Cloud Database Product Usage Prediction Based on Component Decomposition and Multimodal Fusion

doi:10.19678/j.issn.1000-3428.0069841

Abstract

Abstract:

Cloud database technology has been widely used because of its flexible expansion, ease of management, and on-demand charging. Businesses usually select cloud database products based on their specific application scenarios and requirements. Service providers determine the usage of different types of resources, such as computing and storage, to satisfy service requirements. Accurate prediction of cloud product usage is critical for improving resource usage efficiency, reducing operational costs, and ensuring Quality of Service (QoS). However, predicting cloud database product usage is complex. A usage sequence typically comprises multiple interrelated components with complex entanglements. Additionally, the behavioral characteristics of different businesses vary according to cloud products and billing items, which poses a significant challenge for accurate usage prediction. To solve this problem, this study proposes a cloud database product usage prediction model based on component decomposition and multimodal fusion. This model effectively decomposes a time-series with complex entanglement, fuses multimodal demand data, builds a mapping relationship between demand and usage trends, and automatically adjusts the weight parameters of its components to obtain accurate prediction results. In this study, real production data from four major cloud database products from the Ali cloud computing service providers are used to evaluate the prediction effect and the performance is compared with that of five other prediction algorithms. Analyses of evaluation metrics, such as the Mean Absolute Percentage Error (MAPE), reveal that the proposed model improves prediction accuracy to different degrees in the four cloud database products, approximately 18.6%-51.8%. Therefore, this model can be applied to cloud database product usage prediction scenarios and help cloud service providers in improving the accuracy of resource capacity planning.

Key words: cloud computing, cloud database product, time-series, component decomposition, multimodal

摘要：

云数据库技术以其灵活扩展、易于管理、按需收费等特点得到了广泛应用。业务方通常根据自身应用场景和实际需求选择云数据库产品, 而服务提供商确定产品中不同类型资源(如计算资源和存储资源的用量)来满足业务方的业务需求。云产品用量的准确预测对于提升资源使用效率、降低运营成本、保障服务质量(QoS)至关重要。然而, 云数据库产品用量预测场景复杂, 用量序列通常由存在复杂纠缠的多个成分组成, 并且不同业务方在不同云产品及计费项下的行为特征差异较大, 这对用量预测提出了巨大的挑战。针对这一难题, 提出一种基于成分分解和多模态融合的云数据库产品用量预测模型。该模型对存在复杂纠缠的时间序列进行成分分解, 融合多模态需求数据, 构建需求趋势与用量趋势之间的映射关系, 并通过自动调节成分的权重参数以获得准确的预测结果, 同时使用阿里云计算服务商的4个主要云数据库产品的真实生产数据进行预测效果评估, 并与5种预测算法进行性能比较。通过分析平均绝对百分比误差(MAPE)等评估指标, 实验结果表明, 该预测模型在4个云数据库产品中都有不同程度的预测准确率提升, 约18.6%~51.8%, 能更好地适用于云数据库产品用量预测场景, 有助于云服务提供商进行更准确的资源容量规划。

关键词: 云计算, 云数据库产品, 时间序列, 成分分解, 多模态

YANG Dingyu, DENG Yufeng, QIAN Shiyou, CAO Jian, XUE Guangtao. Cloud Database Product Usage Prediction Based on Component Decomposition and Multimodal Fusion[J]. Computer Engineering, 2026, 52(3): 355-363.

