Comparison of Microservice Call Rate Predictions for Replication in the Cloud
Authors: 
Narges Mehran, Arman Haghighi, 
Pedram Aminharati, Nikolay Nikolov, 
Ahmet Soylu, Dumitru Roman, Radu ProdanAuthors Info & Claims
Narges Mehran, Arman Haghighi, Pedram Aminharati, Nikolay Nikolov, Ahmet Soylu, Dumitru Roman, Radu ProdanAuthors Info & ClaimsArticle No.: 51, Pages 1 - 7
Abstract
Deploying microservice-based applications on computing clusters in the Cloud is subject to stochastic changes due to dynamic user requirements. To address the problem of estimating dynamic and runtime user requirements, we compare three machine learning (ML) models for predicting the microservice call rates based on the execution times (also referred as microservice times) and aiming at estimating the scalability requirements of microservices. We apply the linear regression (LR), multilayer perceptron (MLP), and gradient boosting regression (GBR) models on the Alibaba microservice traces, supporting the workloads for microservice-based applications from real production environments. The prediction results reveal that the LR model reaches a lower training time than the GBR and MLP models, leading to lower microservice deployment time. However, the GBR reduces the mean absolute error and the mean absolute percentage error compared to LR and MLP models, predicting the required number of replicas for each microservice close to the actual test data without any prediction.
References
[1]
Christina Terese Joseph and K Chandrasekaran. Intma: Dynamic interaction-aware resource allocation for containerized microservices in cloud environments. Journal of Systems Architecture, 111:101785, 2020.
[2]
Narges Mehran, Zahra Najafabadi Samani, Dragi Kimovski, and Radu Prodan. Matching-based scheduling of asynchronous data processing workflows on the computing continuum. In 2022 IEEE International Conference on Cluster Computing (CLUSTER), pages 58--70, 2022.
[3]
Shutian Luo, Huanle Xu, Chengzhi Lu, Kejiang Ye, Guoyao Xu, Liping Zhang, Yu Ding, Jian He, and Chengzhong Xu. Characterizing microservice dependency and performance: Alibaba trace analysis. In Proceedings of the ACM Symposium on Cloud Computing, pages 412--426, 2021.
[4]
Hamidreza Arkian, Guillaume Pierre, Johan Tordsson, and Erik Elmroth. Model-based stream processing auto-scaling in geo-distributed environments. In ICCCN 2021-30th International Conference on Computer Communications and Networks, 2021.
[5]
Krzysztof Rzadca, Pawel Findeisen, Jacek Swiderski, Przemyslaw Zych, Przemyslaw Broniek, Jarek Kusmierek, Pawel Nowak, Beata Strack, Piotr Witusowski, Steven Hand, et al. Autopilot: workload autoscaling at google. In Proceedings of the Fifteenth European Conference on Computer Systems, pages 1--16, 2020.
[6]
Angelina Horn, Hamid Mohammadi Fard, and Felix Wolf. Multi-objective hybrid autoscaling of microservices in kubernetes clusters. In Euro-Par 2022: Parallel Processing: 28th International Conference on Parallel and Distributed Computing, pages 233--250. Springer, 2022.
[7]
Nikolay Nikolov, Yared Dejene Dessalk, Akif Quddus Khan, Ahmet Soylu, Mihhail Matskin, Amir H Payberah, and Dumitru Roman. Conceptualization and scalable execution of big data workflows using domain-specific languages and software containers. Internet of Things, page 100440, 2021.
[8]
Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, and Artem Babenko. Revisiting deep learning models for tabular data, 2023.
[9]
Yury Gorishniy, Ivan Rubachev, and Artem Babenko. On embeddings for numerical features in tabular deep learning, 2023.
[10]
Tianqi Chen, Tong He, Michael Benesty, Vadim Khotilovich, Yuan Tang, Hyunsu Cho, Kailong Chen, Rory Mitchell, Ignacio Cano, Tianyi Zhou, et al. Xgboost: extreme gradient boosting. R package version 0.4-2, 1(4):1--4, 2015.
