Das, Shweta (2021) Ant Colony Optimization for MapReduce Application to Optimise Task Scheduling in Serverless Platform. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration manual)
Download (3MB) | Preview |
Abstract
Rising demand in computation power gained significant interest towards serverless computing. In serverless billing generates only for code execution. In serverless inefficient tasks, scheduling will result in over provisioning or under-provisioning resources which will incur more cost. Therefore it is very important to schedule the task in serverless as it will impact the cost in serverless. In the proposed paper, the efficiency of the serverless platform is enhanced by implementing Ant Colony Optimization(ACO) with a map-reduce application. ACO is a paradigm of designing a meta-heuristic algorithm that shares a common approach to construct a solution provided by both standard construction and previously constructed solutions. Since map-reduce is best suitable for big data problems but it creates additional overhead. To overcome the additional map-reduce overhead Ant Colony Optimization(ACO) is used along with fast and slow cloud storage. In the proposed paper, the existing MARLA architecture is addressed and improvisation in MARLA architecture is elaborated with the help the of ACO algorithm. Further results were compared and observed with and without implementation the of ACO algorithm.
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: | Clara Chan |
Date Deposited: | 13 Oct 2021 15:49 |
Last Modified: | 13 Oct 2021 15:49 |
URI: | https://norma.ncirl.ie/id/eprint/5084 |
Actions (login required)
View Item |