基于三次指数平滑法和时间卷积网络的云资源预测模型

doi:10.11959/j.issn.1000-436x.2019172

Abstract

Abstract:

The container cloud represented by Docker and Kubernetes has the advantages of less additional resource overhead and shorter start-up and destruction time.However there are still resource management issues such as over-supply and under-supply.In order to allow the Kubernetes cluster to respond “in advance” to the resource usage of the applications deployed on it,and then to schedule and allocate resources in a timely,accurate and dynamic manner based on the predicted value,a cloud resource prediction model based on triple exponential smoothing method and temporal convolutional network was proposed,based on historical data to predict future demand for resources.To find the optimal combination of parameters,the parameters were optimized using TPOT thought.Experiments on the CPU and memory of the Google dataset show that the model has better prediction performance than other models.

Key words: resource prediction, Kubernetes, exponential smoothing method, temporal convolutional network

CLC Number:

TP393

Xiaolan XIE,Zhengzheng ZHANG,Jianwei WANG,Xiaochun GHENG. Cloud resource prediction model based on triple exponential smoothing method and temporal convolutional network[J]. Journal on Communications, 2019, 40(8): 143-150.

Figures/Tables 5

References 33

[1]	BERNSTEIN D . Containers and cloud:from LXC to docker to Kubernetes[J]. IEEE Cloud Computing, 2014,1(3): 81-84.
[2]	FU S , LIU J , CHU X ,et al. Toward a standard interface for cloud providers:the container as the narrow waist[J]. IEEE Internet Computing, 2016,20(2): 66-71.
[3]	VARGHESE B , SUBBA L T , THAI L ,et al. Container-based cloud virtual machine benchmarking[C]// 2016 IEEE International Conference on Cloud Engineering (IC2E). IEEE, 2016: 192-201.
[4]	XIE X L , YUAN T W , ZHOU X ,et al. Research on trust model in container-based cloud service[J]. Computers,Materials and Continua, 2018,56(2): 273-283.
[5]	ISLAM S , KEUNG J , LEE K ,et al. Empirical prediction models for adaptive resource provisioning in the cloud[J]. Future Generation Computer Systems, 2012,28(1): 155-162.
[6]	DI S , KONDO D , CIRNE W . Characterization and comparison of cloud versus grid workloads[C]// 2012 IEEE International Conference on Cluster Computing. IEEE, 2012: 230-238.
[7]	XU D , YANG S , LIU R . A mixture of HMM,GA,and Elman network for load prediction in cloud-oriented data centers[J]. Journal of Zhejiang University:Science C, 2013,14(11): 845-858.
[8]	BASHAR A , . Autonomic scaling of cloud computing resources using BN-based prediction models[C]// 2013 IEEE 2nd International Conference on Cloud Networking. IEEE, 2013: 200-204.
[9]	HU R , JIANG J , LIU G ,et al. KSwSVR:a new load forecasting method for efficient resources provisioning in cloud[C]// 2013 IEEE International Conference on Services Computing. IEEE, 2013: 120-127.
[10]	RASHEDUZZAMAN M , ISLAM M A , RAHMAN R M . Workload prediction on Google cluster trace[J]. International Journal of Grid and High Performance Computing, 2014,6(3): 34-52.
[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(11): 4072-4083.
[12]	SHYAM G K , MANVI S S . Virtual resource prediction in cloud environment:a Bayesian approach[J]. Journal of Network and Computer Applications, 2016,65: 144-154.
[13]	JIANG Y , PERNG C , LI T ,et al. Asap:a self-adaptive prediction system for instant cloud resource demand provisioning[C]// 2011 IEEE 11th International Conference on Data Mining. IEEE, 2011: 1104-1109.
[14]	ZHANG Q , ZHANI M F , BOUTABA R ,et al. Harmony:dynamic heterogeneity-aware resource provisioning in the cloud[C]// 2013 IEEE 33rd International Conference on Distributed Computing Systems. IEEE, 2013: 510-519.
[15]	CALHEIROS R N , MASOUMI E , RANJAN R ,et al. Workload prediction using ARIMA model and its impact on cloud applications’ QoS[J]. IEEE Transactions on Cloud Computing, 2015,3(4): 449-458.
