检索结果-内蒙古大学图书馆

RL-routing: An SDN routing algorithm Based on Deep Reinforcement Learning

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2020年第4期7卷 3185-3199页

作者： Chen, Yi-Ren Rezapour, Amir Tzeng, Wen-Guey Tsai, Shi-Chun Natl Chiao Tung Univ Dept Comp Sci Hsinchu Taiwan

Communication networks are difficult to model and predict because they have become very sophisticated and dynamic. We develop a reinforcement learning routing algorithm (RL-routing) to solve a traffic engineering (TE) problem of SDN in terms of throughput and delay. RL-routing solves the TE problem via experience, instead of building an accurate mathematical model. We consider comprehensive network information for state representation and use one-to-many network configuration for routing choices. Our reward function, which uses network throughput and delay, is adjustable for optimizing either upward or downward network throughput. After appropriate training, the agent learns a policy that predicts future behavior of the underlying network and suggests better routing paths between switches. The simulation results show that RL-routing obtains higher rewards and enables a host to transfer a large file faster than Open Shortest Path First (OSPF) and Least Loaded (LL) routing algorithms on various network topologies. For example, on the NSFNet topology, the sum of rewards obtained by RL-routing is 119.30, whereas those of OSPF and LL are 106.59 and 74.76, respectively. The average transmission time for a 40GB file using RL-routing is 25.2 s. Those of OSPF and LL are 63 s and 53.4 s, respectively.

关键词： routing Throughput Delays Reinforcement learning Heuristic algorithms Network topology Control systems Cognitive sdn deep reinforcement learning routing algorithm software defined networks

来源：评论

学校读者我要写书评

暂无评论

ARAG: A routing algorithm Based on Incentive Mechanisms for DTN With Nodes' Selfishness

引用

IEEE ACCESS 2018年 6卷 29419-29425页

作者： Wang, Hezhe Wang, Huiqiang Guo, Fangfang Feng, Guangsheng Lv, Hongwu Harbin Engn Univ Coll Comp Sci & Technol Harbin 150001 Heilongjiang Peoples R China

A delay tolerant network (DTN) is a mobile ad hoc network with extremely limited network resources. When DTN is applied in the urban environment, nodes are not willing to consume their limited resources to forward messages for other nodes, or they prefer a relay node that encounters the destination node with a higher probability to forward messages for themselves owing to the characteristics of sociality and selfishness of nodes, which results in poor network performance. To address this issue, a routing algorithm based on incentive mechanisms was proposed in this paper, which is called ARAG. In the process of forwarding message, the algorithm determines the probability of messages received by relay nodes based on the resource consumption of the sender node. Simultaneously, when a source node generates a message, the threshold of copies is set based on the consumption of its resources, and the total number of the same message in the network will not exceed the threshold. Simulation results show that the algorithm is superior to the existing Epidemic algorithm, Prophet algorithm, and GTMEA algorithm in terms of the delivery ratio, the average delay, and network overhead.

关键词： DTN routing algorithm buffer management incentive mechanism

来源：评论

学校读者我要写书评

暂无评论

A Reliable Energy-Efficient Multi-Level routing algorithm for Wireless Sensor Networks Using Fuzzy Petri Nets

引用

SENSORS 2011年第3期11卷 3381-3400页

作者： Yu, Zhenhua Fu, Xiao Cai, Yuanli Vuran, Mehmet C. AF Engn Univ Sch Telecommun Engn Xian 710077 Peoples R China Xi An Jiao Tong Univ Sch Elect & Informat Engn Xian 710049 Peoples R China Univ Nebraska Dept Comp Sci & Engn Cyber Phys Networking Lab Lincoln NE 68588 USA

A reliable energy-efficient multi-level routing algorithm in wireless sensor networks is proposed. The proposed algorithm considers the residual energy, number of the neighbors and centrality of each node for cluster formation, which is critical for well-balanced energy dissipation of the network. In the algorithm, aknowledge-based inference approach using fuzzy Petri nets is employed to select cluster heads, and then the fuzzy reasoning mechanism is used to compute the degree of reliability in the route sprouting tree from cluster heads to the base station. Finally, the most reliable route among the cluster heads can be constructed. The algorithm not only balances the energy load of each node but also provides global reliability for the whole network. Simulation results demonstrate that the proposed algorithm effectively prolongs the network lifetime and reduces the energy consumption.

