Space-Time Derivative-Based Prediction: A Novel Trickling Mechanism for WSN

Time series prediction techniques reduce the number of messages generated at the application level, saving energy spent in the communication and, consequently, extending the network lifetime. Trickle is a well-known time series prediction mechanism commonly used to decrease the number of transmitted messages in Wireless Sensor Networks (WSN) and thus save energy. This paper presents the Space-Time Derivative-Based Prediction (ST-DBP), a novel Trickling mechanism to suppress data transmission in space-time regions in WSNs. We integrate ST-DBP with the Trustful Space-Time Protocol (TSTP), an application-oriented, cross-layer communication protocol, and compare two variations of the ST-DBP with the original DBP using real data from a Solar Farm in terms of suppression data ratio. Our results show that the two variations of the ST-DBP outperform the original DBP.

[1]  Petr Musílek,et al.  Derivative based prediction with look ahead , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[2]  Antônio Augusto Fröhlich,et al.  A cross-layer approach to trustfulness in the Internet of Things , 2013, 16th IEEE International Symposium on Object/component/service-oriented Real-time distributed Computing (ISORC 2013).

[3]  Sebastian Fischmeister,et al.  Implementation and evaluation of global and partitioned scheduling in a real-time OS , 2013, Real-Time Systems.

[4]  Antônio Augusto Fröhlich,et al.  Design rationale of a cross-layer, Trustful Space-Time Protocol for Wireless Sensor Networks , 2015, 2015 IEEE 20th Conference on Emerging Technologies & Factory Automation (ETFA).

[5]  Ahmed Yassin Al-Dubai,et al.  E-Trickle: Enhanced Trickle Algorithm for Low-Power and Lossy Networks , 2015, 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing.

[6]  Samuel Madden,et al.  An energy-efficient querying framework in sensor networks for detecting node similarities , 2006, MSWiM '06.

[7]  Amy L. Murphy,et al.  Data Prediction + Synchronous Transmissions = Ultra-low Power Wireless Sensor Networks , 2016, SenSys.

[8]  Dimitrios Gunopulos,et al.  Streaming Time Series Summarization Using User-Defined Amnesic Functions , 2008, IEEE Transactions on Knowledge and Data Engineering.

[9]  Xiaobin Xu,et al.  A Hybrid Model for Data Prediction in Real-World Wireless Sensor Networks , 2017, IEEE Communications Letters.

[10]  Amy L. Murphy,et al.  Practical Data Prediction for Real-World Wireless Sensor Networks , 2015, IEEE Transactions on Knowledge and Data Engineering.

[11]  Amy L. Murphy,et al.  What does model-driven data acquisition really achieve in wireless sensor networks? , 2012, 2012 IEEE International Conference on Pervasive Computing and Communications.

[12]  Gustavo Medeiros de Araújo,et al.  On the Impact of Dynamic Routing Metrics on a Geographic Protocol for WSNs , 2016, 2016 VI Brazilian Symposium on Computing Systems Engineering (SBESC).