[11]
Léo Grinsztajn, Edouard Oyallon, and Gaël Varoquaux. Why do tree-based models still outperform deep learning on typical tabular data? Advances in Neural Information Processing Systems, 35:507--520, 2022.
[12]
Shutian Luo, Huanle Xu, Chengzhi Lu, Kejiang Ye, Guoyao Xu, Liping Zhang, Jian He, and Chengzhong Xu. An in-depth study of microservice call graph and runtime performance. IEEE Transactions on Parallel and Distributed Systems, 33(12):3901--3914, 2022.
[13]
Shutian Luo, Huanle Xu, Kejiang Ye, Guoyao Xu, Liping Zhang, Guodong Yang, and Chengzhong Xu. The power of prediction: microservice auto scaling via workload learning. In Proceedings of the 13th Symposium on Cloud Computing, pages 355--369, 2022.
[14]
Joy Rahman and Palden Lama. Predicting the end-to-end tail latency of containerized microservices in the cloud. In 2019 IEEE International Conference on Cloud Engineering (IC2E), pages 200--210, 2019.
[15]
Yi-Lin Cheng, Ching-Chi Lin, Pangfeng Liu, and Jan-Jan Wu. High resource utilization auto-scaling algorithms for heterogeneous container configurations. In 23rd IEEE International Conference on Parallel and Distributed Systems (ICPADS), pages 143--150, 2017.
[16]
Fabiana Rossi, Valeria Cardellini, Francesco Lo Presti, and Matteo Nardelli. Geo-distributed efficient deployment of containers with kubernetes. Computer Communications, 159:161--174, 2020.
[17]
Sebastian Ştefan and Virginia Niculescu. Microservice-oriented workload prediction using deep learning. e-Informatica Software Engineering Journal, 16(1):220107, March 2022. Available online: 25 Mar. 2022.
[18]
Hangtao He, Linyu Su, and Kejiang Ye. Graphgru: A graph neural network model for resource prediction in microservice cluster. In 2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS), pages 499--506, 2023.
[19]
Zahra Najafabadi Samani, Narges Mehran, Dragi Kimovski, Shajulin Benedikt, Nishant Saurabh, and Radu Prodan. Incremental multilayer resource partitioning for application placement in dynamic fog. IEEE Transactions on Parallel and Distributed Systems, pages 1--18, 2023.
[20]
scikit-learn developers. Linear regression pipeline by scikit-learn. https://scikit-learn.org/stable/modules/linear_model.html#ordinary-least-squares, 2023.
[21]
The MathWorks, Inc. What Is a Linear Regression Model? https://www.mathworks.com/help/stats/what-is-linear-regression.html, 2023.
[22]
Kanad Keeni, Kenji Nakayama, and Hiroshi Shimodaira. Estimation of initial weights and hidden units for fast learning of multilayer neural networks for pattern classification. In IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No. 99CH36339), volume 3, pages 1652--1656. IEEE, 1999.
[23]
PyTorch Contributors. Linear - pytorch 2.0 documentation. https://pytorch.org/docs/stable/generated/torch.nn.Linear.html#linear, 2023.
[24]
Alexey Natekin and Alois Knoll. Gradient boosting machines, a tutorial. Frontiers in neurorobotics, 7:21, 2013.
[25]
Zhiheng Zhong, Minxian Xu, Maria Alejandra Rodriguez, Chengzhong Xu, and Rajkumar Buyya. Machine learning-based orchestration of containers: A taxonomy and future directions. ACM Computing Surveys (CSUR), 54(10s):1--35, 2022.
[26]
scikit-learn developers. 1.11. ensemble methods - scikit-learn 1.3.0 documentation. https://scikit-learn.org/stable/modules/ensemble.html#gradient-boosting, 2023.
[27]
Nikolay Nikolov, Arnor Solberg, Radu Prodan, Ahmet Soylu, Mihhail Matskin, and Dumitru Roman. Container-based data pipelines on the computing continuum for remote patient monitoring. Computer, 56(10):40--48, 2023.
