摘要
本文提出了基于深度置信网络的3种不同架构的网络流量预测模型来预测互联网流量。首先,介绍了深度置信网络的网络结构,然后构建了3种不同架构的深度置信网络拓扑结构,最后通过实验对比,发现隐层的神经元数量对更深层次的网络至关重要,该模型被证明是一种有效的预测模型。本文所采用的方法在模拟流量数据模式和随机要素的同时,提供了准确的网络流量预测,使测试数据集的均方根误差值为0.028。
This paper proposes three different network traffic prediction models based on deep belief network to predict the Internet traffic in the next 1 hour.First,the network structure of deep belief network is introduced.Then,the deep belief network topology of three different architectures was constructed.Finally,through experimental comparison,it was found that the number of neurons in the hidden layer was crucial to the deeper level of the network.This model proved to be an effective prediction model.The method adopted in this paper provides accurate network traffic prediction while simulating traffic data patterns and random elements,so that the root mean square error value of the test data set is 0.028.
作者
孟智慧
MENG Zhi-hui(China Mobile Group Design Institute Co.,Ltd.Shanxi Branch,Taiyuan 030000,China)
出处
《电信工程技术与标准化》
2020年第10期42-47,共6页
Telecom Engineering Technics and Standardization
关键词
深度学习
深度置信网络
互联网流量预测
deep learning
deep belief network
Internet traffi c prediction
