Abstract

A novel action-dependent adaptive critic design (ACD) is developed for dynamic optimization. the proposed combination of a particle swarm optimization-Based actor and a neural network critic is demonstrated through dynamic sleep scheduling of wireless sensor motes for wildlife monitoring. the objective of the sleep scheduler is to dynamically adapt the sleep duration to node's battery capacity and movement pattern of animals in its environment in order to obtain snapshots of the animal on its trajectory uniformly. Simulation results show that the sleep time of the node determined by the actor critic yields superior quality of sensory data acquisition and enhanced node longevity. © 2010 Elsevier Ltd.

Department(s)

Electrical and Computer Engineering

Comments

National Science Foundation, Grant 0348221

Keywords and Phrases

Adaptive critic design; Energy efficiency; Sleep scheduling; Wildlife monitoring; Wireless sensor networks

International Standard Serial Number (ISSN)

0893-6080

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 Elsevier, All rights reserved.

Publication Date

01 Jun 2010

PubMed ID

20223635

Share

 
COinS