Efficient Energy Management and Data Recovery in Sensor Networks using Latent Variables Based Tensor Factorization
Bojan Milosevic, Jinseok Yang, Sameer Tilak, Piero Zappi, Elisabetta Farella, Luca Benini, Tajana Simunic Rosing

Citation
Bojan Milosevic, Jinseok Yang, Sameer Tilak, Piero Zappi, Elisabetta Farella, Luca Benini, Tajana Simunic Rosing. "Efficient Energy Management and Data Recovery in Sensor Networks using Latent Variables Based Tensor Factorization". ACM/IEEE International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems 2013, 2013.

Abstract
A key factor in a successful sensor network deployment is finding a good balance between maximizing the number of measurements taken (to maintain a good sampling rate) and minimizing the overall energy consumption (to extend the network lifetime). In this work, we present a data-driven sta- tistical model to optimize this tradeoff. Our approach takes advantage of the multivariate nature of the data collected by a heterogeneous sensor network to learn spatio-temporal patterns. These patterns enable us to employ an aggressive duty cycling policy on the individual sensor nodes, thereby reducing the overall energy consumption. Our experiments with the OMNeT++ network simulator using realistic wire- less channel conditions, on data collected from two real- world sensor networks, show that we can sample just 20% of the data and can reconstruct the remaining 80% of the data with less than 9% mean error, outperforming similar techniques such is distributed compressive sampling. In ad- dition, energy savings ranging up to 76%, depending on the sampling rate and the hardware configuration of the node.

Electronic downloads

Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.

Citation formats

• HTML

  Bojan Milosevic, Jinseok Yang, Sameer Tilak, Piero  Zappi,
  Elisabetta Farella, Luca Benini, Tajana Simunic Rosing.
  <a
  href="http://www.terraswarm.org/pubs/100.html"
  >Efficient Energy Management and Data Recovery in Sensor
  Networks using Latent Variables Based Tensor
  Factorization</a>, ACM/IEEE International Conference
  on Modeling, Analysis  and Simulation of Wireless and Mobile
  Systems 2013, 2013.

• Plain text

  Bojan Milosevic, Jinseok Yang, Sameer Tilak, Piero  Zappi,
  Elisabetta Farella, Luca Benini, Tajana Simunic Rosing.
  "Efficient Energy Management and Data Recovery in
  Sensor Networks using Latent Variables Based Tensor
  Factorization". ACM/IEEE International Conference on
  Modeling, Analysis  and Simulation of Wireless and Mobile
  Systems 2013, 2013.

• BibTeX

  @inproceedings{MilosevicYangTilakZappiFarellaBeniniRosing13_EfficientEnergyManagementDataRecoveryInSensorNetworks,
      author = {Bojan Milosevic and Jinseok Yang and Sameer Tilak
                and Piero  Zappi and Elisabetta Farella and Luca
                Benini and Tajana Simunic Rosing},
      title = {Efficient Energy Management and Data Recovery in
                Sensor Networks using Latent Variables Based
                Tensor Factorization},
      booktitle = {ACM/IEEE International Conference on Modeling,
                Analysis  and Simulation of Wireless and Mobile
                Systems 2013},
      year = {2013},
      abstract = {A key factor in a successful sensor network
                deployment is finding a good balance between
                maximizing the number of measurements taken (to
                maintain a good sampling rate) and minimizing the
                overall energy consumption (to extend the network
                lifetime). In this work, we present a data-driven
                sta- tistical model to optimize this tradeoff. Our
                approach takes advantage of the multivariate
                nature of the data collected by a heterogeneous
                sensor network to learn spatio-temporal patterns.
                These patterns enable us to employ an aggressive
                duty cycling policy on the individual sensor
                nodes, thereby reducing the overall energy
                consumption. Our experiments with the OMNeT++
                network simulator using realistic wire- less
                channel conditions, on data collected from two
                real- world sensor networks, show that we can
                sample just 20% of the data and can reconstruct
                the remaining 80% of the data with less than 9%
                mean error, outperforming similar techniques such
                is distributed compressive sampling. In ad-
                dition, energy savings ranging up to 76%,
                depending on the sampling rate and the hardware
                configuration of the node. },
      URL = {http://terraswarm.org/pubs/100.html}
  }
  

Posted by Mila MacBain on 21 Aug 2013.