Application-Specific Customization of Dynamic Profiling Mechanisms for Sensor Networks

Lu Ding, Adrian Lizarraga, Ashish Shenoy, Ann Gordon-Ross, Susan Lysecky, Roman L Lysecky

Research output: Contribution to journalArticle

Abstract

To reduce the complexity associated with application-specific tuning of wireless sensor networks (WSNs), dynamic profiling enables an accurate view of an application's runtime behavior, such that the network can be reoptimized at runtime in response to changing application behavior or environmental conditions. However, the dynamic profiling must be able to accurately capture application behavior without incurring significant runtime overheads. Since application- and sensor-specific constraints dictate the profiling requirements and tolerated overheads, designers require design assistance to quickly evaluate and select appropriate profiling methodologies. To increase designer productivity, we formulate profiling methodology design guidelines based on extensive evaluation and analysis of a variety of profiling methodologies suitable for dynamically monitoring WSNs with respect to network traffic overhead, power, and code impacts associated with each method. While energy consumption increases are reasonable, ranging from 0.5% to 2.6%, network traffic, code size, and computation time overheads can be as high as 66.2%, 75.9%, and 136.6%, respectively. Our results show that these overhead variations are highly application specific, and a single profiling method is not suitable for all types of application behavior, thus necessitating, application-specific profiling methodology customization. To facilitate rapid development of these profiling methodologies, we present a profiler-customization methodology consisting of a code generator module, overhead estimation module, and profile data management module. Using our profiling-customization methodology, designers can rapidly evaluate the overhead of different profiling methodologies, and automatically integrate the most appropriate methodology into the application at design time.

Original languageEnglish (US)
Article number7086003
Pages (from-to)303-322
Number of pages20
JournalIEEE Access
Volume3
DOIs
StatePublished - 2015

Fingerprint

Sensor networks
Wireless sensor networks
Information management
Energy utilization
Tuning
Productivity
Monitoring
Sensors

Keywords

  • Adaptive algorithm
  • dynamic profiling
  • dynamic profiling and optimization (DPOP)
  • embedded software
  • wireless sensor networks (WSN)

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)
  • Materials Science(all)

Cite this

Application-Specific Customization of Dynamic Profiling Mechanisms for Sensor Networks. / Ding, Lu; Lizarraga, Adrian; Shenoy, Ashish; Gordon-Ross, Ann; Lysecky, Susan; Lysecky, Roman L.

In: IEEE Access, Vol. 3, 7086003, 2015, p. 303-322.

Research output: Contribution to journalArticle

Ding, L, Lizarraga, A, Shenoy, A, Gordon-Ross, A, Lysecky, S & Lysecky, RL 2015, 'Application-Specific Customization of Dynamic Profiling Mechanisms for Sensor Networks', IEEE Access, vol. 3, 7086003, pp. 303-322. https://doi.org/10.1109/ACCESS.2015.2422783
Ding, Lu ; Lizarraga, Adrian ; Shenoy, Ashish ; Gordon-Ross, Ann ; Lysecky, Susan ; Lysecky, Roman L. / Application-Specific Customization of Dynamic Profiling Mechanisms for Sensor Networks. In: IEEE Access. 2015 ; Vol. 3. pp. 303-322.
@article{043d3b6d79f14bcab7f587a5938c933e,
title = "Application-Specific Customization of Dynamic Profiling Mechanisms for Sensor Networks",
abstract = "To reduce the complexity associated with application-specific tuning of wireless sensor networks (WSNs), dynamic profiling enables an accurate view of an application's runtime behavior, such that the network can be reoptimized at runtime in response to changing application behavior or environmental conditions. However, the dynamic profiling must be able to accurately capture application behavior without incurring significant runtime overheads. Since application- and sensor-specific constraints dictate the profiling requirements and tolerated overheads, designers require design assistance to quickly evaluate and select appropriate profiling methodologies. To increase designer productivity, we formulate profiling methodology design guidelines based on extensive evaluation and analysis of a variety of profiling methodologies suitable for dynamically monitoring WSNs with respect to network traffic overhead, power, and code impacts associated with each method. While energy consumption increases are reasonable, ranging from 0.5{\%} to 2.6{\%}, network traffic, code size, and computation time overheads can be as high as 66.2{\%}, 75.9{\%}, and 136.6{\%}, respectively. Our results show that these overhead variations are highly application specific, and a single profiling method is not suitable for all types of application behavior, thus necessitating, application-specific profiling methodology customization. To facilitate rapid development of these profiling methodologies, we present a profiler-customization methodology consisting of a code generator module, overhead estimation module, and profile data management module. Using our profiling-customization methodology, designers can rapidly evaluate the overhead of different profiling methodologies, and automatically integrate the most appropriate methodology into the application at design time.",
keywords = "Adaptive algorithm, dynamic profiling, dynamic profiling and optimization (DPOP), embedded software, wireless sensor networks (WSN)",
author = "Lu Ding and Adrian Lizarraga and Ashish Shenoy and Ann Gordon-Ross and Susan Lysecky and Lysecky, {Roman L}",
year = "2015",
doi = "10.1109/ACCESS.2015.2422783",
language = "English (US)",
volume = "3",
pages = "303--322",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Application-Specific Customization of Dynamic Profiling Mechanisms for Sensor Networks

