Suppressing Temporal Data in Sensor Networks using a Scheme Robust to Aberrant Readings

Abstract

The main goal of a data collection protocol for sensor networks is to keep the network's database updated while saving the nodes' energy as much as possible. To achieve this goal without continuous reporting, data suppression is a key strategy. The basic idea behind data suppression schemes is to send data to the base station only when the nodes' readings are different from what both the nodes and the base station expect. Data suppression schemes can be sensitive to aberrant readings, since these outlying observations mean a change in the expected behavior for the data. Transmitting these erroneous readings is a waste of energy. In this article, we present a temporal suppression scheme that is robust to aberrant readings. We use a technique to detect outliers from a time series. Our proposal classifies the detected outliers as aberrant readings or change-points using a post-monitoring window. This idea is the basis for TS-SOUND (Temporal Suppression by Statistical OUtlier Notice and Detection). TS-SOUND detects outliers in the sequence of sensor readings and sends data to the base station only when a change-point is detected. Therefore, TS-SOUND filters aberrant readings and, even when this filter fails, TS-SOUND does not send the deviated reading to the base station. Experiments with real and simulated data have shown that the TS-SOUND scheme is more robust to aberrant readings than other temporal suppression schemes (value-based, PAQ and exponential regression). Furthermore, TS-SOUND has got suppression rates comparable or greater than the rates of the cited schemes, in addition to keeping the prediction errors at acceptable levels.

Keywords:

• Temporal Data Suppression
• Outlier Detection
• Erroneous Readings
• Time Series
• Data Collection

The first author was partially supported by CAPES under PICDT program. The authors thank to the anonymous reviewers for their excellent suggestions, which have contributed to improve this article.

Notes

¹The G statistics is defined as the maximum of the absolute value of the normalized scores of observations in a static dataset.

²Thanks to Professor Rone Ilídio da Silva of Universidade Presidente Antônio Carlos (Campus Conselheiro Lafaiete) for making these data available.