CAREER: A Data-Driven Uncertainty-Guided Architecture for Energy Management in Sensor Systems

University Of California - Merced, Merced CA

Investigators

Abstract

The dramatic growth of wireless sensor networks (WSNs) in the last few years has seen the emergence of a variety of applications and pilot deployments that span scientific, engineering, medical and other disciplines. This project addresses an important research problem in sensor networks: energy management. By using hierarchical WSNs with different resources at different proxy and sensor tiers, as well as novel machine learning methods, we plan to develop DURACEM, a data-driven uncertainty-guided architecture that addresses energy efficiency across many sensor network services in a unified manner. Our architecture is built around (a) prediction models of phenomena, energy usage, and communication and the uncertainty in these models, (b) a slew of services that can exploit the uncertainty measures to save energy and (c) an overall energy optimization framework that combines the different models and services at both the proxy and sensor tiers. DURACEM has the potential for broad social impact. Our proposed research will provide fundamental services and tools to build next generation hierarchical sensor networks. DURACEM will provide a suite of efficient prediction models, as well as a variety of energy-optimized services built over these models. Our source code for our tools, libraries and prototypes will be made available to other researchers via an open-source software license. The project also focuses on building an inter-disciplinary teaching lab that can spur adoption of sensor networks by educating students across engineering and sciences. The project includes the development of a comprehensive curriculum that provides graduate and undergraduate students with core systems and analytical skills in sensor networks. The DURACEM project will enhance the research experiences of minority groups at University of California, Merced (UCM), which is one of only few research universities in the nation with a Hispanic student population greater than 40% and it is considered a Hispanic Serving Institution. The project includes an outreach undergraduate component specifically targeted to the minority students.