Write a Blog >>
Wed 12 Oct 2022 16:50 - 17:10 at Gold A - Technical Session 20 - Web, Cloud, Networking Chair(s): Karine Even-Mendoza

In industrial environments it is critical to find out the capacity of a system and plan for a deployment layout that meets the production traffic demands. The system capacity is influenced by both the performance of the system’s constituting components and the physical environment setup. In a large system, the configuration parameters of individual components give the flexibility to developers and load test engineers to tune system performance without changing the source code. However, due to the large search space, estimating the capacity of the system given different configuration values is a challenging and costly process. In this paper, we propose an approach, called MLASP, that uses machine learning models to predict the system key performance indicators (i.e., KPIs), such as throughput, given a set of features made off configuration parameter values, including server cluster setup, to help engineers in capacity planning for production environments. Under the same load, we evaluate MLASP on two large-scale mission-critical enterprise systems developed by Ericsson and on one open-source system. We find that: 1) MLASP can predict the system throughput with a very high accuracy. The difference between the predicted and the actual throughput is less than 1%; and 2) By using only a small subset of the training data (e.g., 3% of the entire data for the open-source system), MLASP can still predict the throughput accurately. We also document our experience of successfully integrating the approach into an industrial setting. In summary, this paper highlights the benefits and potential of using machine learning models to assist load test engineers in capacity planning.

Wed 12 Oct

Displayed time zone: Eastern Time (US & Canada) change

16:00 - 18:00
Technical Session 20 - Web, Cloud, NetworkingJournal-first Papers / Late Breaking Results / Research Papers / Tool Demonstrations / Industry Showcase at Gold A
Chair(s): Karine Even-Mendoza Imperial College London
16:00
20m
Paper
Mutation-based Analysis of Queueing Network Performance Models -- Journal First Research
Journal-first Papers
Thomas Laurent Lero & University College Dublin, Paolo Arcaini National Institute of Informatics , Catia Trubiani Gran Sasso Science Institute, Anthony Ventresque University College Dublin & Lero, Ireland
Link to publication DOI
16:20
10m
Demonstration
WebMonitor: https://youtu.be/hqVw0JU3k9c
Tool Demonstrations
Ennio Visconti TU Wien, Christos Tsigkanos University of Bern, Switzerland, Laura Nenzi University of Trieste
16:30
20m
Research paper
Exploiting Epochs and Symmetries in Analysing MPI Programs
Research Papers
Rishabh Ranjan IIT Delhi, Ishita Agrawal IIT Delhi, Subodh Sharma IIT Delhi
16:50
20m
Paper
MLASP: Machine learning assisted capacity planning
Journal-first Papers
Arthur Vitui Concordia University, Tse-Hsun (Peter) Chen Concordia University
Link to publication DOI
17:10
20m
Research paper
Graph based Incident Extraction and Diagnosis in Large-Scale Online SystemsVirtual
Research Papers
Zilong He Sun Yat-Sen University, Pengfei Chen Sun Yat-Sen University, Yu Luo Tencent Inc., Qiuyu Yan Tencent Inc., Hongyang Chen School of Computer Science and Engineering, Sun Yat-sen University, Guangba  Yu Sun Yat-Sen University, Fangyuan Li Tencent Inc.
17:30
10m
Paper
ESAVE: Estimating Server and Virtual Machine EnergyVirtual
Late Breaking Results
Priyavanshi Pathania Accenture Labs, Rohit Mehra Accenture Labs, Vibhu Saujanya Sharma Accenture Labs, Vikrant Kaulgud Accenture Labs, India, Sanjay Podder Accenture, Adam P. Burden Accenture
17:40
20m
Industry talk
MCDA Framework for Edge-Aware Multi-Cloud Hybrid Architecture RecommendationVirtual
Industry Showcase
Manish Ahuja Accenture Labs, Narendranath Sukhavasi Accenture Labs, Swapnajeet Choudhury Accenture Labs, Kaushik Amar Das Accenture Labs, Kapil Singi Accenture, Kuntal Dey Accenture Labs, India, Vikrant Kaulgud Accenture Labs, India