一种基于模糊逻辑的主动队列管理算法

主动队列管理 (ActiveQueueManagement,AQM)技术作为Internet拥塞控制的一种有效方法 ,对于提高In ternet的服务质量具有十分重要的作用 .本文根据TCP拥塞控制算法基于数据包丢失的窗口变化机制 ,设计了一种基于模糊逻辑的主动队列管理算法 .该算法依据路由器中队列长度的变化情况 ,根据一定的模糊自校正原则来调整数据包的丢弃概率 ,从而使路由器中的队列长度稳定在参考值附近 .仿真结果表明该算法不但十分有效 ,而且对不同的网络状况具有很好的适应能力 .     

基于BP神经网络的温度模糊PID控制器设计

根据BP神经网络对温度控制的要求设计出一种模糊PID控制器,采用误差和误差变化率作为模糊PID控制器的输入,PID参数作为模糊PID控制器的输出,使用一组模糊规则实现对PID参数的在线优化调节。采用Simulink图形化工具平台对模糊PID控制器和传统的PID控制器进行建模和仿真,结果表明和传统PID控制器相比,模糊PID控制器性能优良,使系统响应速度加快,超调减小。     

基于T-S模糊神经网络的ATM网络拥塞控制

本文充分考虑了模糊神经网络的学习功能，提出了利用T－S模糊神经网络算法对ATM网络进行拥塞控制的方案。仿真结果表明，该方法改善了网络对拥塞的实时处理能力，又增加了网络资源的利用率。     

动态权重调整RED

IETF推荐RED(Random Early Detection)作为下一代Internet路由器的拥塞控制算法.但RED中平均队列长度对实际队列变化反应较慢,导致出现拥塞的时间增加,丢包增多,本文在现有RED算法的基础上通过改进RED算法的平均队列长度计算,使用平均队列长度的均值,判断拥塞的发生和结束,动态调整权重,提高RED对拥塞发生和拥塞结束的反应速度.仿真结果表明算法减少了拥塞时间,能够维持较低的实际队列长度,进而减少了数据包排队时间.     

动态权重RED网关

随着网络流量的增加,拥塞控制的重要性日益突出,尤其是链路拥塞控制。IETF推荐RED(Random Early Detection)作为下一代Internet路由器的拥塞控制算法。该文在分析了RED的优点和缺点后,在现在RED算法的基础上通过改进RED算法的平均队列长度计算,使用平均队列长度的均值,判断拥塞的发生和结束,动态调整权重,提高RED对拥塞发生和拥塞结束的反应速度,缩短拥塞时间,维持较低的实际队列长度。最后用仿真验证了该方法。     

一种基于模糊逻辑的主动队伍管理算法

主动队列管理（AciiveQueue Management,AQM)技术作为Internet拥塞控制的一种有效方法，对于提高Internet的服务质量具有十分重要的作用，本文根据TCP拥塞控制算法基于数据包丢失的窗口变化机制，设计了一种基于模糊逻辑的主动队伍管理算法，该算法依据路由器中队列长度的变化情况，根据一定的模糊自校正原则来调整数据包的丢弃概率，从而使路由器中的队列长度稳定在参考值附近，仿真结果表明该算法不但十分有效，而且对不同的网络状况具有很好的适应能力。     

互联网中的不确定时滞全局滑模AQM算法

为解决互联网中的拥塞现象,基于全局滑模理论,提出了一种主动队列管理算法.将互联网中的不确定因素等效为拥塞控制模型的参数摄动,并考虑到时变时滞因素,利用线性矩阵不等式设计了渐近稳定的全局滑模面,使系统运动的全程都是滑动模态,显著提高了系统的鲁棒性.并且所设计的控制器能够有效降低路由器中队列长度的稳态振荡.仿真对比表明,所提出的算法具有更高的稳定性和鲁棒性,能够适应复杂多变的互联网环境.     

