检索结果-内蒙古大学图书馆

GraphNET: Graph Neural Networks for routing optimization in Software Defined Networks

COMPUTER COMMUNICATIONS 2021年 178卷 169-182页

作者： Swaminathan, Avinash Chaba, Mridul Sharma, Deepak Kumar Ghosh, Uttam Netaji Subhas Univ Technol Dept Informat Technol New Delhi 110078 India Vanderbilt Univ Dept EECS Nashville TN USA

In this paper, a graph neural net-based routing algorithm is designed which leverages global information from controller of a software-defined network to predict optimal path with minimum average delay between source and destination nodes in software-defined networks. Graph nets are used because of their generalization capability which allows the routing algorithm to scale across varying topologies, traffic schemes and changing conditions. A deep reinforcement learning framework is developed to train the Graph Neural Networks using prioritized experience replay from the experiences learnt by the controllers. The algorithm is tested on various small and large topologies in terms of packets successfully routed and average packet delay time. Experiments are performed to check robustness of routing algorithms to changes in network structure and effects of varying hyperparameters. The proposed algorithm shows impressive results when compared to q-routing and shortest path routing algorithm in terms of above experiments and is robust to varying graphical structure of the network.

关键词： Deep Reinforcement Learning Deep Q-learning Graph Neural Networks Q-table routing algorithm routing optimization Software-Defined Networking

来源：评论

学校读者我要写书评

暂无评论

3D path planning, routing algorithms and routing protocols for unmanned air vehicles: a review

引用

AIRCRAFT ENGINEERING AND AEROSPACE TECHNOLOGY 2019年第9期91卷 1245-1255页

作者： Ben Amarat, Samia Zong, Peng Nanjing Univ Aeronaut & Astronaut Coll Elect & Informat Engn Nanjing Jiangsu Peoples R China Nanjing Univ Aeronaut & Astronaut Aeronaut Coll Nanjing Jiangsu Peoples R China

Purpose This paper aims to present a comprehensive review in major research areas of unmanned air vehicles (UAVs) navigation, i.e. three degree-of-freedom (3D) path planning, routing algorithm and routing protocols. The paper is further aimed to provide a meaningful comparison among these algorithms and methods and also intend to find the best ones for a particular application. Design/methodology/approach The major UAV navigation research areas are further classified into different categories based on methods and models. Each category is discussed in detail with updated research work done in that very domain. Performance evaluation criteria are defined separately for each category. Based on these criteria and research challenges, research questions are also proposed in this work and answered in discussion according to the presented literature review. Findings The research has found that conventional and node-based algorithms are a popular choice for path planning. Similarly, the graph-based methods are preferred for route planning and hybrid routing protocols are proved better in providing performance. The research has also found promising areas for future research directions, i.e. critical link method for UAV path planning and queuing theory as a routing algorithm for large UAV networks. Originality/value The proposed work is a first attempt to provide a comprehensive study on all research aspects of UAV navigation. In addition, a comparison of these methods, algorithms and techniques based on standard performance criteria is also presented the very first time.

关键词： UAVs routing algorithm 3D path planning algorithm routing protocol

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Multi-Criteria routing algorithm Based in Centrality Measures for WSNs

A Dynamic Multi-Criteria Routing Algorithm Based in Centrali...

引用

3rd IEEE International Colloquium on Information Science and Technology (CIST)

作者： El Hajji, Fouad Leghris, Charekaoui Douzi, Khadija FST Lab LM BP 146 Mohammadia 20650 Morocco

ISBN: (纸本)9781479959792

The challenges posed by the deployment and routing in sensor networks, are a superset of those found in wireless ad hoc networks. An example of these specific requirements is the limited energy supply and batteries which usually irreplaceable and not rechargeable. In order to maximize the lifetime of the network, the protocols need to be designed from the beginning with the objective to manage efficiently many characteristics and requirements like fault tolerance, scalability, production costs and others. In this paper, we present our new adaptive multi-criteria routing algorithm. Our approach provides a routing mechanism, which considers the best path based on the evaluation of the topological metrics (centrality measures) of neighbouring nodes, according to an automatically varying criteria set. These criteria are controlled and supervised dynamically by the root node (The Sink). In response to changes in the network state, criteria and application-defined goals, the best path between each node and the Sink will be called.

