Sayyed, Saifali (2020) Optimization of Resource Allocation and Prediction Analysis in Serverless Computing using Dynamic Resource Algorithm. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Resource Allocation in Serverless Computing is an essential factor when there is a necessity for better application performance. But, to allocate the resources dynamically based on the serverless application requirement is a tedious task. In this proposed approach, OpenSource Serverless Platform has been leveraged named OpenFaaS for creating the functions which are deployed on AWS EC2 Instance. In this novel approach, Dynamic Allocation of Resources for serverless functions has been implemented using the Dynamic Resource Algorithm. The algorithm analyzes the past resource consumption and based on the thresholds configured for each resource, it allocates the resources to serverless functions. Moreover, the proposed approach, predicts future resource utilization of serverless functions using the ARIMA time series analysis model. Once, the resources are forecasted they are sent to the AWS CloudWatch Dashboard. Next, the Dynamic Resource Algorithm is evaluated with the Default Docker Resource Allocation Method. Whereas, ARIMA time-series model is evaluated with the Standard time-series model. Lastly, their results are explained and compared with each other and concluded which worked best.
Item Type: | Thesis (Masters) |
---|---|
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing |
Divisions: | School of Computing > Master of Science in Cloud Computing |
Depositing User: | Dan English |
Date Deposited: | 29 Jan 2021 11:12 |
Last Modified: | 29 Jan 2021 11:12 |
URI: | https://norma.ncirl.ie/id/eprint/4549 |
Actions (login required)
View Item |