计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220300272-9.doi: 10.11896/jsjkx.220300272

• 网络&通信 • 上一篇    下一篇

基于CEEMDAN-ConvLSTM组合模型的云计算负载预测方法

赵鹏1, 周建涛1,2,3,4,5,6,7, 赵大明1   

  1. 1 内蒙古大学计算机学院 呼和浩特 010021;
    2 蒙古文智能信息处理技术国家地方联合工程研究中心 呼和浩特 010021;
    3 生态大数据教育部工程研究中心 呼和浩特 010021;
    4 内蒙古自治区云计算与服务软件工程实验室 呼和浩特 010021;
    5 内蒙古自治区社会计算与数据处理重点实验室 呼和浩特 010021;
    6 内蒙古自治区大数据分析技术工程实验室 呼和浩特 010021;
    7 内蒙古自治区纪检监察大数据重点实验室 呼和浩特 010021
  • 出版日期:2023-06-10 发布日期:2023-06-12
  • 通讯作者: 周建涛(cszjtao@imu.edu.cn)
  • 作者简介:(zp15247468996@163.com)
  • 基金资助:
    国家自然科学基金(62162046);内蒙古科技攻关项目(2021GG0155);内蒙古自然科学基金重大项目 (2019ZD15);内蒙古自然科学基金(2019GG372)

Cloud Computing Load Prediction Method Based on Hybrid Model of CEEMDAN-ConvLSTM

ZAHO Peng1, ZHOU Jiantao1,2,3,4,5,6,7, ZHAO Daming1   

  1. 1 College of Computer Science,Inner Mongolia University,Hohhot 010021,China;
    2 National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot 010021,China;
    3 Engineering Research Center of Ecological Big Data,Ministry of Education,Hohhot 010021,China;
    4 Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software,Hohhot 010021,China;
    5 Inner Mongolia Key Laboratory of Social Computing and Data Processing,Hohhot 010021,China;
    6 Inner Mongolia Engineering Laboratory for Big Data Analysis Technology,Hohhot 010021,China;
    7 Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data,Hohhot 010021,China
  • Online:2023-06-10 Published:2023-06-12
  • About author:ZHAO Peng,born in 1998,postgraduate.His main research interests include cloud computing and machine learning. ZHOU Jiantao,born in 1972,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.Her main research interests include formal me-thods,cloud computing and software engineering.
  • Supported by:
    National Natural Science Foundation of China(62162046),Key Science-Technology Program of Inner Mongolia,China(2021GG0155),Major Program of the Inner Mongolia Natural Science Foundation of China(2019ZD15) and Natural Science Foundation of Inner Mongolia,China(2019GG372).

PDF (PC)

227

摘要： 随着云计算技术的快速发展,越来越多的用户选择使用云服务。负载请求与资源供应的不匹配问题日益凸显,使得用户请求无法得到及时响应,极大地影响云服务质量,实时预测负载请求,将有助于及时供应资源。针对云计算环境中的负载预测方法性能低的问题,提出了一种基于自适应噪声的完备经验模态分解和卷积长时序神经网络组合模型(CEEMDAN-ConvLSTM)的云计算负载预测方法。首先运用自适应噪声的完备经验模态(CEEMDAN)分解技术对数据序列进行分解操作,将其转换为若干个易于分析和建模的子序列;然后运用卷积长时序神经网络(ConvLSTM)预测模型对这一系列子序列进行建模预测,并采用基于多进程并行计算的研究思路,实现多序列并行预测及贝叶斯优化调参;最后将预测值综合叠加以获得整个模型的预测输出,从而实现对原始复杂序列数据进行高精度预测的目标。使用Google集群工作负载数据集进行实验验证,实验结果表明,CEEMDAN-ConvLSTM组合模型具有良好的预测效果,相比自回归差分移动平均模型(ARIMA)、长短期记忆网络(LSTM)和卷积长时序神经网络(ConvLSTM),所提模型预测均方根误差(RMSE)指标分别提升了30.9%,30.1%和22.5%。

关键词: 云计算, 负载预测, 卷积长时序神经网络(ConvLSTM), 模态分解技术, 贝叶斯优化

Abstract: With the rapid development of cloud computing technology,more and more users choose to use cloud services,and the problem of mismatch between load requests and resource supply becomes increasingly prominent.As a result,user requests cannot be timely responded,which greatly affects the cloud service quality.Real-time prediction of load requests will help the timely supply of resources.To solve the problem of low performance of load prediction methods in the cloud computing environment,a cloud computing load prediction method based on hybrid model of complete ensemble empirical mode decomposition with adaptive noise and convolutional long short-term memory(CEEMDAN-ConvLSTM) is proposed.To begin with,the data sequence is decomposed into several sub-sequences which are easy to analyze and model.Then the convolutional long short-term memory(ConvLSTM) prediction model is used to predict the series of sub-sequences.The research idea based on multi-process parallel computation is adopted to realize multi-sequence parallel prediction and Bayesian optimization parameter tuning.Finally,the prediction values are integrated and superimposed to obtain the prediction output of the whole model,to achieve the goal of high-precision prediction of the original complex sequence data.The CEEMDAN-ConvLSTM hybrid model is verified by using the Google cluster workload data set.Experiment results show that the CEEMDAN-ConvLSTM hybrid model had a good prediction effect.Compared with the autoregressive differential moving average model(ARIMA),long short-term memory network(LSTM) and the convolutional long short-term memory(ConvLSTM),the Root Mean Square Error(RMSE) increases by 30.9%,30.1% and 22.5%,respectively.

