Networked and Embedded Systems Laboratory

Tryear

Trmonth

Trnumber

Title

Abstract

System-wide energy efficiency is the main driving force of the current 
sensor network research. Energy efficiency is highly application-specific 
and as a result designing a sensor network algorithm is also performed
under the constraints of a specific application such as latency and 
accuracy. In this paper we consider one such sensor network application, 
namely collaborative target tracking using acoustic sensors. This 
algorithm is an application of a traditional signal processing algorithm 
on a sensor network. Traditional target tracking disregards the 
underlying sensor measurement transport mechanism and focuses on the 
algorithm performance (tracking accuracy) based on parameters such as 
the number of trackers. Moreover the timing constraints of target 
tracking combined with the nature of the underlying network (wireless, 
multi-hop) which drops or delays measurements introduces run time energy, 
latency and accuracy tradeoffs. In this paper we study the performance 
tradeoff among the three above-mentioned metrics when we vary algorithm
parameters such as the number of trackers and the measurement rate. 
We find that we can achieve up to 20% error reduction by introducing 
latencies up to 60ms for the a fixed energy consumption. We give
directions about how to exploit directly measurable quantities such 
as packet receive rate to adaptively change the latency that achieves 
a specific level of accuracy. We also show that in such systems processing
energy is dominating communication energy thus hinting the need for 
node diversity and hierarchy.

Filename

File

Urlpdfpaper

Urlsrcpaper

Urlpdfpresentation

Urlsrcpresentation

Urlavmedia

Urldoi

Urlpublisher

Urlgooglescholar

Urlciteseer

Pubin

Pubvol

Pubnum

Pubnum end

Pubpagefirst

Pubpagelast

Pubpagecount

Pubdate

Pubdate end

Pubplace

Publisher

Ispublic

Islabdocument

Miscattributes

Document category

Main research area

Editing document