杨定裕, 邓喻丰, 钱诗友, 曹健, 薛广涛. 基于成分分解和多模态融合的云数据库产品用量预测[J]. 计算机工程, 2026, 52(3): 355-363.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069841

https://www.ecice06.com/EN/Y2026/V52/I3/355

Figures/Tables 9

Fig.1 Complex entangled time-series of multiple components

Fig.2 Prediction model architecture

Fig.3 Comparison of predicted MAPE for different cloud products

Fig.4 Comparison of predicted variance for different cloud products

Fig.5 Comparison of prediction errors in ablation experiments

References 31

1	RAMANATHAN S, GOEL S, ALAGUMALAI S. Comparison of cloud database: Amazon's SimpleDB and Google's bigtable[C]//Proceedings of the International Conference on Recent Trends in Information Systems. Washington D.C., USA: IEEE Press, 2011: 165-168.
2	段宏伟, 郇甜甜, 白彦辉. 扩充关系型激光点云数据库语义精准标注方法. 激光杂志, 2025, 46 (9): 202- 207.
	DUAN H W , HUAN T T , BAI Y H . Semantic precise annotation method for expanding relational laser point cloud database. Laser Journal, 2025, 46 (9): 202- 207.
3	姜文, 徐洋, 孙艺璇. 基于云数据库的医疗数据互通系统设计研究. 山西电子技术, 2025 (5): 99- 101.
	JIANG W , XU Y , SUN Y X . Research on the design of medical data interoperability system based on cloud database. Shanxi Electronic Technology, 2025 (5): 99- 101.
4	SINGH B , MARTYR R , MEDLAND T , et al. Cloud based evaluation of databases for stock market data. Journal of Cloud Computing, 2022, 11 (1): 53. doi: 10.1186/s13677-022-00323-4
5	DURNER D , CHANDRAMOULI B , LI Y N . Crystal. Proceedings of the VLDB Endowment, 2021, 14 (11): 2432- 2444. doi: 10.14778/3476249.3476292
6	LIU Q . A high performance memory key-value database based on Redis. Journal of Computers, 2019, 14 (3): 170- 183. doi: 10.17706/jcp.14.3.170-183
7	ZHANG Y D , LIU F G , WANG B , et al. A multi-output prediction model for physical machine resource usage in cloud data centers. Future Generation Computer Systems, 2022, 130, 292- 306. doi: 10.1016/j.future.2022.01.002
8	CHEN H X, FU X, TANG Z R, et al. Resource monitoring and prediction in cloud computing environments[C]//Proceedings of the 3rd International Conference on Applied Computing and Information Technology/2nd International Conference on Computational Science and Intelligence. Washington D.C., USA: IEEE Press, 2015: 288-292.
9	LUO S T, XU H L, LU C Z, et al. Characterizing microservice dependency and performance: Alibaba trace analysis[C]//Proceedings of the ACM Symposium on Cloud Computing. New York, USA: ACM Press, 2021: 412-426.
10	LUO S T, XU H L, YE K J, et al. The power of prediction: microservice auto scaling via workload learning[C]//Proceedings of the 13th Symposium on Cloud Computing. New York, USA: ACM Press, 2022: 355-369.
11	ALDOSSARY M . A review of dynamic resource management in cloud computing environments. Computer Systems Science and Engineering, 2021, 36 (3): 461- 476. doi: 10.32604/csse.2021.014975
12	CHEN S, DELIMITROU C, MARTÍNEZ J F. PARTIES: QoS-aware resource partitioning for multiple interactive services[C]//Proceedings of the 24th International Conference on Architectural Support for Programming Languages and Operating Systems. New York, USA: ACM Press, 2019: 107-120.
13	YAN M , LIANG X M , LU Z H , et al. HANSEL: adaptive horizontal scaling of microservices using Bi-LSTM. Applied Soft Computing, 2021, 105, 107216. doi: 10.1016/j.asoc.2021.107216
14	ZHOU D C , CHEN H C , SHANG K , et al. Cushion: a proactive resource provisioning method to mitigate SLO violations for containerized microservices. IET Communications, 2022, 16 (17): 2105- 2122. doi: 10.1049/cmu2.12464
