Data reduction methods for wireless smart sensors in monitoring water distribution systems

In this paper, we introduce smart sensors for monitoring water distribution systems. To improve the quality of monitoring and prolong the lifetime of the sensor node, there is a need to reduce the amount of data transmitted by predicting the future behaviour of the data while detecting and classifying important events locally in the sensor node, transferring only important data. We propose to reduce the amount of data transmitted between the sensor node and end user by using Principle Component Analysis (PCA) and dual prediction models for the monitoring of hydraulic data based on an Autoregressive Moving Average (ARMA) model. © 2013 The Authors. Published by Elsevier Ltd. Selection and peer-review under responsibility of the CCWI2013 Committee.

[1]  Francesco Marcelloni,et al.  An Efficient Lossless Compression Algorithm for Tiny Nodes of Monitoring Wireless Sensor Networks , 2009, Comput. J..

[2]  L. Nachman,et al.  PIPENET: A Wireless Sensor Network for Pipeline Monitoring , 2007, 2007 6th International Symposium on Information Processing in Sensor Networks.

[3]  Silvia Santini,et al.  Adaptive model selection for time series prediction in wireless sensor networks , 2007, Signal Process..

[4]  SrirangarajanSeshan,et al.  Wavelet-based Burst Event Detection and Localization in Water Distribution Systems , 2013 .

[5]  Hui Wang,et al.  Leak Detection of Water Pipeline Using Wavelet Transform Method , 2009, 2009 International Conference on Environmental Science and Information Application Technology.

[6]  Edward Y. Chang,et al.  Adaptive stream resource management using Kalman Filters , 2004, SIGMOD '04.

[7]  Samuel Madden,et al.  PAQ: Time Series Forecasting for Approximate Query Answering in Sensor Networks , 2006, EWSN.

[8]  Michael Allen,et al.  Water Main Burst Event Detection and Localization , 2011 .

[9]  Kay Römer,et al.  An Adaptive Strategy for Quality-Based Data Reduction in Wireless Sensor Networks , 2006 .

[10]  Wei Hong,et al.  Approximate Data Collection in Sensor Networks using Probabilistic Models , 2006, 22nd International Conference on Data Engineering (ICDE'06).

[11]  Tomasz Imielinski,et al.  Prediction-based monitoring in sensor networks: taking lessons from MPEG , 2001, CCRV.