基于ATM流量控制的模糊逻辑控制

在概述拥塞控制基本思想和方法的基础上,针对ATM的流量控制提出了一种模糊逻辑控制的方法。该模糊逻辑控制器主要由:FCAC和IUPC两部分组成。FCAC评估所有输入连接所需要的带宽,以判断是否接受连接请求。IUPC监管和规范受FCAC容许连接的输入流量。为了充分利用统计复用增益,IUPC还采用了一种网络拥塞内反馈机制来判断是丢弃还是标记违约信元。     

基于遗传算法的模糊神经网络控制技术研究

提出了一种基于去模糊优化的模糊神经网络控制器及模糊神经网络的遗传学习算法.利用遗传算法优化包含控制器性能的指标来离线寻找最优的模糊神经网络控制器结构和参数,经过遗传算法训练的模糊神经网络控制器被接入模糊神经网络智能控制系统中.仿真结果表明,利用此方法实现的控制,系统的控制精度高,超调量小,鲁棒性能很强,获得了良好的控制效果.     

QoS体系中的主动队列管理算法研究综述

随着Internet的迅速发展，服务质量(QoS)正成为当前研究的热点之一。为了达到QoS的性能指标，拥塞控制作为一个很重要的方面在发挥着作用。主动队列管理是实现拥塞控制的重要手段之一，长期以来一直受到广泛的关注，基于不同理论的各种主动队列管理的算法也随之涌现。这些队列管理算法在一定程度上完成网络拥塞控制的任务，但是也不同程度地在公平性、可扩展性以及算法的复杂度上存在缺陷。本文通过对目前几种主要队列管理算法的实现原理的分析，考察了这些队列管理算法的优点和其可能存在的一些问题，而这些可能存在的问题也是下一步研究的起点。     

A fuzzy-logic control algorithm for active Queue Management in IP networks

Active Queue Management （AQM） is an active research area in the Internet community. Random Early Detection （RED） is a typical AQM algorithm, but it is known that it is difficult to configure its parameters and its average queue length is closely related to the load level. This paper proposes an effective fuzzy congestion control algorithm based on fuzzy logic which uses the predominance of fuzzy logic to deal with uncertain events. The main advantage of this new congestion control algorithm is that it discards the packet dropping mechanism of RED, and calculates packet loss according to a preconfigured fuzzy logic by using the queue length and the buffer usage ratio. Theoretical analysis and Network Simulator （NS） simulation results show that the proposed algorithm achieves more throughput and more stable queue length than traditional schemes. It really improves a router＇s ability in network congestion control in IP network.     

An evolutionary management scheme in high-performance packet switches

This paper deals with a novel buffer management scheme based on the combination of evolutionary computing and fuzzy logic for shared-memory packet switches. The philosophy behind it is adaptation of the threshold for each logical output queue to the real traffic conditions by means of a system of fuzzy inferences. The optimal fuzzy system is achieved using a systematic methodology based on Genetic Algorithms for membership-function selecting and tuning. This methodology approach allows the fuzzy system parameters to be automatically derived when the switch parameters vary, offering a high degree of scalability to the fuzzy control system. Its performance is close to that of the push-out mechanism, which can be considered ideal from a performance viewpoint, and at any rate much better than that of threshold schemes based on conventional logic. In addition, the fuzzy threshold scheme is simple to implement, unlike the push-out mechanism which is not practically feasible in high-speed switches due to the amount of time required for computation, and above all inexpensive when implemented using current standard technology.     

传感器网络拥塞避免与控制的模糊AQM算法

传感器网络节点通信能力有限,当数据到达速率持续超过节点转发能力时网络会发生拥塞;传感器网络是任务型网络,对不同优先级的信息具有不同的服务质量要求.针对传感器网络信息传输的上述特性,提出了一种新的拥塞避免与控制算法FAQM（Fuzzy Active Queue Management）.该算法在综合考虑数据包的随机指数标记概率和优先级权值的基础上,建立了模糊逻辑推理系统,并以数据包丢弃因子作为参量来实现数据流的智能调控.NS2仿真实验结果表明：FAQM算法能减少高优先级数据包的丢弃率和节点间链路的时延,稳定节点队列长度,在有效避免与控制拥塞网络的同时提升网络整体QoS（Quality of Service）性能.     

Service-aware based fuzzy admission control scheme in multi-service networks

Multi-service aggregated transmission is the direction of IP network. Providing different Quality of Service (QoS) assurance for different services has become a crucial problem in future network. Admission control is a vital function for multi-service IP network. This paper proposes a novel fuzzy admission control scheme based on coarse granularity service-aware technique. Different service has discriminative sensitivity to the same QoS characteristic parameter in general. The traffic class can be perceived by the service request parameter and the proposed QoS function. And requirements of dif- ferent applications can be met by maintaining the life parameter. From simulation results, the proposed scheme shows a better QoS provisioning than those traditional fuzzy logic based methods under the same admission probability.     

