Please use this identifier to cite or link to this item:
Title: Distributed Optimisation in Wireless Sensor Networks: A Hierarchical Learning Approachs
Keywords: Hierarchical Learning, Distributed Optimisation, Sensor Networks
Issue Date: 9-Jun-2008
Citation: YEOW WAI LEONG (2008-06-09). Distributed Optimisation in Wireless Sensor Networks: A Hierarchical Learning Approachs. ScholarBank@NUS Repository.
Abstract: Wireless sensor networks (WSNs) are an emerging technology of the 21st century. Massively deployed, tiny and intelligent sensors cooperatively network among themselves, instrument and control environments from wildlife habitats to homes and cities worldwide. However, with limited resource, can these tiny sensors meet hard application demands? This thesis addresses the question through hierarchical reinforcement learning. Reinforcement learning has its roots in Markov Decision Processes (MDP), which have been popularly used to model optimisation problems, and a hierarchical architecture makes it suitable for sensors. We addressed how soft constraints can be incorporated into MDP and apply it to optimise data quality and up-to-date data-gathering WSNs. We further develop a hierarchical solution for significant memory savings. The hierarchical architecture is further explored in multiple-target tracking which demonstrates significant energy savings with uncompromised accuracy. In all, hierarchical learning is effective in supporting two canonical applications of WSNs.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
YWL_thesis.pdf2.52 MBAdobe PDF



Page view(s)

checked on Jan 27, 2019


checked on Jan 27, 2019

Google ScholarTM


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