[28]
Dumitru Roman, Radu Prodan, Nikolay Nikolov, Ahmet Soylu, Mihhail Matskin, Andrea Marrella, Dragi Kimovski, Brian Elvesæter, Anthony Simonet-Boulogne, Giannis Ledakis, Hui Song, Francesco Leotta, and Evgeny Kharlamov. Big data pipelines on the computing continuum: Tapping the dark data. Computer, 55(11):74--84, 2022.
[29]
Shirin Tahmasebi, Amirhossein Layegh, Nikolay Nikolov, Amir H Payberah, Khoa Dinh, Vlado Mitrovic, Dumitru Roman, and Mihhail Matskin. Dataclouddsl: Textual and visual presentation of big data pipelines. In 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), pages 1165--1171. IEEE, 2022.
[30]
Aleena Thomas, Nikolay Nikolov, Antoine Pultier, Dumitru Roman, Brian Elvesæter, and Ahmet Soylu. Sim-pipe dryrunner: An approach for testing container-based big data pipelines and generating simulation data. In 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), pages 1159--1164. IEEE, 2022.
[31]
Anthony Simonet-Boulogne, Arnor Solberg, Amir Sinaeepourfard, Dumitru Roman, Fernando Perales, Giannis Ledakis, Ioannis Plakas, and Souvik Sengupta. Toward blockchain-based fog and edge computing for privacy-preserving smart cities. Frontiers in Sustainable Cities, page 136, 2022.
[32]
Lars Buitinck, Gilles Louppe, Mathieu Blondel, Fabian Pedregosa, Andreas Mueller, Olivier Grisel, Vlad Niculae, Peter Prettenhofer, Alexandre Gramfort, Jaques Grobler, Robert Layton, Jake VanderPlas, Arnaud Joly, Brian Holt, and Gaël Varoquaux. API design for machine learning software: experiences from the scikit-learn project. In ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pages 108--122, 2013.
[33]
PyTorch Contributors. L1loss - pytorch 2.0 documentation. https://pytorch.org/docs/stable/generated/torch.nn.L1Loss.html#torch.nn.L1Loss, 2023.
Index Terms
- Comparison of Microservice Call Rate Predictions for Replication in the Cloud
Recommendations
Performance Modeling for Cloud Microservice Applications
ICPE '19: Proceedings of the 2019 ACM/SPEC International Conference on Performance EngineeringMicroservices enable a fine-grained control over the cloud applications that they constitute and thus became widely-used in the industry. Each microservice implements its own functionality and communicates with other microservices through language- and ...
A Self-Adaptive Prediction Algorithm for Cloud Workloads
It is difficult to analyze the workload in complex cloud computing environments with a single prediction algorithm as each algorithm has its own shortcomings. A self-adaptive prediction algorithm combining the advantages of linear regression LR and a BP ...
Graph Neural Networks for Metrics Prediction in Microservice Architecture
Computational Science and Its Applications – ICCSA 2024 WorkshopsAbstractThe article examines the issues of monitoring performance in microservice architectures. We explore the problem of forecasting performance indicators as well as fault propagation in such systems, which are distributed and have independent service ...
Comments
Information & Contributors
Information
Published In
December 2023
502 pages
ISBN:9798400702341
DOI:10.1145/3603166
- Co-chairs:
- Omer Rana,
- Massimo Villari,
- Program Co-chairs:
- Song Fu,
- Lorenzo Carnevale
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 04 April 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- European Union's grant agreements Horizon 2020 (DataCloud)
- Graph-Massivizer
- enRichMyData
Conference
UCC '23
Sponsor:
UCC '23: IEEE/ACM 16th International Conference on Utility and Cloud Computing
December 4 - 7, 2023
Taormina (Messina), Italy
Acceptance Rates
Overall Acceptance Rate 38 of 125 submissions, 30%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 152Total Downloads
- Downloads (Last 12 months)152
- Downloads (Last 6 weeks)25
Reflects downloads up to 18 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in