Fuzzy Logic QoS Dynamic Source Routing for Mobile Ad Hoc Networks

Considering the characters of dynamic topology and the imprecise state information in mobile ad hoc network,we propose a Fuzzy Logic QoS Dynamic Source Routing(FLQDSR)algorithm based on Dynamic Source Routing(DSR)protocol while adopting fuzzy logic to select the appropriate QoS routing in multiple paths which are searched in parallel.This scheme considers not only the bandwidth and end-to-end delay of routing,but also the cost of the path.On the otherhand the merit of using fuzzy logic is that it can be implemented by hardware.This makes the realization of the schemeeasier and faster.However our algorithm is based on DSR,the maximal hop count should be less than 10,i.e.,the scaleof mobile ad hoc network should not be very large.Simulation results show that FLQDSR can tolerate a high degree of in-formation imprecision by adding the fuzzy logic module which integrates the QoS requirements of application and the rout-ing QoS parameters to determine the most qualified one in every node.     

一种新的基于网络丢包率的主动队列管理策略

提出了一种新的基于网络丢包率的动态自适应的主动队列管理的改进算法。该算法首先用早期网络的丢包率标记到达的数据包,并作为数据包的丢弃概率。这样使得到达数据包的丢弃概率逼近当前实际网络的丢包率,然后经过自适应调整丢弃概率使得缓冲队列长度保持在一定范围内。通过NS仿真实验表明了该算法可以很好的控制队列长度,降低延迟抖动。     

A Dynamic Adaptation Mechanism for Traffic Conditions in Wireless Sensor Network

As overall network traffic pursue to expand, a lot of low-power medium access control protocols have been proposed to deal with burst traffic in wireless sensor network. Although most of them provide low throughput but do not well optimize the energy consumption. In this paper, we propose a new hybrid carrier sense multiple access with collision avoidance (CSMA/CA) and time division multiple access (TDMA) protocol that arranges nodes into two categories of priority according to their traffic rate and data transmission delay. Nodes that have continuous data should send its data during the contention free period, those one will be classified as low priority and its data will be scheduling using TDMA. Others nodes who have a random data should transmit it immediately during the contention access period (CAP) using a fuzzy logic algorithm, based on their queue length and implemented in the CSMA/CA algorithm. Therefore, the proposed scheme dynamically changes the CAP length to ensure that nodes can complete its transaction during the same super-frame. Simulation results are done using the network simulator tools (NS-2) and have improved good efficiency regarding the IEEE 802.15.4 standard. The mechanism has improved the energy consumption, minimised the packet loss probability, increased the throughput variation in the network and also minimised the average end to end delay.     

A fuzzy logic based buffer management scheme with traffic differentiation support for delay tolerant networks

Delay tolerant networks (DTNs) are an emerging class of wireless networks which enable data delivery even in the absence of end-to-end connectivity. Under these circumstances, message replication may be applied to increase the delivery ratio. The requirement of long term storage and message replication puts a burden on network resources such as buffer and bandwidth. Buffer management is an important issue which greatly affects the performance of routing protocols in DTNs. Two main issues in buffer management are drop decision when buffer overflow occurs and scheduling decision when a transmission opportunity arises. The objective of this paper is to propose an enhancement to the Custom Service Time Scheduling traffic differentiation scheme by integrating it with a fuzzy based buffer ranking mechanism based on three message properties, namely, number of replicas, message size and remaining time-to-live. It uses fuzzy logic to determine outgoing message order and to decide which messages should be discarded within each traffic class queue. Results of simulation study show that the proposed fuzzy logic-based traffic differentiation scheme achieves improved delivery performance over existing traffic differentiation scheme for DTNs.     

A gradient‐based binary feedback scheme for congestion control in computer networks

In this paper, we propose a binary feedback scheme for congestion control in computer networks using a gradient‐based mechanism which employs neural network modelling of the system dynamics. The optimal direction for rate adjustment at the source is based on a single bit feedback signal which depends upon the sign of the sensitivity of the system performance index with respect to queue input rate. The paper presents the scheme and the analysis that went into the choice of the various decision mechanisms. Simulation results are presented to show the performance of the gradient based technique as compared to the conventional queue‐based approach. Copyright © 2000 John Wiley & Sons, Ltd.