Resource load prediction model based on long-short time series feature fusion

doi:10.11772/j.issn.1001-9081.2021030393

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (5): 1508-1515.DOI: 10.11772/j.issn.1001-9081.2021030393

• Advanced computing • Previous Articles Next Articles

Resource load prediction model based on long-short time series feature fusion

Yifei WANG¹, Lei YU²^,³, Fei TENG¹(), Jiayu SONG¹, Yue YUAN¹

^1.School of Information Sciences and Technology，Southwest Jiaotong University，Chengdu Sichuan 610000，China
^2.Sino? french Engineer School，Beihang University，Beijing 100000，China
^3.Beihang Hangzhou Institute for Innovation at Yuhang，Hangzhou Zhejiang 310000，China

Received:2021-03-16 Revised:2021-06-08 Accepted:2021-06-11 Online:2022-06-11 Published:2022-05-10
Contact: Fei TENG
About author:WANG Yifei， born in 1996， M. S. candidate. Her researchinterests include cloud computing，big data mining.
YU Lei， born in 1972，Ph. D.，associate professor. His researchinterests include energy consumption optimization and simulation of big data computing center，image processing based on deep learning，natural language processing and classification.
TENG Fei， born in 1984，Ph. D.，associate professor. Her researchinterests include cloud computing，medical informatics，industrial big data mining.
SONG Jiayu， born in 1995， M. S. candidate. Her researchinterests include big data mining，time series prediction.
YUAN Yue， born in 1997，M. S. candidate. Her research interestsinclude big data mining，deep learning.
Supported by:
Science and Technology Project of Sichuan Province(2019YJ0214);Natural Science Foundation of Beijing(4192030)

基于长-短时序特征融合的资源负载预测模型

王艺霏¹, 于雷²^,³, 滕飞¹(), 宋佳玉¹, 袁玥¹

^1.西南交通大学信息科学与技术学院, 成都 610000
^2.北京航空航天大学中法工程师学院, 北京 100000
^3.北京航空航天大学杭州创新研究院(余杭), 杭州 310000

通讯作者: 滕飞
作者简介:王艺霏（1996—），女，山西吕梁人，硕士研究生，主要研究方向：云计算、大数据挖掘
于雷（1972—），男，山东淄博人，副教授，博士，主要研究方向：大数据计算中心能耗优化与仿真、基于深度学习的图像处理、自然语言处理与分类
滕飞（1984—），女，山东淄博人，副教授，博士，CCF会员，主要研究方向：云计算、医疗信息、工业大数据挖掘 fteng@swjtu.edu.cn
宋佳玉（1995—），女，四川成都人，硕士研究生，主要研究方向：大数据挖掘、时间序列预测
袁玥（1997—），女，四川泸州人，硕士研究生，主要研究方向：大数据挖掘、深度学习。
基金资助:
四川省科技项目(2019YJ0214);北京市自然科学基金资助项目(4192030)

Abstract

Abstract:

Resource load prediction with high accuracy can provide a basis for real-time task scheduling， thus reducing energy consumption. However， most prediction models for time series of resource load make short-term or long-term prediction by extracting the long-time series dependence characteristics of time series and neglecting the short-time series dependence characteristics of time series. In order to make a better long-term prediction of resource load， a new edge computing resource load prediction model based on long-short time series feature fusion was proposed. Firstly， the Gram Angle Field （GAF） was used to transform time series into image format data， so as to extract features by Convolutional Neural Network （CNN）. Then， the CNN was used to extract spatial features and short-term data features， the Long Short-Term Memory （LSTM） network was used to extract the long-term time series dependent features of time series. Finally， the extracted long-term and short-term time series dependent features were fused through dual-channel to realize long-term resource load prediction. Experimental results show that， the Mean Absolute Error （MAE）， Root Mean Square Error （RMSE） and R-squared（R²） of the proposed model for CPU resource load prediction in Alibaba cloud clustering tracking dataset are 3.823， 5.274， and 0.815 8 respectively. Compared with the single-channel CNN and LSTM models， dual-channel CNN+LSTM and ConvLSTM+LSTM models， and resource load prediction models such as LSTM Encoder-Decoder （LSTM-ED） and XGBoost， the proposed model can provide higher prediction accuracy.

