UCSB SmartFarm is a research project that investigates the design and implementation of an open source,
hybrid cloud approach to agriculture analytics for enabling sustainable farming practices.
- Integrates disparate environmental and Internet-of-Things (IoT) sensor technologies
into an on-farm, private cloud
software infrastructure that ensures that all private data remain under the control of farmers.
- Provides farmers with a secure, easy to use, low-cost data analysis system.
- Couples data from external cloud sources
(weather predictions, satellite imagery, state and national datasets, etc) with farm-local
- Provides an interface into which custom analytics apps can be plugged (via an AppStore model).
The research that we pursue related to this project includes the design, implementation, and empirical evaluation of
- Low-cost, robust sensing devices and intermediate nodes (intercessors) for the Internet of Things (IoT) using off-the-shelf components,
- Self-managing edge cloud systems and their integration into multi-tier (sensing, edge, cloud) IoT systems,
- Characterization and optimization of performance interference across big/fast data frameworks
for resource constrained, multi-analytics edge clouds,
- New programming models, virtualization techniques, and communications protocols for multi-tier IoT systems, and
- Novel analytics and machine learning services for decision support.