无线网络规划中短信业务分布预测方法

随着数据业务,特别是短信业务的迅速发展,现有的短信业务分布预测算法已经严重影响了无线网络规划的准确性.文章提出一种基于聚类分析和模拟退火的短信业务分布预测方法.根据电子地图、基站语音和短信业务统计数据,提取影响短信业务分布的相关属性,采用聚类分析将网络中基站进行分类,然后采用模拟退火算法计算得到不同类型基站中的短信日均业务密度值,从而实现对短信进行业务分布的预测.     

一种短信业务分布预测算法分析

随着移动通信短信业务的迅速发展,现有的短信业务分布预测算法已经无法满足需求。提出了一种基于聚类分析和模拟退火的短信业务分布预测算法。根据电子地图、基站语音和短信业务统计数据,提取影响短信业务分布的相关属性,采用聚类分析方法中的自组织映射(Self Organizing Map,SOM)方法和k-means算法,将网络中基站进行分类,然后采用模拟退火算法和最小二乘法计算得到不同类型基站中的不同地物的短信日均业务密度值,从而达到对短信进行业务分布预测的目的。通过实际基站短信业务统计数据的验证,该算法大幅提高了短信业务分布预测的准确度。     

RBF神经网络在视频业务建模及预测中的应用

ＡＴＭ技术在关键在于业务控制,能否有效地实施业务控制则取决于对业务特征的了解和预测能力。传统的解析方法对视频业务进行预测的局限性较为明显。本文采用径向基函数神经网络对视频业务进行建模和预测,并提出了分别采用ＬＢＧ算法和Ｈｅｓｔｅｎｅｓ奇异值解进行隐含层神经元中心选择和输出神经腱权值计算的改进方法。     

基于SAPSO算法优化Elman神经网络的话务量预测

文章提出一种模拟退火(SA)与粒子群优化(PSO)算法相结合的算法来优化Elman神经网络权值和阈值。当PSO处于停滞状态时,利用粒子群优化算法的全局寻优性质,以及SA能跳出局部最优解的特性,在搜索到的最优位置处用模拟退火算法继续寻找最优解,并对具有动态递归性能的Elman神经网络进行学习训练,这样就能对忙时话务量进行预测。结果表明,与传统Elman神经网络和PSO-Elman神经网络相比,基于模拟退火粒子群算法训练的神经网络具有更高的预测精度和良好的自适应性。     

基于LMBP神经网络的惯性器件故障预报方法研究

利用Levenberg-Marquardt(L-M)算法优化计算BP权值调整量,将L-M算法与传统的BP网络相结合开发出一种快速收敛的LMBP网络,并在此基础上提出了基于LMBP神经网络的时间序列预测方法。最后利用该方法对某惯性器件进行故障预报,通过仿真实验证明了该方法的有效性。     

一种改进的ELM及其在光伏发电上的应用

为了改善极限学习机(Extreme Learning Machine,ELM)收敛速度慢、预测精度不稳定、隐层神经元对网络参数敏感度低等缺点,文中提出了粒子群(Particle Swarm Optimization,PSO)并行模拟退火(Simulated Annealing,SA)优化ELM的算法(APSO-ELM)。该算法首先通过对ELM随机产生的初始权值和阈值进行优化,进化出较优解,然后对每组解进行模拟退火,从而提高算法摆脱局部极值点的能力,最后将优化退火后的解集,用来预测ELM的输出。算法仿真结果表明:改进的ELM可有效解决粒子群寻优过程易陷入局部最优的问题,其预测精度、收敛速度、隐层神经元的敏感度均优于其他常见ELM扩展算法。将改进的ELM应用在光伏发电输出功率预测上,可以预测光伏发电输出功率的变化规律,精度较高。     

基于序贯蒙特卡罗的非同步长码DS-CDMA信号扩频码及信息序列联合估计

针对多径信道环境下非同步长码DS-CDMA信号扩频码及信息序列等参数的联合估计问题,该文提出了基于序贯蒙特卡罗(SMC)的盲估计算法。该算法采用混合重要密度函数对联合后验分布模型进行抽样,并迭代计算重要性权值,以完成所需状态参量的估计。同时为了减少算法的计算量,在算法的实现过程中,先估计出各用户的扩频码,再对观测数据进行处理,从而修正原有的迭代步骤,提出一种修正的SMC算法。仿真结果验证了算法对多种情况的适应性,且在时变的多径信道环境下也能获得较好的估计性能。     