[16]	田鹤, 赵海, 王进法 ,等. 互联网传播行为的时序演化与预测[J]. 通信学报, 2018,39(6): 116-126.
	TIAN H , ZHAO H , WANG J F ,et al. Timing evolution and prediction of Internet transmission behavior[J]. Journal on Communications, 2018,39(6): 116-126.
[17]	冯宁, 郭晟楠, 宋超 ,等. 面向交通流量预测的多组件时空图卷积网络[J]. 软件学报, 2019,30(3): 759-769.
	FENG N , GUO S N , SONG C ,et al. Multi-component spatial-temporal graph convolution networks for traffic flow forecasting[J]. Journal of Software, 2019,30(3): 759-769.
[18]	屈景怡, 叶萌, 渠星 . 基于区域残差和LSTM网络的机场延误预测模型[J]. 通信学报, 2019,40(4): 149-159.
	QU J Y , YE M , QU X . Airport delay prediction model based on regional residual and LSTM network[J]. Journal on Communications, 2019,40(4): 149-159.
[19]	BAI S , KOLTER J Z , KOLTUN V . An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[J]. arXiv Preprint,arXiv:1803.01271, 2018
[20]	BUI D M , NGUYEN H Q , YOON Y I ,et al. Gaussian process for predicting CPU utilization and its application to energy efficiency[J]. Applied Intelligence, 2015,43(4): 874-891.
[21]	BARATI M , SHARIFIAN S . A hybrid heuristic-based tuned support vector regression model for cloud load prediction[J]. The Journal of Supercomputing, 2015,71(11): 4235-4259.
[22]	HU W , YAN L , LIU K ,et al. A short-term traffic flow forecasting method based on the hybrid PSO-SVR[J]. Neural Processing Letters, 2016,43(1): 155-172.
[23]	CHEN N , AGARWAL A , WIERMAN A ,et al. Online convex optimization using predictions[C]// ACM SIGMETRICS Performance Evaluation Review. ACM, 2015: 191-204.
[24]	HUANG L , CHEN M , LIU Y . Learning-aided stochastic network optimization with imperfect state prediction[C]// The 18th ACM International Symposium on Mobile Ad Hoc Networking and Computing. ACM, 2017:12.
[25]	CHEN K , HUANG L . Timely-throughput optimal scheduling with prediction[J]. IEEE/ACM Transactions on Networking, 2018,26(6): 2457-2470.
[26]	CAO J , FU J , LI M ,et al. CPU load prediction for cloud environment based on a dynamic ensemble model[J]. Software:Practice and Experience, 2014,44(7): 793-804.
[27]	SUBIRATS J , GUITART J . Assessing and forecasting energy efficiency on cloud computing platforms[J]. Future Generation Computer Systems, 2015,45: 70-94.
[28]	MESSIAS V R , ESTRELLA J C , EHLERS R ,et al. Combining time series prediction models using genetic algorithm to autoscaling web applications hosted in the cloud infrastructure[J]. Neural Computing and Applications, 2016,27(8): 2383-2406.
[29]	KAUR G , BALA A , CHANA I . An intelligent regressive ensemble approach for predicting resource usage in cloud computing[J]. Journal of Parallel and Distributed Computing, 2019,123: 1-12.
[30]	HUANG J , LI C , YU J . Resource prediction based on double exponential smoothing in cloud computing[C]// 2012 2nd International Conference on Consumer Electronics,Communications and Networks . IEEE, 2012: 2056-2060.
[31]	YOU J , WANG Y , PAL A ,et al. Hierarchical temporal convolutional networks for dynamic recommender systems[C]// The World Wide Web Conference. ACM, 2019: 2236-2246.
[32]	HE K , ZHANG X , REN S ,et al. Deep residual learning for image recognition[C]// IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2016: 770-778.
[33]	OLSON R S , URBANOWICZ R J , ANDREWS P C ,et al. Automating biomedical data science through tree-based pipeline optimization[C]// European Conference on the Applications of Evolutionary Computation. Springer, 2016: 123-137.

Metrics

Recommended 0

No Suggested Reading articles found!

α值	适用情况
0.10~0.30	时间序列呈现水平趋势
0.30~0.50	序列有波动但长期趋势变化不大
0.60~0.80	序列波动较大且呈现明显上升或下降趋势

参数	值
kernel_size	2
n_layers	6
n_filters	32
learning_rate	0.000 75
training_steps	10 000
ω₁(CPU)	0.4
ω₂(CPU)	0.6
α(CPU)	0.390 73
ω₁(memory)	0.27
ω₂(memory)	0.73
α(memory)	0.344 37

Cloud resource prediction model based on triple exponential smoothing method and temporal convolutional network

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 5

References 33

Related Articles 1

Metrics

Recommended 0