Key words: Cloud computing, Load prediction, Convolutional long short-term memory(ConvLSTM), Modal decomposition technique, Bayesian optimization

中图分类号: 

  • TP311.1
[1]AN C Y.Research on Cloud Application Load Modeling and Resource Prediction Method[D].Hohhot:Inner Mongolia University,2018.
[2]WANG B,LIU F,LIN W.Energy-efficient VM schedulingbased on deep reinforcement learning[J].Future Generation Computer Systems,2021,125:616-628.
[3]ZHAO D M,ZHOU J T,LI K.An energy-aware algorithm for virtual machine placement in cloud computing[J].IEEE Access,2019,7:55659-55668.
[4]SU M F,WANG G J,LI R F.Resource Deployment and Task Scheduling Optimization based on Prediction in EdgeCloud Collaborative Computing[J].Journal of Computer Research and Development,2021,58(11):2558-2570.
[5]PANNEERSELVAM J,LIU L,ANTONOPOULOS N.InOt-RePCoN:Forecasting user behavioural trend in large-scale cloud environments[J].Future Generation Computer Systems,2018,80:322-341.
[6]PANNEERSELVAM J,LIU L,ANTONOPOULOS N,et al.Workload analysis for the scope of user demand prediction mo-del evalu-ations in cloud environments[C]//2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing.IEEE,2014:883-889.
[7]DUY T V T,SATO Y,INOGUCHI Y.Improving accuracy of host load predictions on computational grids by artificial neural networks[J].International Journal of Parallel,Emergent and Distributed Systems,2011,26(4):275-290.
[8]LIU Y.Container Load Prediction and Integration Strategy in Cloud Environment[D].Guangzhou:South China University of Technology,2020.
[9]CHENG X L.Research on Time Series Prediction Based on Empirical Mode Decomposition[D].Dalian:Dalian University of Technology,2018.
[10]SUN Z,ZHAO M.Short-term wind power forecasting based on VMD decomposition,ConvLSTM networks and error analy-sis[J].IEEE Access,2020,8:134422-134434.
[11]CALHEIROS R N,MASOUMI E,RANJAN R,et al.Workloadprediction using ARIMA model and its impact on cloud applica-tions’ QoS[J].IEEE Transactions on Cloud Computing,2014,3(4):449-458.
[12]LIU J W,WANG Y F,LUO X L.Advances in deep memory Networks[J].Chinese Journal of Computers,2021,44(8):41.
[13]PACHECO-SANCHEZ S,CASALE G,SCOTNEY B,et al.Markovian workload characterization for QoS prediction in the cloud[C]//2011 IEEE 4th International Conference on Cloud Computing.IEEE,2011:147-154.
[14]ZHANG W,LI B,ZHAO D,et al.Workload prediction for cloud cluster using a recurrent neural network[C]//2016 Interna-tional Conference on Identification,Information and Knowledge in the Internet of Things(IIKI).IEEE,2016:104-109.
[15]LIN T,FENG J K,HAO Z X,et al.Research on cloud computing resource load prediction based on combination prediction model[J].Computer Engineering and Science,2020,42(7):1168-1173.
[16]SONG J,ZHANG L,XUE G,et al.Predicting hourly heating load in a district heating system based on a hybrid CNN-LSTM model[J].Energy and Buildings,2021,243:110998.
[17]ZHANG P,WANG M.Variation Characteristics Analysis andShort-Term Forecasting of Load Based on CEEMDAN[C]//2021 International Symposium on Electrical,Electronics and Information Engineering.2021:493-500.
[18]SHI X J,CHEN Z,WANG H,et al.Convolutional LSTM network:A machine learning approach for precipitation now-casting[C]//Advances in Neural Information Processing Systems.2015:802-810.
[19]CUI J X,YANG B.Bayesian optimization algorithm and application review[J].Journal of software,2018,29(10):3068-3090.
[20]REISS C,WILKES J,HELLERSTEIN J.Google clus-ter-usage traces:format＋schema[EB/OL].https://github.com/google/cluster-data.
[21]LIAO X,CAO N,LI M,et al.Research on short-term load forecasting using XGBoost based on similar days[C]//2019 International Conference on Intelligent Transportation,Big Data & Smart City(ICITBS).IEEE,2019:675-678.
[22]YU J,DING F,GUO C,et al.System load trend predictionmethod based on IF-EMD-LSTM[J].International Journal of Distributed Sensor Networks,2019,15(8):15501477198.
[23]FU W,WANG K,TAN J,et al.A composite framework cou-pling multiple feature selection,compound prediction models and novel hybrid swarm optimizer-based synchronization optimi-zation strategy for multi-step ahead short-term wind speed forecasting[J].Energy Conversion and Management,2020,205:112461.
[24]JIANG Y Z,HAO Z F,ZHANG Y S,et al.Bayesian predictive evolutionary algorithm[J].Chinese Journal of Computers,2014,37(8):1846-1858.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发