Cloud KPI data prediction method based on combined attention model EAAT
Author:
Affiliation:

College of Computer Science and Technology,Civil Aviation University Of China

Clc Number:

TP391

  • Article
  • | |
  • Metrics
  • |
  • Reference [18]
  • | |
  • Cited by
  • | |
  • Comments
    Abstract:

    In order to accurately analyze the dynamics and changing trends of KPI data in the daily monitoring of cloud computing clusters and predict the subsequent development to achieve the goal of improving the high availability of cloud computing clusters, this paper proposes a three-frequency cloud KPI data prediction based on the combined attention model EAAT method. First, low, medium and high frequency intrinsic mode variables (IMFs) of cloud KPI data are obtained based on Empirical wavelet transform (EWT) to reduce the complexity of data prediction. Secondly, according to the information characteristics of low, medium and high frequency IMFs obtained from the decomposition, the ARIMA, Autoformer, and TPA-BiLSTM models are used to predict each type of IMFs. Finally, the classification prediction results are combined through the inverse transformation IEWT to obtain the prediction result of the KPI. The prediction method in this paper has been verified on four data sets from Google and Amazon. Regardless of whether the data is periodic or not, the prediction method in this paper has good results. The root mean square error of the EWT-IF-LSTM model on the Google data set is reduced by about 11.26%.

    Reference
    [1] J. Gao, H. Wang and H. Shen, Machine Learning Based Workload Prediction in Cloud Computing[C],2020 29th International Conference on Computer Communications and Networks (ICCCN), 2020, pp. 1-9, doi: 10.109 / ICCCN49398.2020.9209730.
    [2] Muteeh A, Sardaraz M, Tahir M. MrLBA: multi-resource load balancing algorithm for cloud computing using ant colony optimization[J]. Cluster Computing, 2021, 24(4): 3135-3145.
    [3] Kumar J, Singh AK. Performance evaluation of metaheuristics algorithms for workload prediction in cloud environment [J] . Applied Soft Computing . 2021 Dec 1; 113 : 107895.
    [4] Wen Q , Wang Y , Zhang H , et al. Application of ARIMA and SVM mixed model in agricultural managem-ent under the background of intellectual agricul-ture [J]. Cluster Computing, 2018.
    [5] A. S. Saud, S. Shakya, Analysis of look back period for stock price prediction with RNN variants: A case study on banking sector of NEPSE [J] Procedia Computer Science, 167, 788–798, 2020. https: // doi.org / 10.1016/ j. procs . 2020. 03. 419.
    [6] C. Fan, J. Wang, W. Gang, S. Li, Assessment of deep recurrent neural network-based strategies for short-term building energy predictions[J] Applied Energy, 236, 700–710, 2019. https: //doi.org/10.1016/j. apenergy. 2018.12.004.
    [7] Wen Q, Zhou T, Zhang C, et al. Transformers in time series: A survey[J]. arXiv preprint arXiv:2202.7125, 2022.
    [8] Z. Zhang, X. Tang, J. Han, P. Wang, Sibyl. Host Load Prediction with an Efficient Deep Learning Model in Cloud Computing [J]. Algorithms and Architectures for Parallel Processing, 226–237, 2018. https: //doi.org / 10. 1007 / 978 -3-030-05054-2_17
    [9] Zhou H, Zhang S, Peng J, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting [C] //Proceedings of the AAAI Conference on Artificial Intelligence. 2021, 35 (12): 11106-11115. Shih S Y, Sun F K, Lee H. Temporal pattern attention for multivariate time series forecasting [J]. Machine Learning, 2019, 108 (8): 1421-1441.
    [10] Wu H, Xu J, Wang J, et al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting [J]. Advances in Neural Information Processing Systems, 2021, 34: 22419-22430.
    [11] S. Baig, W. Iqbal, J. L. Berral, A. Erradi, D. Carrera, Adaptive Prediction Models for Data Center Resources Utilization Estimation [C], in IEEE Transactions on Network and Service Management, vol. 16, no. 4, pp. 1681-1693 , 2019, https://doi.org /10.109/ .2019. 2932840.
    [12] J. Bi, S. Li, H. Yuan, M. C. Zhou, Integrated deep learning method for workload and resource prediction in cloud systems [J]. Neurocomputing, 424, 35–48, 2021. https: //doi.org/10.1016/j.neucom.2020.11.011
    [13] Yang, Z., Peng, X., Wei, P., Xiong, Y., Xu, X., Song, J. Short-Term Wind Power Prediction Based on CEEMDAN and Parallel CNN-LSTM [C]. In 2022 IEEE/IAS Industrial and Commercial Power System Asia (I CPS Asia) pp.1166-1172. IEEE.
    [14] Zhi-Yu W, Jun Q and Fang-Fang L. Hybrid models combining EMD/EEMD and ARIMA for long-term streamflow forecasting. Water 2018; 10 (7): 853–866.
    [15] 云环境中时序数据的预测和异常检测算法的研究 [D]. 南京大学,2019.
    [16] 李梅, 宁德军, 郭佳程. 基于注意力机制的 CNN-LSTM 模型及其应用 [J]. 计算机工程与应用, 2019, 55(13): 20-27.
    [17] Shih S Y, Sun F K, Lee H. Temporal pattern attention for multivariate time series forecasting [J]. Machine Learning, 2019, 108(8): 1421-1441.
    [18] S. Baig, W. Iqbal, J. L. Berral, A. Erradi, D. Carrera, Adaptive Prediction Models for Data Center Resources Utilization Estimation [C], in IEEE Transactions on Network and Service Management, vol. 16, no. 4, pp. 1681-1693 , 2019, https://doi.org /10.109/ .2019. 2932840.
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation
Share
Article Metrics
  • Abstract:88
  • PDF: 0
  • HTML: 0
  • Cited by: 0
History
  • Received:January 08,2023
  • Revised:March 07,2023
  • Adopted:March 08,2023
Article QR Code

Address:No. 219, Ningliu Road, Nanjing, Jiangsu Province

Postcode:210044

Phone:025-58731025