TY - GEN
T1 - An efficient dynamic neural network for predicting time series data stream
AU - Chen, Liang
AU - Wang, Wei
AU - Yang, Yun
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12
Y1 - 2020/12
N2 - The prediction of the time-series data stream in AIOps is an important research field of data mining. However, due to the non-stationary and non-linear characteristics of time series data, many existing methods cannot comprehensively solve the accuracy and reduce time consumption. To solve this problem, we propose a new MWNN (Memory Wavelet Neural Network) algorithm. It can effectively overcome the contradiction between accuracy and time consumption. In MWNN, we designed a new hidden layer structure. By adding a new memory storage unit to the hidden layer, it can be ensured that the hidden layer can make the best use of historical data and greatly improve the prediction accuracy. Moreover, the model does not require any prior information or data distribution assumptions. This paper selects real Ops data for verification. The final experimental results show that, compared with the commonly used prediction models, this model has the highest prediction accuracy and lower time consumption. The data set used in the experiment has been uploaded to https://github.com/Yang-Yun726/MWNN/tree/master/DATA.
AB - The prediction of the time-series data stream in AIOps is an important research field of data mining. However, due to the non-stationary and non-linear characteristics of time series data, many existing methods cannot comprehensively solve the accuracy and reduce time consumption. To solve this problem, we propose a new MWNN (Memory Wavelet Neural Network) algorithm. It can effectively overcome the contradiction between accuracy and time consumption. In MWNN, we designed a new hidden layer structure. By adding a new memory storage unit to the hidden layer, it can be ensured that the hidden layer can make the best use of historical data and greatly improve the prediction accuracy. Moreover, the model does not require any prior information or data distribution assumptions. This paper selects real Ops data for verification. The final experimental results show that, compared with the commonly used prediction models, this model has the highest prediction accuracy and lower time consumption. The data set used in the experiment has been uploaded to https://github.com/Yang-Yun726/MWNN/tree/master/DATA.
KW - AIOps
KW - Data stream Prediction
KW - Dynamic neural net-work
KW - Memory neuron
UR - https://www.scopus.com/pages/publications/85108028689
U2 - 10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00104
DO - 10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00104
M3 - 会议稿件
AN - SCOPUS:85108028689
T3 - Proceedings - 2020 IEEE International Symposium on Parallel and Distributed Processing with Applications, 2020 IEEE International Conference on Big Data and Cloud Computing, 2020 IEEE International Symposium on Social Computing and Networking and 2020 IEEE International Conference on Sustainable Computing and Communications, ISPA-BDCloud-SocialCom-SustainCom 2020
SP - 625
EP - 632
BT - Proceedings - 2020 IEEE International Symposium on Parallel and Distributed Processing with Applications, 2020 IEEE International Conference on Big Data and Cloud Computing, 2020 IEEE International Symposium on Social Computing and Networking and 2020 IEEE International Conference on Sustainable Computing and Communications, ISPA-BDCloud-SocialCom-SustainCom 2020
A2 - Hu, Jia
A2 - Min, Geyong
A2 - Georgalas, Nektarios
A2 - Zhao, Zhiwei
A2 - Hao, Fei
A2 - Miao, Wang
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE International Symposium on Parallel and Distributed Processing with Applications, 10th IEEE International Conference on Big Data and Cloud Computing, 13th IEEE International Symposium on Social Computing and Networking and 10th IEEE International Conference on Sustainable Computing and Communications, ISPA-BDCloud-SocialCom-SustainCom 2020
Y2 - 17 December 2020 through 19 December 2020
ER -
