynamically adjust resource allocation. However, as network functions diversify, different resource types may be underutilized due to bottlenecks, which can be described as multidimensional resource fragmentation. To address this issue, we firstly define a metric to quantify resource fragmentation in NFV networks. Then, we propose a multi-hop graph attention network (MHGAT) model to effectively extract resource features from tailored network layers, which captures the overall network state and produces high-quality strategies rapidly. Building on this, we develop an MHGAT method to implement fast defragmentation and optimize VNF migration. Simulations demonstrate that by fast defragmentation, the MHGAT method improves the acceptance ratio by an average of 12.8%, reduces the overload ratio by an average of 30.6%, and lowers migration loss by an average of 43.3% compared to the state-of-art benchmark. Copyright © 2024, The Authors. All rights reserved.

关键词： network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Virtual network function Placement for Mapping SFC Requests of UAV-Sourced Video Streaming in Cloud networks

Virtual Network Function Placement for Mapping SFC Requests ...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Duo Xu Xin Tian Khanh Pham Erik Blasch Genshe Chen Intelligent Fusion Technology Inc. Germantown MD USA Air Force Research Lab NM USA Air Force Research Laboratory Arlington VA USA

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

Unmanned Aerial Vehicles (UAVs) have enormous potential in the public and civil domains. They are particularly useful in applications of video surveillance, especially in modern battlefield. However, due to the large amount of resources consumed by video streaming, the issue of poor resource utilization still prevents the use of multi-UAV systems for sharing videos with users in a stable and reliable way. Since the development of network function virtualization (NFV), traditional dedicated network devices in cloud networks can be implemented as software and network functions (NFs) can be flexibly instantiated on common off-the-shelf servers, enabling NFs to be deployed in the form of virtual network functions (VNFs) and hence improving the resource utilization in communication networks. In this article, we investigate the VNF placement problem for mapping users' service function chain requests (SFCRs) of UAV-sourced video streaming in cloud networks. To be more practical, we consider the fundamental resource overheads and synchronization cost of virtual machines (VMs) on servers for processing VNF requests. The VNF placement problem is formulated as an integer linear programming model with the aim of minimizing the total resource consumption under the constraints of the delay requirements. We propose a node ranking-based method (UAV-MA) to find a near optimal solution for UAV-sourced video streaming, including an SFCR mapping phase to map SFCRs onto servers and an adjustment phase to refine the placement of VNFs. Evaluations demonstrate that the proposed approaches can derive a resource-efficient VNF placement strategy, outperforming baseline methods.

关键词： Cloud computing Conferences Streaming media Video surveillance Software network function virtualization Software reliability

来源：评论

学校读者我要写书评

暂无评论

CRA: Cost-Effective and Highly Reusable Architecture of Space-Air-Ground Integrated network Based on TCP and DTN

CRA: Cost-Effective and Highly Reusable Architecture of Spac...

引用

Frontiers Technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Shiqi Guo Li Ma Min Wang Liang Liu Ming Chen College of Computer Sciences and Technology Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Space-Air-Ground Integrated networks (SAGIN) is expected to become an important information infrastructure in the future spatial information field. However, most existing architectures introduce new protocols to interconnect multiple domains, resulting in high time and economic costs, with existing infrastructure being non-reusable. To address these problems, this paper introduces the CRA, a Cost-effective and highly Reusable Architecture of space-air-ground integrated network based on TCP and DTN. It integrates Low Earth Orbit (LEO) satellite networks, Geostationary Orbit (GEO) satellite networks, and the terrestrial Internet into a unified SAGIN framework. Furthermore, we develops an Integration Gateway (IG) to bridge multiple heterogeneous domains, enabling efficient data conversion between Disruption Tolerant networks (DTNs) and TCP/IP-based networks. Additionally, an experimental SAGIN system based on network function virtualization is also constructed to verify our proposed architecture and integrated gateway. The experimental results show that the CRA architecture is feasible and the designed CRA gateway is efficient in terms of throughput and latency.

关键词： Satellites Protocols Low earth orbit satellites Prototypes Computer architecture Logic gates Space-air-ground integrated networks Throughput network function virtualization Internet

来源：评论

学校读者我要写书评

暂无评论

DeepVNP:Virtual network Placing with Deep Reinforcement Learning in Industrial IoT

DeepVNP:Virtual Network Placing with Deep Reinforcement Lear...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Bo Wang Yang Yang Yu Zhang Cheng Zhan Fei Wang College of Computer and Information Science Southwest University Chongqing China College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The diversity of devices, systems, and applications imposes stringent requirements on the Industrial Internet of Things (IIoT) regarding agility, reliability, and delay sensitivity. network function virtualization (NFV) can provide on-demand service and flexible resource management for the IIoT. Of course, a highefficiency and time-saving NFV placement solution is critical for IIoT. Information processing requests in an actual industrial scenario is generally continuous and dynamic. In addition, industrial information systems pay more attention to the real-time nature of the information. Considering the above challenges and the fact that most previous optimization-based solutions cannot cope with the characteristics of dynamic requests, we propose a deep reinforcement learning-based method to solve the virtual network function (VNF) placement problem, called DeepVNP, which automatically places the VNF according to the current physical network state, aiming to reduce the placement cost and improve the profit of the NFV system. In addition, the Information Age (AoI) is introduced to measure the real-time freshness of information, and it is naturally integrated with delay constraints. Through simulations, we evaluate the convergence and performance of DeepVNP. Numerical results show that, compared with several existing solutions, DeepVNP performs well in terms of request acceptance rate, resource utilization, total system cost, and average AoI.

