11th EAI International Conference on Mobile Multimedia Communications

Research Article

Improved Echo State Network (ESN) for the Prediction of Network Traffic

Download552 downloads
  • @INPROCEEDINGS{10.4108/eai.21-6-2018.2276461,
        author={Dezhong Ye and Haibing Lv and Yong Jiang and Zhongzheng Wu and Qiuxia Bao and Yun Gao and Ruochen Huang},
        title={Improved Echo State Network (ESN) for the Prediction of Network Traffic},
        proceedings={11th EAI International Conference on Mobile Multimedia Communications},
        publisher={EAI},
        proceedings_a={MOBIMEDIA},
        year={2018},
        month={9},
        keywords={echo state network (esn) weight matrix wavelet function},
        doi={10.4108/eai.21-6-2018.2276461}
    }
    
  • Dezhong Ye
    Haibing Lv
    Yong Jiang
    Zhongzheng Wu
    Qiuxia Bao
    Yun Gao
    Ruochen Huang
    Year: 2018
    Improved Echo State Network (ESN) for the Prediction of Network Traffic
    MOBIMEDIA
    EAI
    DOI: 10.4108/eai.21-6-2018.2276461
Dezhong Ye1, Haibing Lv1, Yong Jiang1, Zhongzheng Wu1, Qiuxia Bao2,*, Yun Gao2, Ruochen Huang2
  • 1: ZTE CORPORATION,China, 210012
  • 2: College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China, 210003
*Contact email: 18351925305@163.com

Abstract

With the development of computer and network technologies, the network traffic has come to an explosive growth. Considering the non-linearity of network data, we choose echo state network (ESN) to predict the data. ESN is a novel kind of recurrent neural networks, where a reservoir is generated randomly and only output weight matrix is adaptable. In our paper, we propose an improved network of ESN considering its weekness on selection of matrix initialization and activation function. The improved network defines the scope of matrix initialization and replaces the activation function of middle layer with wavelet function. And result shows that our improved network is more effective compared to original ESN. Our evaluation index is normalized mean square error (NMSE), and it drops from 0.7435 to 0.5852 by making improvements.