期刊文献+

基于改进型深度学习的流量预测 被引量:5

Traffic Prediction Based on Modified Deep Learning
在线阅读 下载PDF
导出
摘要 为了解决无线网络中流量的预测精度不高的问题,提出了一种自适应分组的栈式自编码(AG-SAEs)深度学习预测方法。在数据的预处理过程中,首先使用最大最小方式对数据进行归一化处理,并提出一种新型的自适应分组方法,把归一化后的链路数据进行关联性分组;然后,基于深度学习方法建立了一个多输入多输出的预测模型,并将分组后的数据输入到预测模型中,对该模型进行训练来建立输入和输出流量之间的映射关系;最后,为了进一步提高预测精度,在模型的训练过程中,使用改进型的牛顿法来进行权值参数更新。仿真实验以及和其他算法对比的结果证实了所提方案具有更小的预测相对误差。 To solve the problem of low traffic prediction accuracy in wireless networks,a method based on the adaptive grouping stacked auto - encoders ( AG-SAEs) deep learning is proposed. In data preprocess-ing ,the maximum and minimum method is used to normalize the data,and a novel adaptive grouping meth-od is adopted to divide the normalized data into different groups adaptively. Then,a multi-input multi-out-put prediction model based on the deep learning model is established. All the groups are input to the stacked auto-encoder model to train the model and map the relationship between input and output traffic. Finally,in order to further improve the prediction accuracy,the modified Newton method is used to update the weight parameters in the model training section. The simulation experiment and comparison with other methods show that the proposed method processes a smaller prediction relative error.
出处 《电讯技术》 北大核心 2017年第1期1-8,共8页 Telecommunication Engineering
基金 国家自然科学基金资助项目(61271260) 重庆市科委自然科学基金资助项目(cstc2015jcyj A40050)
关键词 认知网络 流量预测 深度学习 自适应分组 cognitive network traffic prediction deep learning adaptive grouping
作者简介 朱江(1977-),男,湖北人,2009年于电子科技大学获博士学位,现为副教授,主要研究方向为认知无线电、移动通信;Email:zhujiang@cqupt.edu.cn 通信作者:songyh1110@163.com宋永辉(1991-),男,河北人,硕士研究生,主要研究方向为认知无线电、网络优化 刘亚利(1989-),男,河南人,硕士研究生,主要研究方向为认知无线电、网络优化.
  • 相关文献

参考文献3

二级参考文献89

  • 1Mohamed A, Dahl G, Hinton G. Deep belief networks for phone recognition[ C]//NIPS Workshop on Deep Learning for Speech Recognition and Related Applications. Whistler, BC, Canada: [ s. n. ],2009 : 1 - 6.
  • 2Mohamed A, Hinton G, Perm G. Understanding how deep belief networks perform acoustic modeling[ C]//Proceedings of 2012 1EEE International Conference on Acoustics, Speech and Signal Processing. Kyoto: IEEE,2012:4273- 4276.
  • 3Dahl G E, Yu D, Deng L, et al. Context-Dependent Pre- Trained Deep Neural Networks for Large-Vocabulary Speech Recoguition[J]. IEEE Transactions on Audio, Speech, and Language Processing, 2012,20( 1 ) : 30 - 42.
  • 4Hinton G. A practical guide to training restricted Boltzmann machines[J]. Momentum,2010(9) : 1 - 20.
  • 5LeCun Y, Bottou L, Orr G B, et al. Efficient backprop [M]//Neural networks: Tricks of the trade. Heidelberg, Berlin: Springer, 1998: 9 - 50.
  • 6Haykin S. Cognitive Radio:Brain- empowered WirelessCommunications [J]. IEEE Journal on Selected Areas inCommunications,2005,23(2):201-220.
  • 7Kartlak H. Performance improvement of secondary usertransmission in cognitive radio networks[C] / / Proceed-ings of 2012 20th Signal Processing and CommunicationsApplications Conference. Mugla:IEEE,2012:1-4.
  • 8Cacciapuoti A S,Akyildiz I F,Paura L. Primary - usermobility impact on spectrum sensing in Cognitive Radionetworks[C] / / Proceedings of 2011 IEEE 22nd Interna-tional Symposium on Personal Indoor and Mobile RadioCommunications. Toronto,ON:IEEE,2011:451-456.
  • 9Butun I,Cagatay T A,Altilar D T,et al. Impact of mobilityprediction on the performance of Cognitive Radio networks[C] / / Proceedings of 2010 Wireless TelecommunicationsSymposium. Tampa,FL:IEEE,2010:1-5.
  • 10Yong Y,Ngoga S R,Popescu A. Cognitive Radio spectrumdecision based on channel usage prediction[C]/ / Proceed-ings of the 8th EURO-NGI Conference on Next GenerationInternet(NGI). Karlskrona:IEEE,2012:41-48.

共引文献395

同被引文献18

引证文献5

二级引证文献7

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部