Key words: resource load prediction, Convolution Neural Network (CNN), Long Short-Term Memory (LSTM) network, Gram Angle Field (GAF), dual-channel, time series prediction

摘要：

高准确率的资源负载预测能够为实时任务调度提供依据，从而降低能源消耗。但是，针对资源负载的时间序列的预测模型，大多是通过提取时间序列的长时序依赖特性来进行短期或者长期预测，忽略了时间序列中的短时序依赖特性。为了更好地对资源负载进行长期预测，提出了一种基于长-短时序特征融合的边缘计算资源负载预测模型。首先，利用格拉姆角场（GAF）将时间序列转变为图像格式数据，以便利用卷积神经网络（CNN）来提取特征；然后，通过卷积神经网络提取空间特征和短期数据的特征，用长短期记忆（LSTM）网络来提取时间序列的长时序依赖特征；最后，将所提取的长、短时序依赖特征通过双通道进行融合，从而实现长期资源负载预测。实验结果表明，所提出的模型在阿里云集群跟踪数据集CPU资源负载预测中的平均绝对误差（MAE）为3.823，均方根误差（RMSE）为5.274，拟合度（R²）为0.815 8，相较于单通道的CNN和LSTM模型、双通道CNN+LSTM和ConvLSTM+LSTM模型，以及资源负载预测模型LSTM-ED和XGBoost，所提模型的预测准确率更高。

关键词: 资源负载预测, 卷积神经网络, 长短期记忆网络, 格拉姆角场, 双通道, 时间序列预测

CLC Number:

TP391

Yifei WANG, Lei YU, Fei TENG, Jiayu SONG, Yue YUAN. Resource load prediction model based on long-short time series feature fusion[J]. Journal of Computer Applications, 2022, 42(5): 1508-1515.

王艺霏, 于雷, 滕飞, 宋佳玉, 袁玥. 基于长-短时序特征融合的资源负载预测模型[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1508-1515.

Figures/Tables 14

Fig. 1 Structure of CNN

Fig. 2 Time expansion of RNN

Fig. 3 Structure of LSTM

Fig. 4 Structure of GAF-CNN-LSTM model

Fig. 5 Structure of ConvlSTM channel model

Fig. 6 Sample construction of ConvLSTM channel data

Tab. 1 ConvLSTM channel configuration

网络层	参数
ConvLSTM2D	卷积核大小为64，卷积步长为（3，3）
LSTM（两层）	隐藏层为10
FC（两层）	输入维度为36，输出维度为6

Tab. 2 LSTM channel configuration

网络层	参数
LSTM1	隐藏层为36
LSTM2	隐藏层为20
FC	输出维度为6

Tab. 3 Comparison of single-channel and dual-channel results

模型	RMSE	MAE	R²
LSTM（单通道）^［20］	6.167	4.492	0.658 0
CNN（单通道）^［19］	6.975	5.131	0.562 7
CNN+LSTM（双通道）	5.375	3.902	0.740 1
ConvLSTM+LSTM+MLP（双通道）	5.412	3.952	0.736 0
ConvLSTM+LSTM（双通道）	5.274	3.823	0.815 8

Fig. 7 Comparison between predicted values of dual-channel model and actual values

Fig. 8 Coparison of R2 between CNN and LSTM

Fig. 9 Comparison of R2 with different inputs

Tab. 4 Performance comparison of proposed model and benchmark models

模型	RMSE	MAE	R²
ConvLSTM+LSTM	5.274	3.823	0.815 8
LSTM-ED	5.715	4.211	0.706 1
XGBoost	7.037	5.294	0.814 0

