A first step towards a dependability framework for smart environment applications

Smart environments will consist of a large number of heterogeneous devices that communicate to collaboratively perform various tasks for users. We propose a novel depend- ability framework to increase availability and reliability of smart environment applications. We argue that the key step in achieving high dependability is to predict faults before they occur. Many statistical fault prediction techniques have been proposed for smart environment applications. Selecting the best one among these techniques involves performance assessment and detailed comparison on given metrics. We present a linear regression- based prediction model to predict the remaining battery lifetime of a device to prevent faults due to low battery. Further, we dis- cuss the proposed dependability framework, the basic approaches and the corresponding mechanisms to achieve our long-term research goal. We envision that dependability framework will reduce maintenance costs of large-scale smart environments and increase the dependability of smart environment applications. Keywords-smart environments; dependability; fault-prediction; battery fault-prediction model; linear regression.

[1]  Diane J Cook,et al.  Assessing the Quality of Activities in a Smart Environment , 2009, Methods of Information in Medicine.

[2]  Chandra Krintz,et al.  Online Prediction of Battery Lifetime for Embedded and Mobile Devices , 2003, PACS.

[3]  Tsuyoshi Idé,et al.  Predicting battery life from usage trajectory patterns , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[4]  Miroslaw Malek,et al.  A survey of online failure prediction methods , 2010, CSUR.

[5]  David E. Culler,et al.  Lessons from a Sensor Network Expedition , 2004, EWSN.

[6]  John Anderson,et al.  Wireless sensor networks for habitat monitoring , 2002, WSNA '02.

[7]  Gregory J. Pottie,et al.  Sensor network data fault types , 2007, TOSN.

[8]  Tanir Ozcelebi,et al.  Increasing reliability and availability in smart spaces: A novel architecture for resource and service management , 2012, 2012 IEEE International Conference on Consumer Electronics (ICCE).

[9]  Debanjan Ghosh,et al.  Self-healing systems - survey and synthesis , 2007, Decis. Support Syst..

[10]  Alexandre de Assis Mota,et al.  Predicting battery charge Depletion in Wireless Sensor Networks using received signal strength indicator , 2013, J. Comput. Sci..

[11]  Jiannong Cao,et al.  Application mobility in pervasive computing: A survey , 2013, Pervasive Mob. Comput..

[12]  Marco Aiello,et al.  A Machine Learning Approach for Identifying and Classifying Faults in Wireless Sensor Network , 2012, 2012 IEEE 15th International Conference on Computational Science and Engineering.