关键词： Costs Information processing Information age Deep reinforcement learning Real-time systems network function virtualization Numerical models

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-based Virtual network function Placement Approach in NFV-enabled networks

A Deep Learning-based Virtual Network Function Placement App...

引用

IEEE Conference on Wireless Communications and networking

作者： Yi Yue Shiding Sun Xiongyan Tang Zhiyan Zhang Wencong Yang China Unicom Research Institute Beijing China National Engineering Research Center of Next Generation Internet Broadband Service Application Beijing China School of Electrical Engineering Zhengzhou University Zhengzhou China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

The emergence of Software-Defined networks (SDN) and network function virtualization (NFV) has made Service function Chain (SFC) a popular method for delivering network services. This innovative computing and networking paradigm allows Virtual network functions (VNFs) to be cost-effectively deployed on a network of physical equipment flexibly and elastically. Traffic can be directed as needed by linking VNFs as an SFC. However, the current algorithms for VNF placement computation and traffic steering in SFC are often complex, unscalable, and time-consuming. This paper investigates the VNF placement and SFC chaining problem in NFV-enabled networks. To obtain the VNF placement solution that maximizes network resource utilization, we formulate the problem as a Binary Integer Programming (BIP) model. Additionally, we introduce a novel Deep Learning-based VNF Placement Algorithm (DLVPA) that uses an intelligent node selection network to place VNFs for SFC requests. Performance evaluations demonstrate that DLVPA can effectively improve network resource utilization and achieve high solution computation time efficiency.

关键词： Performance evaluation Integer programming Deep learning Service function chaining Computational modeling network function virtualization Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Tracing the Progression: networking Applications From Conventional Methods to Incremental AI/ML Integration

Tracing the Progression: Networking Applications From Conven...

引用

Communication, Computer Sciences and Engineering (IC3SE), International Conference on

作者： Sushma Singh Varsha Rawat Dolly Sharma Department of Computer Science & Engineering Amity University Noida Uttar Pradesh India

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

The swift progression of networking technologies and the escalating intricacy of contemporary network environments have stimulated a burgeoning interest in utilizing advanced techniques to tackle various networking hurdles. This paper offers an overview of the evolution of applications within networking, tracing the progression of fundamental technologies, methodologies, and approaches over time. Through an examination of existing literature, we scrutinize pivotal works, recent progressions, and emerging patterns in the field, encompassing areas such as network optimization, anomaly detection, security, and automation. Our observations underscore the profound impact of these techniques on networking, facilitating more effective utilization of resources, improved security measures, and heightened adaptability to fluctuating network dynamics. By exploring ongoing trends and deliberating on future avenues of research, this paper furnishes insights into the current landscape of applications within networking and provides guidance for researchers and professionals endeavouring to navigate the complexities of contemporary networking environments.

关键词： Automation Scalability Routing Routing protocols network function virtualization Security Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Intelligent optimization of computing task management in an Edge environment

Intelligent optimization of computing task management in an ...

引用

International Conference on Pattern Analysis and Intelligent Systems (PAIS)

作者： Amira Cheriet Tahar Mekhaznia Department of Computer Science Laboratory of Mathematics Informatics and Systems (LAMIS) Echahid Cheikh Larbi Tebessi University Tebessa Algeria

ISBN: (数字)9798350350265

ISBN: (纸本)9798350350272

The advent of Mobile Edge Computing (MEC) offers significant benefits in terms of reduced latency and improved throughput for distributed applications and services. However, the integration of streaming services in these frameworks faces major challenges, particularly in terms of security, due to computational and processing limitations. In this context where resources are deployed as close as possible to the edge network, guaranteeing streaming security poses serious challenges. The restricted computing capabilities of edge nodes make it difficult to perform complex security tasks while maintaining acceptable performance for real-time streaming. To address these challenges, distributed solutions leveraging network functions virtualization (NFV) present themselves as promising options. In this paper, we aim to propose a distributed management solution leveraging NFV capabilities to improve the management of security task execution for streaming, while preserving overall performance. This solution is based on a process of allocation and orchestration of resources for security policies, using NFV Orchestrator (NFVO) nodes. In the evaluation phase, the proposed solution demonstrates that the NFVO-based allocation model demonstrated better performance compared to priority-based and heuristic allocation models.

关键词： Multi-access edge computing Computational modeling Refining Throughput Real-time systems network function virtualization Security

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：