15	RAMPÉREZ V , SORIANO J , LIZCANO D , et al. FLAS: a combination of proactive and reactive auto-scaling architecture for distributed services. Future Generation Computer Systems, 2021, 118, 56- 72. doi: 10.1016/j.future.2020.12.025
16	RZADCA K, FINDEISEN P, SWIDERSKI J, et al. Autopilot: workload autoscaling at Google[C]//Proceedings of the 15th European Conference on Computer Systems. New York, USA: ACM Press, 2020: 1-16.
17	杨哲兴, 谢晓兰, 李水旺. 基于VDM-ISSA-LSSVM的云资源短期负载预测模型. 实验室研究与探索, 2023, 42 (6): 117- 124.
	YANG Z X , XIE X L , LI S W . Short term load prediction model for cloud resources based on VMD-ISSA-LSSVM. Research and Exploration in Laboratory, 2023, 42 (6): 117- 124.
18	EDIGER V S , AKAR S . ARIMA forecasting of primary energy demand by fuel in Turkey. Energy Policy, 2007, 35 (3): 1701- 1708. doi: 10.1016/j.enpol.2006.05.009
19	GARDNER E S . Exponential smoothing: the state of the art: part Ⅱ. International Journal of Forecasting, 2006, 22 (4): 637- 666. doi: 10.1016/j.ijforecast.2006.03.005
20	TAYLOR S J , LETHAM B . Forecasting at scale. The American Statistician, 2018, 72 (1): 37- 45. doi: 10.1080/00031305.2017.1380080
21	TRIEBE O, HEWAMALAGE H, PILYUGINA P, et al. NeuralProphet: explainable forecasting at scale[EB/OL]. [2024-04-11]. https://arxiv.org/abs/2111.15397.
22	HOCHREITER S , SCHMIDHUBER J . Long short-term memory. Neural Computation, 1997, 9 (8): 1735- 1780. doi: 10.1162/neco.1997.9.8.1735
23	赵鹏, 周建涛, 赵大明. 基于CEEMDAN-ConvLSTM组合模型的云计算负载预测方法. 计算机科学, 2023, 50 (S1): 652- 660.
	ZHAO P , ZHOU J T , ZHAO D M . Cloud computing load forecasting method based on CEEMDAN-ConvLSTM combined model. Computer Science, 2023, 50 (S1): 652- 660.
24	ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: beyond efficient Transformer for long sequence time-series forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2021: 11106-11115.
25	WU H , XU J , WANG J , et al. Autoformer: decomposition Transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems, 2021, 34, 22419- 22430.
26	李浩阳, 贺小伟, 王宾, 等. 基于改进Informer的云计算资源负载预测. 计算机工程, 2024, 50 (2): 43- 50. doi: 10.19678/j.issn.1000-3428.0066399
	LI H Y , HE X W , WANG B , et al. Cloud computing resource load prediction based on improved Informer. Computer Engineering, 2024, 50 (2): 43- 50. doi: 10.19678/j.issn.1000-3428.0066399
27	李姜辛, 王鹏, 汪卫. 多机理指导的深度学习工业时序预测框架. 计算机工程, 2025, 51 (7): 47- 58. doi: 10.19678/j.issn.1000-3428.0069406
	LI J X , WANG P , WANG W . Multi-mechanism-guided deep learning framework for industrial time-series forecasting. Computer Engineering, 2025, 51 (7): 47- 58. doi: 10.19678/j.issn.1000-3428.0069406
28	ZHOU T, MA Z Q, WEN Q S, et al. FEDformer: frequency enhanced decomposed Transformer for long-term series forecasting[C]//Proceedings of the 39th International Conference on Machine Learning. [S. l. ]: ICML, 2025: 27268-27286.
29	MONTEIL J, DEKUSAR A, GAMBELLA C, et al. Deep learning to scale up time series traffic prediction[EB/OL]. [2024-04-11]. https://doi.org/10.48550/arXiv.1911.13042.
30	SOARES E , COSTA P , COSTA B , et al. Ensemble of evolving data clouds and fuzzy models for weather time series prediction. Applied Soft Computing, 2018, 64, 445- 453. doi: 10.1016/j.asoc.2017.12.032
31	MARIO L, THOMAS F, VINCENT G. Identification, modelling and prediction of non-periodic bursts in workloads[C]//Proceedings of the 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing. Washington D.C., USA: IEEE Press, 2010: 485-494.