Fig. 10 Comparison of training loss functions ofdifferent models

References 22

1	SUN X， ANSARI N， WANG R. Optimizing resource utilization of a data center ［J］. IEEE Communications Surveys & Tutorials， 2016， 18（4）： 2822-2846. 10.1109/comst.2016.2558203
2	PREVOST J， NAGOTHU K， KELLEY B， et al. Prediction of cloud data center networks loads using stochastic and neural models ［C］// Proceedings of the 2011 6th International Conference on System of Systems Engineering. Piscataway： IEEE， 2011： 276-281. 10.1109/sysose.2011.5966610
3	ZHANG Q， ZHANI M F， BOUTABA R， et al. HARMONY： dynamic heterogeneity-aware resource provisioning in the cloud ［C］// Proceedings of the 2013 33rd International Conference on Distributed Computing Systems. Piscataway： IEEE， 2013： 510-519. 10.1109/icdcs.2013.28
4	KUMAR T L M， SURENDRA H S， MUNIRAJAPPA R. Holt-winters exponential smoothing and sesonal ARIMA time-series technique for forecasting of onion price in Bangalore market ［J］. Mysore Journal of Agricultural Sciences， 2011， 2（1）： 602-607.
5	LI Q， HAO Q F， XIAO L M， et al. An Integrated approach to automatic management of virtualized resources in cloud environments ［J］. Computer Journal， 2011， 54（6）： 905-919. 10.1093/comjnl/bxq082
6	SUN Y S， CHEN Y F， CHEN M C. A workload analysis of live event broadcast service in cloud ［J］. Procedia Computer Science， 2013， 19（1）： 1028-1033. 10.1016/j.procs.2013.06.143
7	VERCAUTEREN T， AGGARWAL P， WANG X， et al. Hierarchical forecasting of web server workload using sequential Monte Carlo training ［J］. IEEE Transactions on Signal Processing， 2007， 55（4）： 1286-1297. 10.1109/tsp.2006.889401
8	ARDAGNA D， CASOLARI S， COLAJANNI M， et al. Dual time-scale distributed capacity allocation and load redirect algorithms for cloud systems ［J］. Journal of Parallel and Distributed Computing， 2012， 72（6）： 796-808. 10.1016/j.jpdc.2012.02.014
9	ROY N， DUBEY A， GOKHALE A. Efficient autoscaling in the cloud using predictive models for workload forecasting ［C］// Proceedings of the 2011 International Conference on Cloud Computing. Piscataway： IEEE， 2011： 500-507. 10.1109/cloud.2011.42
10	RAJARAM K， MALARVIZHI M P. Utilization based prediction model for resource provisioning ［C］// Proceedings of the 2017 International Conference on Computer. Piscataway： IEEE， 2017：1-6. 10.1109/icccsp.2017.7944099
11	KATTEPUR A， NAMBIAR M. Service demand modeling and performance prediction with single-user tests ［J］. Performance Evaluation， 2017， 110（4）： 1-21. 10.1016/j.peva.2017.02.003
12	CAO L. Support vector machines experts for time series forecasting ［J］. Neurocomputing， 2003， 51（4）： 321-339. 10.1016/s0925-2312(02)00577-5
13	EDDAHECH A， CHTOUROUS S， CHTOUROU M. Hierarchical neural networks based prediction and control of dynamic reconfiguration for multilevel embedded systems ［J］. Journal of Systems Architecture， 2013， 59（1）： 48-59. 10.1016/j.sysarc.2012.11.002
14	DANG T， TRAN N， NGUYEN B M， et al. PD-GABP： A novel prediction model applying for elastic applications in distributed environment ［C］// Proceedings of the 2016 3rd National Foundation for Science and Technology Development Conference on Information and Computer Science. Piscataway： IEEE， 2016： 240-248. 10.1109/nics.2016.7725658
15	ZHANG G， PATUWO B E， HU M Y. Forecasting with artificial neural networks： the state of the art ［J］. International Journal of Forecasting， 1998， 14（1）： 35-62.
16	VENKATESAN. A genetic algorithm based artificial neural network model for the optimization of machining processes ［J］. Neural Computing and Applications， 2009， 2（1）： 135-140.
17	VAZQUEZ C. Time series forecasting of cloud data center workloads for dynamic resource provisioning ［D］. San Antonio： The University of Texas at San Antonio， 2015： 10-15.
18	REN S， HE K， GIRSHICK R， et al. Faster R-CNN： towards real-time object detection with region proposal networks ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 39（6）： 1137-1149. 10.1109/tpami.2016.2577031
19	胡荣磊，芮璐，齐筱，等.基于循环神经网络和注意力模型的文本情感分析［J］.计算机应用研究，2019，36（11）：3282-3285. 10.19734/j.issn.1001-3695.2018.05.0300
	HU R L， RUI L， QI X， et al. A novel approach to contextual sentiment analysis based on a neural network and attention model ［J］. Application Research of Computer， 2019， 36（11）： 3282-3285. 10.19734/j.issn.1001-3695.2018.05.0300
20	WANG Z， OATES T. Imaging time-series to improve classification and imputation ［C］// Proceedings of the 2015 24th International Conference on Artificial Intelligence. Menlo Park： AAAI Press， 2015： 3939-3945.
21	NGUYEN H M， KALRA G， KIM D. Host load prediction in cloud computing using long short-term memory encoder-decoder ［J］. Journal of supercomputing， 2019， 75（11）： 7592-7605. 10.1007/s11227-019-02967-7
22	CHEN T， GUESTRIN C. XGBoost： a scalable tree boosting system ［EB/OL］. ［2016-06-09］. . 10.1145/2939672.2939785