基于PSO-RBF神经网络的海战场电磁态势预测

针对海战场电磁态势的预测问题,提出一种基于改进粒子群(PSO)优化径向基函数(RBF)神经网络的海战场电磁态势预测方法。该方法使用自适应惯性权重、模拟退火法和遗传算法对常规的粒子群算法进行改进,提高算法的搜寻精度和速度,并采用改进粒子群算法优化RBF神经网络参数,提高网络的学习效率和预测精度。最后,对海战场电磁态势值之间的非线性映射关系进行仿真预测。实验结果表明,该方法可以有效地提高海战场电磁态势的预测精度,具有较好的适用性。     

光散射模型参量反演中的遗传模拟退火算法

为了研究遗传模拟退火算法在光散射模型参量反演中的迭代搜索性能问题,分别采用遗传模拟退火算法和单一遗传算法迭代搜索了几种介质的双向反射分布函数模型的相关参量。将两种算法的反演结果与在特定激光波长下的双向反射分布函数实验数据进行了对比,通过理论分析和实验验证,取得了两种算法所得到的拟合值,两种拟合值都与实验数据吻合得较好;同时比较了遗传模拟退火算法和单一遗传算法在迭代次数、计算时间和均方误差等之间的差异。结果表明,两种算法在不同介质表面双向反射分布函数模型参量反演时都可以得到满意的结果,且前者优化效果更优。这一结果对研究不同算法的迭代搜索性能是有帮助的。     

光散射模型参量反演中的遗传模拟退火算法

为了研究遗传模拟退火算法在光散射模型参量反演中的迭代搜索性能问题,分别采用遗传模拟退火算法和单一遗传算法迭代搜索了几种介质的双向反射分布函数模型的相关参量.将两种算法的反演结果与在特定激光波长下的双向反射分布函数实验数据进行了对比,通过理论分析和实验验证,取得了两种算法所得到的拟合值,两种拟合值都与实验数据吻合得较好;同时比较了遗传模拟退火算法和单一遗传算法在迭代次数、计算时间和均方误差等之间的差异.结果表明,两种算法在不同介质表面双向反射分布函数模型参量反演时都可以得到满意的结果,且前者优化效果更优.这一结果对研究不同算法的迭代搜索性能是有帮助的.     

基于Fisher的加权马尔可夫的话务预测

基于话务量数据的特性,提出基于加权马尔可夫的移动话务量预测模型。该模型具有要求的样本数量少,运算速度快,预测精度高,可检验等的特点。根据该模型的缺陷,应用模糊Fisher准则的有序聚类方法,可以对话务序列进行分类并建立分类标准,该方法克服了聚类有效性对样本空间分布的依赖并同时提高了算法的效率。仿真结果表明,在移动通信话务量预测中,该算法与其他方法相比较,运算速度快,准确度高。     

基于神经网络的城市交通流预测研究

 建立了一种基于神经网络的交通流量动态预测模型,分别采用BP神经网络和径向基网络(RBF)建立了预测模型,给出了数据预处理方法和预测模型评价指标.仿真结果表明该交通流量预测方法的有效性,结果分析得出径向基网络能够更加快速有效的进行城市交通流预测.     

因特网流量矩阵的流形结构

当前,流量矩阵已经被广泛应用于异常检测、流量预测、流量工程等领域,但是现有研究仅仅发现流量矩阵存在线性结构。为了寻找流量矩阵中可能存在的非线性结构,构建流量矩阵模型并从实际因特网骨干网Abilene中采集流量矩阵数据集,应用经典的流形学习算法进行实测数据分析,发现这些高维(81维或121维)的流量矩阵数据集实际上是嵌入的固有维度为5维的低维流形,且其受采样密度和噪声数据等各种因素的影响呈现出不同的结构。     

Queuing Models for Dimensioning Interactive and Streaming Services in High-Speed Downlink Packet Access Networks

We consider modeling the statistical behavior of interactive and streaming traffics in high-speed downlink packet access (HSDPA) networks. Two important applications in these traffic categories are web-browsing (interactive service) and video streaming (streaming service). Web-browsing is characterized by its important sensitivity to delay. Video streaming on the other hand is less sensitive to delay, however, due to its large frame sizes, video traffic is more affected by the packet loss resulting from a limited buffer size at the base station. Taking these characteristics into account, we consider modeling the queuing delay probability density function (PDF) of the Web-browsing traffic, and modeling the queuing buffer size distribution of video streaming traffic. Specifically, we show that the queuing delay of the Web-browsing traffic follows an exponential distribution and that the queuing buffer size of video streaming traffic follows a weighted Weibull distribution. Model fitting based on simulated data is used to provide simple mathematical formulations for the different parameters that characterize the PDFs under consideration. The provided equations could be used, directly, in HSDPA network dimensioning and, as a reference, to satisfy a certain quality of service (QoS).     

