Skip navigation
Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp011n79h741t
Title: Understanding Cache Patterns and Caching Algorithm Performance for Content Delivery Networks
Authors: Xu, Maxwell
Advisors: Li, Kai
Department: Computer Science
Class Year: 2021
Abstract: This project aims to develop methods of evaluating the performance of caching algorithms for content delivery networks in order to understand what characteristics and patterns of cache traces affect caching algorithm performance. Using clustering algorithms on caching algorithm predictions and analyzing the types of objects evicted by different algorithms were two techniques that were able to determine what kinds of objects and access patterns different caching algorithms perform better or worse on. Heuristic caching algorithms, and even more sophisticated learned algorithms like Learned Relaxed Belady, each have their own strengths and weaknesses, performing better or worse on different types of object access patterns found in a cache trace.
URI: http://arks.princeton.edu/ark:/88435/dsp011n79h741t
Type of Material: Princeton University Senior Theses
Language: en
Appears in Collections:Computer Science, 1987-2024

Files in This Item:
File Description SizeFormat 
XU-MAXWELL-THESIS.pdf1.24 MBAdobe PDF    Request a copy


Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.