计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (12): 147-156.doi: 10.11896/jsjkx.231000098

• 高性能计算 • 上一篇    下一篇

基于v-Informer的云平台资源负载预测方法

尤文龙, 邓莉, 李锐龙, 谢雨欣, 任正伟   

  1. 武汉科技大学计算机科学与技术学院 武汉 430065
    智能信息处理与实时工业系统湖北省重点实验室 武汉 430065
  • 收稿日期:2023-10-16 修回日期:2024-03-11 出版日期:2024-12-15 发布日期:2024-12-10
  • 通讯作者: 邓莉(dengli@wust.edu.cn)
  • 作者简介:(1526347207@qq.com)
  • 基金资助:
    国家自然科学基金(61902285)

Load Prediction Method of Cloud Resource Based on v-Informer

YOU Wenlong, DENG Li, LI Ruilong, XIE Yuxin, REN Zhengwei   

  1. College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China
    Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan 430065, China
  • Received:2023-10-16 Revised:2024-03-11 Online:2024-12-15 Published:2024-12-10
  • About author:YOU Wenlong,born in 1999,postgra-duate.His main research interests include cloud computing and artificial intelligence.
    DENG Li,born in 1972,Ph.D,associate professor,is a member of CCF(No.57882M).Her main research interests include cloud computing and distributed computing.
  • Supported by:
    National Natural Science Foundation of China(61902285).

PDF (PC)

146

摘要： 目前,云计算技术的使用非常广泛。随着用户量的增加,云计算资源的分配管理也越来越重要,而准确的负载预测是分配管理的重要依据。但由于云平台任务有多个负载特征,且特征的相关性变化趋势各不相同,因此难以从长期的历史数据中提取出有效的依赖信息。在Informer模型的基础上,提出了一种针对高动态云平台任务CPU长期负载预测方法v-Informer,该方法通过变分模态分解来分解负载序列中的变化趋势,引入多头自注意力机制捕获其中的长期依赖性和局部非线性关系,同时应用梯度集中技术改进优化器,减少计算开销。分别在微软云平台和谷歌云平台数据上进行实验,结果表明,与目前已有的CPU负载预测模型LSTM,Transformer,TCN和CEEMDAN-Informer相比,v-Informer在Google数据集上的预测误差分别减少了34%,19%,15%和6.5%;在微软数据集上的预测误差分别减少了32%,16%,12%和7%,具有较好的预测精度。

关键词: 云平台, CPU负载, 多步预测, 模态分解, Informer, 梯度收敛

Abstract: Cloud computing technology is widely used at present.With the increase in the number of users,the allocation and management of cloud computing resources is becoming more and more important,and accurate load prediction is an important basis for allocation and management.Based on the Informer model,this paper proposes a long-term CPU load prediction method for high dynamic cloud platform tasks,called v-Informer.v-Informer decomposes the variation trend in the load sequence through va-riational mode decomposition,and introduces a multi-head self-attention mechanism to capture the long-term dependence and local nonlinear relationship.At the same time,the gradient concentration technique is used to improve the optimizer and reduce the computational cost.Experiments are carried out on the data of Microsoft and Google cloud platforms.The results show that,compared with the existing CPU load prediction models LSTM,Transformer,TCN and CEEMDAN-Informer,the prediction error of v-Informer is reduced by 34%,19%,15% and 6.5% respectively on the Google dataset.The prediction error on the Microsoft dataset is reduced by 32%,16%,12% and 7% respectively,with better prediction accuracy.

