NORMA eResearch @NCI Library

Dynamic Load Balancing and Resource Management Using Machine Learning

Goswami, Amit (2023) Dynamic Load Balancing and Resource Management Using Machine Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (435kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (999kB) | Preview


The key objective of this research paper is to explain the processes used in the implementation of Load balancing and Resource management methods. Load balancing is considered to be one of the key aspects in networking as it maintains the incoming network traffic and subsequently in a long duration, it saves data, time and money. In this project, AWS Cloud Service is utilised in order to perform load balancing tasks. The data presented here shows various features like server id, time stamp, and also load on servers. Moreover, Machine Learning algorithms have been employed in the procedure and three datasets are utilised in the entire process. The dataset is gathered from an open source website. In order to achieve better results, proper analysis of data is conducted by eliminating null values and noise. With the help of ML techniques, the servers with high load are selected and the load is then transferred to servers with low load so as to achieve load balancing.

The entire research is conducted with the implementation of Python Programming language and programs run in the Jupyter Notebook environment. Artificial Neural Network (ANN) and Linear Regression are the two chief Machine Learning algorithms employed in this research as they provide highly promising results. Furthermore, the Linear Regression approach is considered more effective than ANN algorithm as its R2 value is closest to 1 hence produces much more accurate results. Therefore, it can be concluded that highly accurate results are achieved and can be utilised practically.

Item Type: Thesis (Masters)
Sahni, Vikas
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
Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: Tamara Malone
Date Deposited: 18 Apr 2023 17:47
Last Modified: 18 Apr 2023 17:47

Actions (login required)

View Item View Item