AU - Ding, Lu

AU - Lizarraga, Adrian

AU - Shenoy, Ashish

AU - Gordon-Ross, Ann

AU - Lysecky, Susan

AU - Lysecky, Roman L

PY - 2015

Y1 - 2015

N2 - To reduce the complexity associated with application-specific tuning of wireless sensor networks (WSNs), dynamic profiling enables an accurate view of an application's runtime behavior, such that the network can be reoptimized at runtime in response to changing application behavior or environmental conditions. However, the dynamic profiling must be able to accurately capture application behavior without incurring significant runtime overheads. Since application- and sensor-specific constraints dictate the profiling requirements and tolerated overheads, designers require design assistance to quickly evaluate and select appropriate profiling methodologies. To increase designer productivity, we formulate profiling methodology design guidelines based on extensive evaluation and analysis of a variety of profiling methodologies suitable for dynamically monitoring WSNs with respect to network traffic overhead, power, and code impacts associated with each method. While energy consumption increases are reasonable, ranging from 0.5% to 2.6%, network traffic, code size, and computation time overheads can be as high as 66.2%, 75.9%, and 136.6%, respectively. Our results show that these overhead variations are highly application specific, and a single profiling method is not suitable for all types of application behavior, thus necessitating, application-specific profiling methodology customization. To facilitate rapid development of these profiling methodologies, we present a profiler-customization methodology consisting of a code generator module, overhead estimation module, and profile data management module. Using our profiling-customization methodology, designers can rapidly evaluate the overhead of different profiling methodologies, and automatically integrate the most appropriate methodology into the application at design time.

AB - To reduce the complexity associated with application-specific tuning of wireless sensor networks (WSNs), dynamic profiling enables an accurate view of an application's runtime behavior, such that the network can be reoptimized at runtime in response to changing application behavior or environmental conditions. However, the dynamic profiling must be able to accurately capture application behavior without incurring significant runtime overheads. Since application- and sensor-specific constraints dictate the profiling requirements and tolerated overheads, designers require design assistance to quickly evaluate and select appropriate profiling methodologies. To increase designer productivity, we formulate profiling methodology design guidelines based on extensive evaluation and analysis of a variety of profiling methodologies suitable for dynamically monitoring WSNs with respect to network traffic overhead, power, and code impacts associated with each method. While energy consumption increases are reasonable, ranging from 0.5% to 2.6%, network traffic, code size, and computation time overheads can be as high as 66.2%, 75.9%, and 136.6%, respectively. Our results show that these overhead variations are highly application specific, and a single profiling method is not suitable for all types of application behavior, thus necessitating, application-specific profiling methodology customization. To facilitate rapid development of these profiling methodologies, we present a profiler-customization methodology consisting of a code generator module, overhead estimation module, and profile data management module. Using our profiling-customization methodology, designers can rapidly evaluate the overhead of different profiling methodologies, and automatically integrate the most appropriate methodology into the application at design time.

KW - Adaptive algorithm

KW - dynamic profiling

KW - dynamic profiling and optimization (DPOP)

KW - embedded software

KW - wireless sensor networks (WSN)

UR - http://www.scopus.com/inward/record.url?scp=84959857247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959857247&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2015.2422783

DO - 10.1109/ACCESS.2015.2422783

M3 - Article

VL - 3

SP - 303

EP - 322

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 7086003

ER -