University of Illinois Urbana-Champaign

Multi-dimensional user scheduling by MDP and reinforcement learning

Xie, Fengze

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/107236

Description

Title
Multi-dimensional user scheduling by MDP and reinforcement learning
Author(s)
Xie, Fengze
Contributor(s)
Srikant, Rayadurgam
Issue Date
2020-05
Keyword(s)
  • User Scheduling
  • Markov Decision Process
  • Reinforcement Learning
Abstract
In this project we try to simulate user scheduling in high dimension. We have two machines that can serve multiple users at one time. Each machine has two-dimensional spaces, the memory and the CPU. There are two types of user that take different amounts of resource. Each user will arrive at the system and stay in the machine in a Poisson process. We want to maximize the average number of users in the system by using MDP and reinforcement learning separately.
Type of Resource
other
Language
en
Permalink
http://hdl.handle.net/2142/107236

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research