Loading...

Design and Implementation of an Intelligent Agent for Automatic Configuration of Content Delivery Servers

Lotfi, Hossein | 2023

55 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56516 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Fazli, Mohammad Amin
  7. Abstract:
  8. Content delivery networks play a significant role in improving the quality of internet services by placing the necessary content closer to users on servers. Currently, over half of internet traffic is delivered through these networks to end users. The efficiency of a content delivery network depends on various parameters, including the type of requested content, workload distribution methods, network topology, routing algorithms, caching policies, network server configurations, and resource allocation (shared or dedicated hardware resources). Additionally, the requests made to a content delivery network vary based on the type of service and even the time of day, making optimization a necessity through the use of automated methods. The objective of this project is to design and implement an intelligent agent for automatic configuration of content delivery servers. Intelligence in this context refers to the utilization of various machine learning methods to determine the importance of different parameters, allowing these operations to be performed without human intervention. The intelligent agent, when deployed on a content delivery server, configures it to handle different workloads, types of content, and various hardware resources. The required data for the functioning of this intelligent agent includes the status of hardware and software resources of the server, server configuration, as well as server access logs. One of the complexities of this problem is creating a simulated environment that resembles real-world conditions to learn different scenarios. In operational servers, configuration changes are usually infrequent. Therefore, to obtain the necessary data for the learning process, we need to provide a simulated environment that closely resembles the operational environment
  9. Keywords:
  10. Content Delivery Network (CDN) ; Machine Learning ; Reinforcement Learning ; Performance Improvement ; Automatic Configuration ; Improving Quality of Service

 Digital Object List

 Bookmark

No TOC