计算机科学 ›› 2023, Vol. 50 ›› Issue (7): 254-260.doi: 10.11896/jsjkx.220500036
李英豪, 郭昊龚, 刘盼盼, 相毅浩, 刘成明
LI Yinghao, GUO Haogong, LIU Panpan, XIANG Yihao, LIU Chengming
摘要: 针对云平台资源负载数据高度非平稳以及存在着随机噪声导致预测准确度较低等问题,结合信号分解和深度学习等技术,提出了一种云平台资源负载预测方法。首先利用经验模态分解(Empirical Mode Decomposition,EMD)方法对原始数据进行分解,得到多个IMF分量;然后构建出基于时间卷积网络(Temporal Convolutional Network,TCN)的预测模型,分别对IMF分量进行预测;最后将预测结果进行合并以得到最终的预测值。将所提方法与传统的预测方法及深度学习预测方法进行比较,并在阿里巴巴开源的数据中心资源监控日志数据集上进行了对比实验。实验结果表明,所提方法的预测误差分别比ARIMA,Bi-LSTM,GRU,TCN降低了36.75%,23.5%,24.44%,24.53%,预测结果具有最优的准确度。
中图分类号:
[1]JADEJA Y,MODI K.Cloud computing-concepts,architectureand challenges[C]//2012 International Conference on Computing,Electronics and Electrical Technologies(ICCEET).Nagercoil:IEEE,2012:877-880. [2]MIYACHI C.What is “Cloud”? It is time to update the NIST definition?[J].IEEE Cloud Computing,2018,5(3):6-11. [3]ZHANG C,WANG Y,LV Y,et al.An energy and sla-aware resource management strategy in cloud data centers[J].Scientific Programming,2019,2019:1-16. [4]PANNEERSELVAM J,LIU L,HARDY J,et al.Analysis,Modelling and Characterisation of Zombie Servers in Large-Scale Cloud Datacentres[J].IEEE Access,2017,5:15040-15054. [5]MORENO-VOZMEDIANO R,MONTERO R S,HUEDO E,et al.Efficient resource provisioning for elastic Cloud services based on machine learning techniques[J].Journal of Cloud Computing,2019,8(1):1-18. [6]REISS C,WILKES J,HELLERSTEIN J L.Google cluster-usage traces:format+ schema [J].Google Inc.,White Paper,2011,1:1-14. [7]YANG H M,PAN Z S,BAI W.Review of Time Series Prediction Methods[J].Computer Science,2019,46(1):21-28. [8]ZHI G W,GAO M.Parameter estimation of random coefficient autoregressive model with missing data [J].Statistics & Decision,2022,38(1):16-20. [9]XIE Y,JIN M,ZOU Z,et al.Real-time prediction of docker container resource load based on a hybrid model of ARIMA and triple exponential smoothing[J].IEEE Transactions on Cloud Computing,2020,10(2):1386-1401. [10]SUN Y,SONG X Y,JIN L T,et al.Railway Passenger FlowForecast Based on Armah stm combined model [J].Computer Applications and Software,2021,38(12):262-267,273. [11]WU F,JING R,ZHANG X P,et al.A combined method of improved grey BP neural network and MEEMD-ARIMA for day-ahead wave energy forecast[J].IEEE Transactions on Sustai-nable Energy,2021,12(4):2404-2412. [12]OPREA S,MARTINEZ-GONZALEZ P,GARCIA-GARCIA A,et al.A review on deep learning techniques for video prediction[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,44(6):2806-2826. [13]HSIEH S Y,LIU C S,BUYYA R,et al.Utilization-prediction-awarevirtual machine consolidation approach for energy-efficient cloud data centers[J].Journal of Parallel and Distributed Computing,2020,139:99-109. [14]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(11):4072-4083. [15]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. [16]TOFIGHY S,RAHMANIAN A A,GHOBAEI-ARANI M.An ensemble CPU load prediction algorithm using a Bayesian information criterion and smooth filters in a cloud computing environment[J].Software:Practice and Experience,2018,48(12):2257-2277. [17]RAHMANIAN A A,GHOBAEI-ARANI M,TOFIGHY S.Alearning automata-based ensemble resource usage prediction algorithm for cloud computing environment[J].Future Generation Computer Systems,2018,79:54-71. [18]LIU B,WANG M S,LI Y,et al.Deep Learning for Spatio-Temporal Sequence Forecasting:A Survey[J].Journal of BeijingUniversity of Technology,2021,47(8):925-941. [19]NI X L,SHI C A,M Y L,et al.Research on fault predictionmethod of electronic Equipment based on BI-LSTM[J].Aero Weaponry,2022,29(6):102-110. [20]CAO G H,ZHAO Z L,XU Y H.Research on Health State Prediction of Lithium Battery Pack Based on GRU[J].Journal of Jilin University(Information Science Edition),2022,40(2):181-187. [21]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. [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(12):6554-6568. [23]NGUYEN H M,KALRA G,KIM D.Host load prediction in cloud computing using long short-term memory encoder-decoder[J].The Journal of Supercomputing,2019,75(11):7592-7605. [24]KARIM M E,MASWOOD M M S,DAS S,et al.BHyPreC:a novel Bi-LSTM based hybrid recurrent neural network model to predict the CPU workload of cloud virtual machine[J].IEEE Access,2021,9:131476-131495. [25]FLANDRIN P,RILLING G,GONCALVES P.Empirical mode decomposition as a filter bank[J].IEEE Signal Processing Letters,2004,11(2):112-114. [26]DONOHO D L.De-noising by soft-thresholding[J].IEEETransactions on Information Theory,1995,41(3):613-627. [27]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[J/OL].Advances in Neural Information Processing Systems,2017,30.https://papers.nips.cc/paper_files/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html. [28]GUO J,CHANG Z,WANG S,et al.Who limits the resource efficiency of my datacenter:An analysis of alibaba datacenter traces[C]//2019 IEEE/ACM 27th International Symposium on Quality of Service(IWQoS).Phoenix,AZ,USA:IEEE,2019:1-10. |
|