According to a recent analysis, by 2030, 15% of all vehicles on U.S. roads (44 million cars) will be electric. By 2050, electric loads from transportation could account for more than a quarter of electricity demand.
Utilities must account for and manage these new loads, especially as renewable generation increases the variability of the power supply. However, often utilities have little visibility into when and where electric vehicles (EVs) are charging. Without addressing this blind spot, EV charging could create serious challenges to grid management in an already constrained environment.
Recurve’s Electric Vehicle Detector solution gives utilities the visibility to turn a potential EV charging liability into an asset that facilitates clean energy adoption and helps stabilize the grid. Using deep learning techniques, Recurve’s Electric Vehicle Detector identifies EV charging locations, giving utilities the information they need to engage EV owners in programs and rate schedules that encourage optimal charging patterns. In tests to date, the Electric Vehicle Detector has been able to identify the presence of electric vehicles in the residential sector with over 85% accuracy.
Using Smart Meters - Recurve’s Electric Vehicle Detector solution utilizes smart meter data to locate EV charging points on the grid
Advanced Machine Learning - Advanced machine learning algorithms and neural networks generate models with high accuracy in identifying EV charging
Recurve’s EV Detector solution offers utilities a powerful tool to manage the growing presence of electric vehicles on their grids. With accurate identification of EV charging patterns, utilities can optimize grid operations, integrate renewables efficiently, engage customers, and reduce greenhouse gas emissions, ultimately paving the way for a more sustainable and cost-effective energy future.
Schedule a call with one of our specialists to learn how our solutions can transform your distributed energy resource strategy.
Schedule a MeetingThe solution to DERMS complexity is integrated, third-party Measurement and Verification (M&V) using open-source methods and code.