Key words: Cloud platform, CPU load, Multi-step forecasting, Modal decomposition, Informer, Gradient convergence

中图分类号: 

  • TP391
[1]MASDARI M,VALIKARDAN S,SHAHI Z,et al.Towardsworkflow scheduling in cloud computing:a comprehensive ana-lysis[J].Journal of Network and Computer Applications,2016,66:64-82.
[2]MASDARI M,NABAVI S S,AHMADI V.An overview of virtual machine placement schemes in cloud computing[J].Journal of Network and Computer Applications,2016,66:106-127.
[3]REISS C,WILKES J,HELLERSTEIN J L.Google cluster-usage traces:format+ schema[J].Google Inc.,White Paper,2011,1:1-14.
[4]MASDARI M,SALEHI F,JALALI M,et al.:A survey of PSO-based scheduling algorithms in cloud computing[J].Journal of Network and Systems Management,2017,25(1):122-158.
[5]SINGH S,CHANA I.A survey on resource scheduling in cloud computing:issues and challenges[J].Journal of Grid Compu-ting,2016,14(2):217-264.
[6]MASDARI M,KHOSHNEVIS A.A survey and classification of the workload forecasting methods in cloud computing[J].Cluster Computing,2020,23(4):2399-2424.
[7]KUMAR J,SINGH A K,BUYYA R.Self directed learningbased workload forecasting model for cloud resource management[J].Information Sciences,2021,543:345-366.
[8]OUHAME S,HADI Y,ULLAH A.An efficient forecasting ap-proach for resource utilization in cloud data center using CNN-LSTM model[J].Neural Computing and Applications,2021,33:10043-10055.
[9]ZHOU S,LI J,ZHANG K,et al.An accurate ensemble forecasting approach for highly dynamic cloud workload with VMD and R-transformer[J].IEEE Access,2020,8:115992-116003.
[10]HU Y,DENG B,PENG F,et al.Workload prediction for cloud computing elasticity mechanism[C]//2016 IEEE International Conference on Cloud Computing and Big Data Analysis(ICCCBDA).IEEE,2016:244-249.
[11]ZHONG W,ZHUANG Y,SUN J,et al.A load prediction model for cloud computing using PSO-based weighted wavelet support vector machine[J].Applied Intelligence,2018,48:4072-4083.
[12]PENG H,WEN W S,TSENG M L,et al.A cloud load forecasting model with nonlinear changes using whale optimization algorithm hybrid strategy[J].Soft Computing,2021,25(15):10205-10220.
[13]KUMAR J,SINGH A K.Workload prediction in cloud using artificial neural network and adaptive differential evolution[J].Future Generation Computer Systems,2018,81:41-52.
[14]DUGGAN M,MASON K,DUGGAN J,et al.Predicting hostCPU utilization in cloud computing using recurrent neural networks[C]//2017 12th International Conference for Internet Technology and Secured Transactions(ICITST).IEEE,2017:67-72.
[15]GUO W,GE W,LU X,et al.Short-term load forecasting of virtual machines based on improved neural network[J].IEEE Access,2019,7:121037-121045.
[16]OUHAME S,HADI Y,ULLAH A.An efficient forecasting approach for resource utilization in cloud data center using CNN-LSTM model[J].Neural Computing and Applications,2021,33(16):10043-10055.
[17]DU S,LI T,YANG Y,et al.Multivariate time series forecasting via attention-based encoder-decoder framework[J].Neurocomputing,2020,388:269-279.
[18]YU Z H,LIU Z Q,LIU Y,et al.Software defect prediction feature selection method based on adaptive mixed particle swarm optimization[J].Computer Applications,2023,43(4):1206-1213.
[19]LI Y H,GUO H G,LIU P P,et al.Load prediction method of cloud platform based on temporal convolutional network[J].Computer Science,2023,50(7):254-260.
[20]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.2021:11106-11115.
[21]YONG H,HUANG J,HUA X,et al.Gradient centralization:A new optimization technique for deep neural networks[C]//European Conference on Computer Vision.Cham:Springer,2020:635-652.
[22]SONG B,YU Y,ZHOU Y,et al.Host load prediction with long short-term memory in cloud computing[J].The Journal of Supercomputing,2018,74:6554-6568.
[23]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[24]BAI S,KOLTER J Z,KOLTUN V.An empirical evaluation of generic convolutional and recurrent networks for sequence mo-deling[J].arXiv:1803.01271,2018.
[25]WU T,PAN M,YU Y.A Long-term Cloud Workload Prediction Framework for Reserved Resource Allocation[C]//2022 IEEE International Conference on Services Computing(SCC).IEEE,2022:134-139.
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