[1]	CHEN Guolian, FENG Ziyang, CAO Junkuo. Research on Cyberbullying Detection Based on Multimodal Spatial Feature Fusion [J]. Computer Engineering, 2026, 52(3): 255-263.
[2]	ZHANG Tianzhi, ZHOU Gang, ZHANG Shuang, CHEN Jing, HUANG Ningbo, WU Hao. Target-Entity Sentiment Classification with Image-Text Multimodal Entity Alignment [J]. Computer Engineering, 2026, 52(3): 222-233.
[3]	LIU Xiaoyu, LIAO Zhifang, TAN Sui, YU Zhiwu. Bridge Dynamic Strain Prediction Based on Stacked GRU Neural Network [J]. Computer Engineering, 2026, 52(3): 441-450.
[4]	SU Jianhua, CHI Yunxian, XU Yunfeng, GAO Kai. Multimodal Intent Recognition Based on Attention Modality Fusion [J]. Computer Engineering, 2026, 52(3): 234-242.
[5]	SUN Wei, CHEN Junjie. MF-cache: CLIP-Based Multimodal Cache Model for Maize Disease Recognition [J]. Computer Engineering, 2026, 52(3): 420-428.
[6]	WANG Limin, ZHU Guanghui, WU Tao. Evolution of Large Model Technologies: World Models Drive Artificial Intelligence from Perception to Decision-Making (Invited) [J]. Computer Engineering, 2026, 52(2): 1-6.
[7]	ZENG Biqing, YAO Yongtao, XIE Liangqi, CHEN Pengfei, DENG Huimin, WANG Ruitang. Multimodal Aspect-Based Sentiment Analysis Combining Local Perception and Multi-Level Attention [J]. Computer Engineering, 2025, 51(9): 80-90.
[8]	LI Jiangxin, WANG Peng, WANG Wei. Multi-mechanism-guided Deep Learning Framework for Industrial Time-series Forecasting [J]. Computer Engineering, 2025, 51(7): 47-58.
[9]	LONG Liye, JIAO Shichao, GUO Lei, HAN Xie, KUANG Liqun. Multimodal 3D Model Retrieval Based on Compact Center Loss [J]. Computer Engineering, 2025, 51(2): 322-334.
[10]	FENG Saisai, GE Dongfeng, LI Tao, LIU Yijing, JI Zhihang, WANG Lin, ZHANG Mingchuan. Assisted Diagnosis of Cervical Intraepithelial Neoplasia Based on Multimodal Fusion [J]. Computer Engineering, 2025, 51(12): 304-310.
[11]	FAN Yiying, GUO Wei. Dual-Branch SAR Image Ship Detection Method Based on Time-Series Images [J]. Computer Engineering, 2025, 51(12): 31-42.
[12]	FENG Shuai, GAO Jian. Malicious Code Classification Method Based on Multidimensional Feature Fusion [J]. Computer Engineering, 2025, 51(12): 232-243.
[13]	ZHANG Xiaoming, CHEN Tongqing, WANG Huiyong. Dynamic Guided Multimodal Entity Alignment Based on Image Confidence [J]. Computer Engineering, 2025, 51(12): 140-150.
[14]	ZHOU Shixiang, YU Kai. Multimodal Sentiment Analysis Based on Dense Co-Attention [J]. Computer Engineering, 2025, 51(11): 144-151.
[15]	LI Yakang, LI Jianfang, HU Peng, CHEN Juan, WANG Shengxiang, QI Fazhi, CHEN Gang. A Survey of Artificial Intelligence Applications Throughout the Full Lifecycle of Neutron Scattering Experiments [J]. Computer Engineering, 2025, 51(10): 53-70.

Please choose a citation manager

Content to export