Dynamic Resource Scaling for Microservices: A Machine Learning-driven Predictive Approach

Joshi, Akshay (2023) Dynamic Resource Scaling for Microservices: A Machine Learning-driven Predictive Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (754kB) | Preview

Abstract

In my research on ”Dynamic Resource Scaling for Microservices: A Machine Learning-driven Predictive Approach,” the focus is on optimizing microservice-based applications by predicting and adjusting resource needs using cloud autoscaling mechanisms. The machine learning models, including Multinomial Logistic Regression and Linear Regression, are trained on historical workload data, specifically the Netflix NDbench dataset. Following the training, microservices are deployed on AWS Lambda with AWS API Gateway and a Load Balancer for efficient management. The machine learning outcomes categorize CPU usage into High, Normal, and Low, stored for subsequent actions. To operationalize these predictions, a dedicated webpage is developed, displaying machine learning results and Lambda function details through AWS SDK. The critical component of the research involves autoscaling by dynamically updating the concurrency of the Lambda function. When the machine learning model predicts high CPU utilization, the concurrency is increased, allowing the Lambda function to handle a higher number of simultaneous requests. Conversely, during low CPU usage, the concurrency is decreased to optimize resource allocation. For an in-depth exploration of the autoscaling methodology and its integration with machine learning predictions, further details are provided in subsequent sections.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Heeney, Sean UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	28 Mar 2025 14:05
Last Modified:	28 Mar 2025 14:05
URI:	https://norma.ncirl.ie/id/eprint/7349

Actions (login required)

View Item