关键词： wireless sensor networks routing algorithm clustering fuzzy Petri nets

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware routing algorithm for Wireless Sensor Networks with Optimal Relay Detecting

引用

WIRELESS PERSONAL COMMUNICATIONS 2018年第2期98卷 1701-1717页

作者： Li, Feng Wang, Li Zhejiang Univ Technol Coll Informat Engn 288 Liuhe Rd Hangzhou 310023 Zhejiang Peoples R China

Efficient and reliable routing plays a key role in wireless sensor networks in which routing design with regard to network availability and node lifetime needs to be deliberately considered. When multi-hop relay transmission is frequently applied to reduce a source node's energy consumption and improve network capacity, a key issue affecting the nodes' participation in the transmission is the problem of suitably determining the next hop in order to prolong each node's lifetime and to maintain the energy-balancing of the whole network. In this study, we propose an energy-aware routing scheme by taking the Cauchy operator, node's residual energy and routing distance into account. Based on Cauchy inequation, we achieve a relationship between the routing distance and the energy usage in the routing. By fixing a relay selection parameter and then identifying the next hop appropriately, we obtain a balancing energy-aware routing algorithm. Numerical results are provided to verify the lifetime and equilibrium of the energy distribution by comparing with them with those of a traditional approach.

关键词： Energy awareness routing algorithm Multi-hop transmission Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A DIRECT routing algorithm FOR THE BIT-REVERSAL PERMUTATION ON A SHUFFLE-EXCHANGE NETWORK

引用

INFORMATION PROCESSING LETTERS 1985年第5期21卷 259-268页

作者： BIRKHOFF, IJM Department of Computer Science University of Utrecht P.O. Box 80.012 3508 TA Utrecht The Netherlands

An algorithm is presented for routing the bit-reversal permutation on a shuffle-exchange interconnection network. The algorithm requires 2(log N)-1 stages of N inputs (N being a power of 2). The routing method is given by an explicit control matrix. Also, an adaptation of the bit-reversal algorithm is presented that calculates the control bits online during the execution of the algorithm. The control bits of the switches are given in a control matrix or may be computed during the execution of the algorithm. As a result, the fast Fourier transform algorithm, including the unscrambling of the results, can be calculated in 3(log N)-1 stages on the shuffle-exchange network, and the indirect binary n-cube can be simulated in 5(log N)-1 shuffle-exchange stages.

关键词： Perfect shuffle bit-reversal permutation interconnection networks shuffle-exchange routing algorithm control matrix

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of routing algorithm with energy efficiency based on clustering and backwards in IoT system

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2023年第4期44卷 6843-6853页

作者： Zhang Zhigang Lu Chunmeng Lu Bei Jiaozuo Univ Coll Artificial Intelligence Jiaozuo 454000 Henan Peoples R China

One of the biggest challenges for Internet of Things (IoT) systems is traffic congestion in large networks. For this reason, the bandwidth should be increased in such systems. In addition, the issue of routing is raised in sending packets from the origin to the destination. Therefore, if there are many IoT devices in the network, it will increase the traffic, which makes faultless routing important in these networks. In this paper, a novel routing method based on routing Protocol for Low-Power (RPL) is presented to minimize the energy consumption of the Internet of Things. Using the backward method based on the A* method to reduce energy consumption in a large graph, promising nodes are selected. A coordinate node is used to manage packets and transfer them. The selection of the coordinator node helps to receive packets with less energy and less delay from its neighbors, and the head node selects the best coordinator node with the shortest distance and the highest residual energy. The proposed method improves the energy consumption criteria, the delay between nodes, and the network overhead criterion by considering the estimated energy to the destination with the A* method.

关键词： routing algorithm energy consumption delay internet of things

来源：评论

学校读者我要写书评

暂无评论

RL-Shield: Mitigating Target Link-Flooding Attacks Using SDN and Deep Reinforcement Learning routing algorithm

引用

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 2022年第6期19卷 4052-4067页

作者： Rezapour, Amir Tzeng, Wen-Guey Natl Yang Ming Chiao Tung Univ Dept Comp Sci Taipei 30010 Taiwan

Link-flooding attacks (LFAs) are a new type of distributed denial-of-service (DDoS) attacks that can substantially damage network connectivity. LFAs flows are seemingly legitimate at the origin. But their cumulative volume at critical links causes congestion. We propose RL-Shield, a reinforcement learning based defense system against LFAs. It mitigates LFAs and, at the same time, effectively forwards data traffic in the network. RL-Shield introduces a new detection algorithm for monitoring IP behaviors using the Dirichlet distribution and Bayesian statistics. It monitors the interplay of LFAs and traffic engineering and identifies source IPs that persistently react to re-routing events. The detection algorithm controls two reinforcement learning based routing algorithms that use a hop-by-hop technique to connect related node *** evaluate RL-Shield on various network topologies by simulating several attack strategies. The simulation results demonstrate the effectiveness and high-accuracy of RL-Shield.