关键词： Wireless Sensor Networks Centrality Measures Multi-Criteria routing algorithm Network Lifetime

来源：评论

学校读者我要写书评

暂无评论

A joint and dynamic routing approach to connected vehicles via LEO constellation satellite networks

引用

WIRELESS NETWORKS 2021年 1-13页

作者： Wang, Zhihao Zhang, Weijiong Liu, Bo Jiang, Dingde Wang, Feng Zhang, Jingyang Univ Elect Sci & Technol China Control Sci & Engn Sch Aeronaut & Astronaut Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Aircraft Swarm Intelligent Sensing & Cooperat Con Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Guidance Nav & Control Chengdu 611731 Peoples R China Shanghai Electromech Engn Inst Shanghai 201109 Peoples R China

The rapid development of the Internet of vehicles and the sudden urban traffic conditions bring increasing load pressure on the ground communication network. To solve this problem, in this paper we propose a joint and dynamic routing approach for connected vehicles in Low Earth Orbit (LEO) constellation satellite networks. Firstly, to realize global path planning service, the global situational awareness is conducted by jointing the satellite to transferee the acquired data to the control center which makes the initial route then. We employ the shortest-path algorithm and the ant colony optimization to jointly obtains the optimal end-to-end multi-hop path of the transmission. The joint and dynamic routing scheme in LEO network makes up for the shortcoming of ground communications. Simulation results show that the proposed routing method for connected vehicle networks in this paper is feasible and promising.

关键词： LEO constellation satellite Internet of vehicles Route planning routing algorithm Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Automatic design system for generating routing layout of tubes, hoses, and cable harnesses in a commercial truck

引用

JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING 2021年第4期8卷 1098-1114页

作者： Kim, Saekyeol Kim, Shinyu Choi, Taeheok Kwon, Taejoon Lee, Tae Hee Lee, Kwangrae Hanyang Univ BK21 Four Educ & Res Program Automot Software Con Seoul 04763 South Korea Hanyang Univ Dept Automot Engn Seoul 04763 South Korea Hyundai Motor Co Commercial Vehicle Engn Data Management Team 150 Hyundaiyeonguso Ro Hwaseong Si 18280 Gyeonggi Do South Korea

Although many routing algorithms have been developed, it is difficult for designers in the automotive industry to adopt them because of the complicated preliminary steps that are required. This study presents a systematic framework for generating the routing layout of the tubes, hoses, and cable harnesses in a commercial truck. The routing layout design problem in a commercial truck is analysed and defined. For routing operations, a sequential graph-based routing algorithm is employed to rapidly provide a routing solution. Because a reference routing layout design does not exist in most engineering problems, a cell-based genetic algorithm combined with a modified maze algorithm is employed to generate a reference design. To consider the clamping condition of the routing components, a new fitness function in the genetic algorithm is implemented. The numerical study shows that the proposed routing algorithm provides a better reference routing layout design than the conventional algorithm. The proposed automatic design system was applied to the routing layout design problem of a commercial truck. It was demonstrated that the proposed framework satisfies all industrial practitioners' functional requirements and provides a systematic method of solving the routing layout design problem, considering all its characteristics.

关键词： automatic design system commercial truck Dijkstra's algorithm genetic algorithm routing layout design routing algorithm

来源：评论

学校读者我要写书评

暂无评论

MOLM: Alleviating Congestion through Multi-Objective Simulated Annealing-Based Load Balancing routing in LEO Satellite Networks

引用

FUTURE INTERNET 2024年第4期16卷 109页

作者： Zhou, Yihu Chen, Haiming Dou, Zhibin Ningbo Univ Fac Elect Engn & Comp Sci Dept Comp Sci Ningbo 315211 Peoples R China China Elect Technol Grp Corp Res Inst 54 Shijiazhuang 050081 Peoples R China

In satellite networks, existing congestion resolution methods do not consider the predictability and stability of paths, leading to frequent path switches and high maintenance costs. In this regard, we propose a novel congestion resolution approach, named MOLM, which introduces a continuous neighbor set during path updates. This set includes nodes capable of establishing sustainable connections with the predecessors and successors of congested nodes. Combined with a multi-objective simulated annealing framework, MOLM iteratively derives an optimal selection from this set to replace congested nodes. Additionally, we employ a Fast Reroute mechanism based on backup paths (FRR-BP) to address node failures. The simulation results indicate that the optimal node endows the new path with optimal path stability and path latency.

关键词： satellite internet routing algorithm path stability latency simulation experiments

来源：评论

学校读者我要写书评

暂无评论

FleX: A Flex Interconnected HPC System With Stochastic Load Balancing Scheme

引用

IEEE ACCESS 2022年 10卷 37164-37180页

作者： Jeon, Minsu Joo, Kyung-No Kim, Taewoo Kim, Seonghwan Youn, Chan-Hyun Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea

We propose a new low-diameter interconnection network called FleX, which offers high flexibility when installing interconnections in a HPC system. FleX consists of multiple layers with only connections between neighboring layers and not within each layer. These structural properties make it easy to achieve a low diameter with regardless of the scale. The cross-like connections between the adjacent layers in FleX impart various alternative minimal paths, allowing FleX to have high resiliency and a wide bisection width. We also discuss the minimal routing scheme and a stochastic load balancing scheme (LBR) for the proposed interconnection network. Through cycle-based simulations, the performance of FleX is evaluated, and the cost and power consumption analyses in comparison with other interconnection networks are also conducted. We verify that FleX has high configuration flexibility with regard to cost and performance, and also provides low latency and high saturation throughput with the same cost over the legacy interconnection networks for the HPC system. Moreover, being synergied with the proposing LBR, we also verify that FleX can expand its saturation throughput further while only sacrificing the latency slightly.

