系统辨识建模..docx

上海大学 2015～ 2016学年冬季学期研究生课程考试小论文格式课程名称：系统建模与辨识课程编号： 09SB59002论文题目: 基于改进的BP神经网络模型的网络流量预测 研究生姓名: 李金田 学 号:文评语:成 绩: 任课教师: 张宪评阅日期: 基于改进的BP神经网络模型的网络流量预李金田2016/3/4摘要：随着无线通信技术的快速发展，互联网在人们的日常生活中占据了越来越重要的位置。网络中流量监控和预测对于研究网络拓扑结构有着重要的意义。本文参考BP算法，通过分析算法的优势和存在的一些问题，针对这些缺陷进行了改进。通过建立新的流量传输的传递函数，对比了经典的传递函数，并且在网络中进行了流量预测的实验和验证。新方法在试验中表现出了良好的实验性能，在网络流量预测中有很好的应用，可以作为网络流量预测的一个新方法和新思路，并且对研究网络拓扑结构有着重要的启发作用。网络流量预测在研究网络行为方面有着重要的作用。ARMA时间序列模型是比较常见的用于网络流量预测的模型。但是用在普通时间序列模型里面的一些参数很难估计，同时非固定的时间序列问题用ARMA模型很难解决。人工神经网络技术通过对历史数据的学习可能对大量数据的特征进行缓存记忆，对于解决大数据的复杂问题很合适。IP6 网络流量预测是非线性的，可以使用合适的神经网络模型进行计算。A Novel BP Neural Network Model for Traffic Prediction of The Next Generation Network.Abstract:With the rapid development of wireless communication technology, the internet occupy an important position in people’s daily life. Monitoring and predicting the traffic of the network is of great significant to study the topology of the network. According to the BP algorithm, this paper proposed an improved BP algorithm based on the analysis of the drawback of the algorithm.By establishing a new transfer function of the traffic transmission, we compare it with the previous transmission function. Then, the function is used to do experiments, found to be the better than before. This method can be used as a new way to predict the network traffic, which has important implications for the study of the network topology.Network traffic prediction is an important research aspect of network behavior. Conventionally, ARMA time sequence model is usually adopted in network traffic prediction. However, the parameters used in normal time sequence models are difficult to be estimated and the nonstationary time sequence problem cannot be processed using ARMA time sequence problem model. The neural network technique may memory large quantity of characteristics of data set by learning previous data, and is suitable for solving these problems with large complexity. IP6 network traff