关键词： routing Reinforcement learning Delays Throughput Monitoring Bandwidth Network topology DDoS Link-flooding attacks routing algorithm software defined networks deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A routing algorithm Based on SDN for On-Board Switching Networks

引用

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2017年第5期33卷 1255-1266页

作者： Yu, Xiao Lei, Wei-Min Song, Li Zhang, Wei Northeastern Univ Sch Comp Sci & Engn Shenyang 110819 Liaoning Peoples R China Troop 68026 PLA Lanzhou 730020 Gansu Peoples R China

A new routing algorithm for MPLS (Multi-Protocol Label Switching, MPLS) traffic engineering in SDN-based (Software Defined Network, SDN) satellite switching networks is presented in this paper. LSP (Label Switched Path, LSP) link initial weights are defined as composite functions consisting of link transmission delay, residual bandwidth and BER (Bit Error Rate, BER). Based upon ISL (Inter-Satellite Link, ISL) handoff, LSP link stability function is defined. Next, LSP link criticality function is defined by the frequency of ISL used to establish LSP. The LSP link selection probability function is designed based on the three functions mentioned above. The proposed routing algorithm is able to implement dynamic routing from the source to the destination of multiple LSPs, which can balance the load of network traffic. Some numerical simulations are made to test the validity and capability of the proposed routing algorithm.

关键词： SDN satellite communication networks on-board switching routing algorithm MPLS

来源：评论

学校读者我要写书评

暂无评论

A QoS-Guaranteed Coverage Precedence routing algorithm for Wireless Sensor Networks

引用

SENSORS 2011年第4期11卷 3418-3438页

作者： Jiang, Joe-Air Lin, Tzu-Shiang Chuang, Cheng-Long Chen, Chia-Pang Sun, Chin-Hong Juang, Jehn-Yih Lin, Jiun-Chuan Liang, Wei-Wen Natl Taiwan Univ Dept Bioind Mechatron Engn Taipei 106 Taiwan Natl Taiwan Univ Dept Geog Taipei 106 Taiwan Taiwan Geog Informat Syst Ctr Taipei 10092 Taiwan

For mission-critical applications of wireless sensor networks (WSNs) involving extensive battlefield surveillance, medical healthcare, etc., it is crucial to have low-power, new protocols, methodologies and structures for transferring data and information in a network with full sensing coverage capability for an extended working period. The upmost mission is to ensure that the network is fully functional providing reliable transmission of the sensed data without the risk of data loss. WSNs have been applied to various types of mission-critical applications. Coverage preservation is one of the most essential functions to guarantee quality of service (QoS) in WSNs. However, a tradeoff exists between sensing coverage and network lifetime due to the limited energy supplies of sensor nodes. In this study, we propose a routing protocol to accommodate both energy-balance and coverage-preservation for sensor nodes in WSNs. The energy consumption for radio transmissions and the residual energy over the network are taken into account when the proposed protocol determines an energy-efficient route for a packet. The simulation results demonstrate that the proposed protocol is able to increase the duration of the on-duty network and provide up to 98.3% and 85.7% of extra service time with 100% sensing coverage ratio comparing with LEACH and the LEACH-Coverage-U protocols, respectively.

关键词： quality of service (QoS) routing algorithm sensing coverage problem wireless sensor network (WSN)

来源：评论

学校读者我要写书评

暂无评论

West Antarctic balance calculations: Impact of flux-routing algorithm, smoothing algorithm and topography

引用

COMPUTERS & GEOSCIENCES 2006年第10期32卷 1780-1795页

作者： Le Brocq, Anne M. Payne, Antony J. Siegert, Martin J. Univ Bristol Sch Geog Sci Ctr Polar Observat & Modelling Bristol BS8 1SS Avon England

Balance flux and velocity calculations are important in understanding the large-scale dynamics of ice masses and their state of balance. However the grid-based (finite difference) nature of the current algorithms means that there is a variety of ways in which the balance flux and velocity can be calculated. The flux-routing algorithm, grid orientation and grid size all have an impact on the balance calculations. Previous work has relied on the assumption that the ice flow direction is orthogonal to the surface contours, with the surface having been smoothed to incorporate a representation of the longitudinal stresses within the ice. This assumption is a simplification of the gravitational driving stress equation, which relates the driving stress to the gradient of the surface slope and the ice thickness. Further, the common representation of longitudinal stresses using a fixed size smoothing filter is a simplification of the theoretical treatment of longitudinal stresses by Kamb, B., Echelmeyer, K.A. [1986. Stress-gradient coupling in glacier flow: 1. longitudinal averaging of the influence of ice thickness and surface slope. Journal of Glaciology 32 (111), 267-298]. This study investigates the sensitivity of the balance calculations to these issues, using the West Antarctic Ice Sheet as a case study. Significant differences in both ice stream margins and values of ice flux within them result from the algorithm choice, gridorientation and gridsize. The inclusion of a theoretically appropriate smoothing approach improves the coherence of the pattern of ice flow. The incorporation of gravitational driving stress has a small effect in comparison to practical issues such as the grid orientation and size. As higher resolution datasets (less than 5 km) become available for many ice masses, there is a temptation to calculate the balance flux using the same algorithms on the finer grids. The results shown in this study suggest that the type of algorithm most commonly used i

关键词： balance flux balance velocity West Antarctic ice sheet routing algorithm smoothing filter

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：