Carleton University
Investigation of the Distribution-Based Network Control Learning Environment
Abstract
dc:description.abstractThis thesis explores the application of Distribution Based Network Control (DBNC) using Reinforcement Learning (RL) to manage dynamic network environments. It examines how the controller’s learning environment affects the controllability of influence diffusion within a network, focusing on control signals produced through RL, the diffusion rate within the Real-value Voter Model (RVM), and the role of control nodes, or influencers. Extending McKenney’s work, this research evaluates the efficiency and effectiveness of the controller’s RL environment on small-world networks. The study found that the controller identified critical signal values for various control node configurations and that lower diffusion rates required smaller control signals. Additionally, excluding control nodes' opinions from the network state calculation hindered network control, highlighting the importance of these nodes in controlling the network. This thesis enhances the understanding of DBNC in controlling stochastic diffusion in social networks.
Degree
thesis:*- Name thesis:degree_name
- Master of Computer Science (M.C.S.)
- Level thesis:degree_level
- Master's
- Discipline thesis:degree_discipline
- Computer Science
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Benjamin, Sean Steele
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- Copyright © 2024 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en