A Data Placement Method in Heterogeneous Edge-Cloud Computing for Scientific Workflow via Machine Learning

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: A Data Placement Method in Heterogeneous Edge-Cloud Computing for Scientific Workflow via Machine Learning

ارائه دهنده: Provider: Mahsa Dalvand

اساتید راهنما: Supervisors: Dr.Mehdi Sakhaei nia

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: Dr.Nosrati, Dr.Vakilian

زمان و تاریخ ارائه: Time and date of presentation: 2024

مکان ارائه: Place of presentation: دانشکده فنی-سایت

چکیده: Abstract: Research in the field of data placement in heterogeneous cloud-edge computing is of paramount importance, as it aims to enhance performance, reduce costs, and improve the speed and security of critical information. With the increasing volume and complexity of scientific data, there is a pressing need to optimize data transfer and processing processes. Furthermore, global collaborations in scientific research and the development of distributed computing technologies have significantly intensified in recent years, driven by advancements in information technology. These collaborations and the evolution of distributed computing technologies have led to remarkable changes in scientific works. In this context, leveraging the advantages of both edge and cloud computing can facilitate faster and more secure data transfers. Additionally, considering the existence of both private and public datasets, employing machine learning for data placement can enhance performance and resource efficiency. This study focuses on investigating and proposing an innovative method for data placement in heterogeneous cloud-edge computing environments using machine learning techniques. The primary objective of this research is to develop an effective framework for data placement that can improve processing speed and enhance the security of private datasets. By integrating the benefits of cloud and edge computing, this approach enables users to manage computational resources more optimally while utilizing machine learning capabilities for predictive analytics and decision-making regarding data placement.

فایل: ّFile: Download فایل