A joint parametric prediction model for wireless internet traffic using Hidden Markov Model

Addressing performance related issues of networks and ensuring better Quality of Service (QoS) for end-users calls for simple, tractable and realistic traffic models. The work reported here focuses on modelling the Wireless Internet traffic using realistic traffic traces collected over wireless networks and forecasting the end-to-end QoS parameters for the networks. A measurement framework is set-up to collect the QoS parameters and a traffic model is designed based on Hidden Markov Model considering joint distribution of End to End Delay (E2ED or d), Inter-Packet Delay Variation (IPDV) and Packet Size. States are mapped to the four traffic classes namely conversational, streaming, interactive, and background. The model is validated by forecasting QoS parameters and the results are shown to be within the tolerance limit.     

Short-term traffic forecasting based on principal component analysis and a generalized regression neural network for satellite networks

With the rapid growth of satellite traffic, the ability to forecast traffic loads becomes vital for improving data transmission efficiency and resource management in satellite networks. To precisely forecast the short-term traffic loads in satellite networks, a forecasting algorithm based on principal component analysis and a generalized regression neural network (PCA-GRNN) is proposed. The PCA-GRNN algorithm exploits the hidden regularity of satellite networks and fully considers both the temporal and spatial correlations of satellite traffic. Specifically, it selects optimal time series of spatio-temporally correlated historical traffic from satellites as forecasting inputs and applies principal component analysis to reduce the input dimensions while preserving the main features of the data. Then, a generalized regression neural network is utilized to perform the final short-term load forecasting based on the obtained principal components. The PCA-GRNN algorithm is evaluated based on real-world traffic traces, and the results show that the PCA-GRNN method achieves a higher forecasting accuracy, has a shorter training time and is more robust than other state-of-the-art algorithms, even for incomplete traffic datasets. Therefore, the PCA-GRNN algorithm can be regarded as a preferred solution for use in real-time traffic forecasting for realistic satellite networks.     

New method of traffic flow forecasting based on quantum particle swarm optimization strategy for intelligent transportation system

Traffic flow forecasting is one of the essential means to realize smart cities and smart transportation. The accurate and effective prediction will provide an important basis for decision‐making in smart transportation systems. This paper proposes a new method of traffic flow forecasting based on quantum particle swarm optimization (QPSO) strategy for intelligent transportation system (ITS). We establish a corresponding model based on the characteristics of the traffic flow data. The genetic simulated annealing algorithm is applied to the quantum particle swarm algorithm to obtain the optimized initial cluster center, and is applied to the parameter optimization of the radial basis neural network prediction model. The function approximation of radial basis neural network is used to obtain the required data. In addition, in order to compare the performance of the algorithms, a comparison study with other related algorithms such as QPSO radial basis function (QPSO‐RBF) is also performed. Simulation results show that compared with other algorithms, the proposed algorithm can reduce prediction errors and get better and more stable prediction results.     

基于模拟退火的粒子滤波在目标跟踪中的应用

针对目标跟踪中的机动目标跟踪,提出了一种基于模拟退火（SA,simulated annealing）的粒子滤波（PF,particle filter）跟踪算法（SAPF）。通过采用SA方法改进重要抽样密度函数,在状态转移基础上增加扰动量,依据Metropolis准则解决粒子的贫乏问题,扩展粒子的局部搜索范围;以降温设计...     

一种基于Kalman的实时话务量预测算法

移动网话务量的预测可以为解决移动网的网络拥塞、覆盖规划、负载均衡和接入控制等方面的问题提供决策支持。日益复杂的移动网络环境对移动网话务量预测的实时性提出了新的要求,针对这一问题进行了研究,结合卡尔曼滤波算法在预测时效性方面的优点,提出了一种基于卡尔曼滤波的移动网实时话务量预测算。该算法通过对呼叫时延的实时预测实现对移动网实时话务量的预测。仿真结果表明,所提算法具有良好的实时性和预测质量。     

未来无线通信业务需求预测方法浅析

在介绍预测技术中最常使用的最小二乘拟合法的基础上,综合分析了3种通信业务量预测方法——基于历史数据拟合的业务量预测方法、基于业务分类的业务量预测方法和基于终端分类的业务量预测方法的预测步骤和特点。