Caching for distributed parameter estimation in wireless sensor networks

Pradeep Chennakesavula, Y. W.Peter Hong, Anna Scaglione

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This work examines a cross-layered caching problem for distributed estimation in wireless sensor networks (WSNs). In WSNs, large amounts of data are produced continuously over time, and storing all the data collected from the sensors can be costly. In distributed estimation applications, sensors first gather information about a common phenomenon, and then forward the information to a fusion center where the final estimate is computed. By assuming that the parameters are correlated over time, the estimation quality at the fusion center can be improved by combining both present and past information, where the latter can be obtained from cached data. Different from conventional caching problems, where the goal is to reconstruct the sensors' observations, our caching strategy is designed to minimize the long term average mean-square error (MSE) of the final estimate. This problem can be modelled as a Markov decision process but, due to the curse of dimensionality, is solved here using a greedy one-step-ahead caching strategy, which only minimizes the expected MSE in the next time slot. This results in a nonlinear fractional programming problem that is solved approximately using semi-definite relaxation and a modified Dinkelbach's algorithm. The effectiveness of the proposed scheme is demonstrated through numerical simulations.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Communications, ICC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467389990
DOIs
StatePublished - Jul 28 2017
Event2017 IEEE International Conference on Communications, ICC 2017 - Paris, France
Duration: May 21 2017May 25 2017

Other

Other2017 IEEE International Conference on Communications, ICC 2017
CountryFrance
CityParis
Period5/21/175/25/17

Fingerprint

Parameter estimation
Wireless sensor networks
Mean square error
Sensors
Fusion reactions
Computer simulation

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Chennakesavula, P., Hong, Y. W. P., & Scaglione, A. (2017). Caching for distributed parameter estimation in wireless sensor networks. In 2017 IEEE International Conference on Communications, ICC 2017 [7997045] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICC.2017.7997045

Caching for distributed parameter estimation in wireless sensor networks. / Chennakesavula, Pradeep; Hong, Y. W.Peter; Scaglione, Anna.

2017 IEEE International Conference on Communications, ICC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 7997045.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chennakesavula, P, Hong, YWP & Scaglione, A 2017, Caching for distributed parameter estimation in wireless sensor networks. in 2017 IEEE International Conference on Communications, ICC 2017., 7997045, Institute of Electrical and Electronics Engineers Inc., 2017 IEEE International Conference on Communications, ICC 2017, Paris, France, 5/21/17. https://doi.org/10.1109/ICC.2017.7997045
Chennakesavula P, Hong YWP, Scaglione A. Caching for distributed parameter estimation in wireless sensor networks. In 2017 IEEE International Conference on Communications, ICC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 7997045 https://doi.org/10.1109/ICC.2017.7997045
Chennakesavula, Pradeep ; Hong, Y. W.Peter ; Scaglione, Anna. / Caching for distributed parameter estimation in wireless sensor networks. 2017 IEEE International Conference on Communications, ICC 2017. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{8eab8b1bad1b41c39eb358bd0fd37041,
title = "Caching for distributed parameter estimation in wireless sensor networks",
abstract = "This work examines a cross-layered caching problem for distributed estimation in wireless sensor networks (WSNs). In WSNs, large amounts of data are produced continuously over time, and storing all the data collected from the sensors can be costly. In distributed estimation applications, sensors first gather information about a common phenomenon, and then forward the information to a fusion center where the final estimate is computed. By assuming that the parameters are correlated over time, the estimation quality at the fusion center can be improved by combining both present and past information, where the latter can be obtained from cached data. Different from conventional caching problems, where the goal is to reconstruct the sensors' observations, our caching strategy is designed to minimize the long term average mean-square error (MSE) of the final estimate. This problem can be modelled as a Markov decision process but, due to the curse of dimensionality, is solved here using a greedy one-step-ahead caching strategy, which only minimizes the expected MSE in the next time slot. This results in a nonlinear fractional programming problem that is solved approximately using semi-definite relaxation and a modified Dinkelbach's algorithm. The effectiveness of the proposed scheme is demonstrated through numerical simulations.",
author = "Pradeep Chennakesavula and Hong, {Y. W.Peter} and Anna Scaglione",
year = "2017",
month = "7",
day = "28",
doi = "10.1109/ICC.2017.7997045",
language = "English (US)",
booktitle = "2017 IEEE International Conference on Communications, ICC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Caching for distributed parameter estimation in wireless sensor networks

AU - Chennakesavula, Pradeep

AU - Hong, Y. W.Peter

AU - Scaglione, Anna

PY - 2017/7/28

Y1 - 2017/7/28

N2 - This work examines a cross-layered caching problem for distributed estimation in wireless sensor networks (WSNs). In WSNs, large amounts of data are produced continuously over time, and storing all the data collected from the sensors can be costly. In distributed estimation applications, sensors first gather information about a common phenomenon, and then forward the information to a fusion center where the final estimate is computed. By assuming that the parameters are correlated over time, the estimation quality at the fusion center can be improved by combining both present and past information, where the latter can be obtained from cached data. Different from conventional caching problems, where the goal is to reconstruct the sensors' observations, our caching strategy is designed to minimize the long term average mean-square error (MSE) of the final estimate. This problem can be modelled as a Markov decision process but, due to the curse of dimensionality, is solved here using a greedy one-step-ahead caching strategy, which only minimizes the expected MSE in the next time slot. This results in a nonlinear fractional programming problem that is solved approximately using semi-definite relaxation and a modified Dinkelbach's algorithm. The effectiveness of the proposed scheme is demonstrated through numerical simulations.

AB - This work examines a cross-layered caching problem for distributed estimation in wireless sensor networks (WSNs). In WSNs, large amounts of data are produced continuously over time, and storing all the data collected from the sensors can be costly. In distributed estimation applications, sensors first gather information about a common phenomenon, and then forward the information to a fusion center where the final estimate is computed. By assuming that the parameters are correlated over time, the estimation quality at the fusion center can be improved by combining both present and past information, where the latter can be obtained from cached data. Different from conventional caching problems, where the goal is to reconstruct the sensors' observations, our caching strategy is designed to minimize the long term average mean-square error (MSE) of the final estimate. This problem can be modelled as a Markov decision process but, due to the curse of dimensionality, is solved here using a greedy one-step-ahead caching strategy, which only minimizes the expected MSE in the next time slot. This results in a nonlinear fractional programming problem that is solved approximately using semi-definite relaxation and a modified Dinkelbach's algorithm. The effectiveness of the proposed scheme is demonstrated through numerical simulations.

UR - http://www.scopus.com/inward/record.url?scp=85028323732&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028323732&partnerID=8YFLogxK

U2 - 10.1109/ICC.2017.7997045

DO - 10.1109/ICC.2017.7997045

M3 - Conference contribution

AN - SCOPUS:85028323732

BT - 2017 IEEE International Conference on Communications, ICC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -