We have adapted a
condition-based maintenance (CBM) approach called the Multivariate
State Estimation Technique (MSET) to support automatic failure
prediction and recovery in software systems. Our approach
automatically creates sophisticated statistical models that predict
system failure well before failures occur, leading to simpler and more
successful recoveries.
Some of our recent work is described in:
Some of our recent work is described in:
- Kenny C. Gross, Scott McMaster, Adam Porter, Aleksey Urmanov Lawrence G. Votta, Towards Dependability in Everyday Software Using Software Telemetry, In the Proceedings of the 3rd IEEE Workshop on Engineering of Autonomic Systems. Potsdam, Germany. March 2006.
