MIT EECS — Duke Energy Undergraduate Research and Innovation Scholar
Energy Usage Scorekeeping and Optimization
The utility of monitoring technologies depends on the economical extraction of actionable information from data streams. One of the largest roadblocks to effective analytics for power data arises from the disparities of scale inherent in data collection and processing, which often limits the speed and resolution at which data can be managed. New WattsWorth sensors have been developed that can monitor voltage and current without ohmic contacts, making it easy to install nonintrusive low cost power monitoring systems. The big data problem is solved by using local processing in NILMdb and avoiding the need to send large data packets over the internet. I will explore applying these sensors and NILMdb for energy scorekeeping, activity tracking, and condition-based monitoring.
There was no way I could pass up the opportunity to work with a professor on an awesome project, get credit and make some money. SuperUROP is soon going to be a fundamental part of the engineering experience at MIT