关键词： Flexible printed circuits Multiprocessor interconnection Costs Topology routing Network topology Throughput Network topology parallel computing system routing algorithm

来源：评论

学校读者我要写书评

暂无评论

Simultaneous improvement of multiple transportation performances on link-coupled networks by global dynamic routing

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2023年 616卷

作者： Yang, Chao Chen, Zhuoran Qian, Jianghai Han, Dingding Zhao, Kaidi Fudan Univ Sch Informat Sci & Technol Shanghai 200233 Peoples R China Shanghai Univ Elect Power Sch Math & Phys Shanghai 201306 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China

The interconnected networks are facing with critical congestion issue due to the rapid growth of the traffic and the information on the links with limited capacity. We show that the traditional routing strategies are generally confronted with a tradeoff between the network capacity and the link usage when applying to the link-coupled network. To take a step to the issue, we propose a global dynamic routing (GDR) strategy that can simultaneously achieve multiple improvement of the transport performance with acceptable computational complexity at the cost of the average arrival time. Further analysis indicates the improvement is related to the nontrivial load distribution resulting from GDR. More surprisingly, the simulation experiments suggest our strategy GDR can suppress the occurrence of Braess-like paradox, which is a long-standing problem in transportation.

关键词： Complex network routing algorithm Global dynamic routing Braess paradox Transportation dynamics routing

来源：评论

学校读者我要写书评

暂无评论

Rethinking LEO Mega-Constellation routing to Provide Fast Internet Access Services

引用

SENSORS 2023年第6期23卷 3207-3207页

作者： Yang, Zijian Tian, Feng Jin, Jifeng Liu, Huijie Chinese Acad Sci Innovat Acad Microsatellites Shanghai 201203 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

In the realm of providing space-based internet access services, utilizing large-scale low Earth orbit (LEO) satellite networks have emerged as a promising solution for bridging the digital divide and connecting previously unconnected regions. The deployment of LEO satellites can augment terrestrial networks, with increased efficiency and reduced costs. However, as the size of LEO constellations continues to grow, the routing algorithm design of such networks faces numerous challenges. In this study, we present a novel routing algorithm, designated as Internet Fast Access routing (IFAR), aimed at facilitating faster internet access for users. The algorithm consists of two main components. Firstly, we develop a formal model that calculates the minimum number of hops between any two satellites in the Walker-Delta constellation, along with the corresponding forwarding direction from source to destination. Then, a linear programming is formulated, to match each satellite to the visible satellite on the ground. Upon receipt of user data, each satellite then forwards the data only to the set of visible satellites that correspond to its own satellite. To validate the efficacy of IFAR, we conduct extensive simulation work, and the experimental results showcase the potential of IFAR to enhance the routing capabilities of LEO satellite networks and improve the overall quality of space-based internet access services.

关键词： LEO mega-constellation routing algorithm space communications satellite neworks linear programming

来源：评论

学校读者我要写书评

暂无评论

Emerging QoS Strategies: A Comprehensive Overview of Clustering Techniques in IoT-Equipped WSNS

Emerging QoS Strategies: A Comprehensive Overview of Cluster...

引用

2023 International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2023

作者： Singh, Sonia Gupta, Neha Manav Rachna International Institute of Research and Studies School of Computer Applications Haryana Faridabad India

ISBN: (纸本)9798350344387

The Internet of Things (IoT) with Wireless Sensor Networks (WSN) is a collection of mechanical nodes known as sensors and actuators. The actuators and sensors are connected to each other with restricted battery life. Sensor networks begin to deplete their energy after installation through various activities such as detection, transmission, and aggregation during the transmission of data. Several energy-efficient solutions were developed to extend the lifespan of networks. One of the solutions to this problem is Clustering that plays a crucial function in reducing transmission energy needs. One of the key challenges with large-scale Internet of Things (IoT) is the lack of an efficient routing protocol that can manage thousands of devices while also providing a low-power forwarding mechanism for massive amounts of data. The present paper discuss approaches and protocols are used by various clustering algorithms like Low Energy Adaptive Clustering Hierarchy (LEACH), Fuzzy C-Means (FCM), Hybrid Energy Efficient Distributed (HEED), Fruit Fly Optimization algorithm (FFOA) etc. The paper proposes the need for an efficient routing protocol to manage thousands of devices with low power forwarding mechanisms on a big scale. © 2023 IEEE.

关键词： Clustering Efficiency Energy Network-Lifespan Optimization routing algorithm Sensor Nodes

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：