[1]	Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738.
[2]	Shangbin MO, Wenjun WANG, Ling DONG, Shengxiang GAO, Zhengtao YU. Single-channel speech enhancement based on multi-channel information aggregation and collaborative decoding [J]. Journal of Computer Applications, 2024, 44(8): 2611-2617.
[3]	Yu ZENG, Yang ZHANG, Shang ZENG, Maoli FU, Qixue HE, Linlong ZENG. Time series prediction algorithm based on multi-scale gated dilated convolutional network [J]. Journal of Computer Applications, 2024, 44(11): 3427-3434.
[4]	Xiaoyu HUA, Dongfen LI, You FU, Kejun BI, Shi YING, Ruijin WANG. Industrial chain risk assessment and early warning model combining hierarchical graph neural network and long short-term memory [J]. Journal of Computer Applications, 2024, 44(10): 3223-3231.
[5]	Hanxiao SHI, Leichun WANG. Short-term power load forecasting by graph convolutional network combining LSTM and self-attention mechanism [J]. Journal of Computer Applications, 2024, 44(1): 311-317.
[6]	Li’an CHEN, Yi GUO. Text sentiment analysis model based on individual bias information [J]. Journal of Computer Applications, 2024, 44(1): 145-151.
[7]	Zhiping ZHU, Yan YANG, Jie WANG. Scene graph-aware cross-modal image captioning model [J]. Journal of Computer Applications, 2024, 44(1): 58-64.
[8]	Jiagao WU, Shiwen ZHANG, Yudong JIANG, Linfeng LIU. Social-interaction GAN for pedestrian trajectory prediction based on state-refinement long short-term memory and attention mechanism [J]. Journal of Computer Applications, 2023, 43(5): 1565-1570.
[9]	Haiyu YANG, Wenpu GUO, Kai KANG. Signal modulation recognition method based on convolutional long short-term deep neural network [J]. Journal of Computer Applications, 2023, 43(4): 1318-1322.
[10]	Zhenliang LI, Bo LI. Improved method of convolution neural network based on matrix decomposition [J]. Journal of Computer Applications, 2023, 43(3): 685-691.
[11]	Chunyong YIN, Liwen ZHOU. Unsupervised time series anomaly detection model based on re-encoding [J]. Journal of Computer Applications, 2023, 43(3): 804-811.
[12]	Bennian YU, Yongzhao ZHAN, Qirong MAO, Wenlong DONG, Honglin LIU. Double complex convolution and attention aggregating recurrent network for speech enhancement [J]. Journal of Computer Applications, 2023, 43(10): 3217-3224.
[13]	ZHANG Jun, WU Pengli, SHI Lukui, SHI Jin, PAN Bin. Deep learning model for multi-station temperature prediction combined with MOD11A1 and surface meteorological station data [J]. Journal of Computer Applications, 2023, 43(1): 321-328.
[14]	LIU Hui, MA Xiang, ZHANG Linyu, HE Rujin. Aspect-based sentiment analysis model integrating match-LSTM network and grammatical distance [J]. Journal of Computer Applications, 2023, 43(1): 45-50.
[15]	Minghui WU, Guangjie ZHANG, Canghong JIN. Time series prediction model based on multimodal information fusion [J]. Journal of Computer Applications, 2022, 42(8): 2326-2332.

Resource load prediction model based on long-short time series feature fusion

基于长-短时序特征融合的资源负载预测模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 22

Related Articles 15

Recommended Articles

Metrics