Dynamic Profiling and Optimization (DPOP) for Sensor Networks
The commercialization of sensor-based platforms is facilitating the realization of ubiquitous computing environments previously existing only in science fiction. However, as these platforms continue to evolve, they are becoming increasingly complex to design and implement for a given application. Much of the complexity associated with sensor-based platforms is due to the plethora of parameters that must be considered. To further complicate matters, application developers oftentimes are not trained engineers, but rather biologists, teachers, or agriculturists who wish to utilize the sensor-based systems within their given domain. Faced with an overwhelming number of choices, application design may be a daunting task for non-experts. This project will alleviate some of the complexities associated with sensor-based system design through the use of automated optimization methods that abstracts many of the underlying design and platform details, dynamic profiling methods capable of observing application-level behavior, and dynamic optimization to tune the underlying platform accordingly. Dynamic profiling enables an accurate view of the application behavior and allows the system to monitor how the application responds to changing environmental conditions or changes in the platform itself. If the developer specified performance metrics are not currently being met, dynamic optimization and network reconfiguration can adapt the deployed network to its current surroundings and application requirements. This dynamic profiling and optimization environment reduces developer effort and increases the accessibility of sensor-based systems to a wider audience, where we believe such systems can enhance our everyday lives, and thus, further the emergence of innovative applications.
| Feb 21, 2012:
||Installation and usage instructions for the ATLeS-SN simulator have been posted.Version 2.2 is now available.
| Jan 21, 2009:
||Welcome to the DPOP Project website. This research in funded by the National Science Foundation under a collaborative grant between the University of Arizona (CNS-0834102) and the University of Florida (CNS-0834080).