@misc{d2077099855d460baa84d2c52f46147d,
title = "1.2.4.404 - Data-Driven Approach for Hydropower Plant Controller Prototyping Using Remote Hardware in the Loop (DR-HIL)",
abstract = "Real-time prototyping of hydropower plant controls is important for reducing the cost and the risk of field deployment. This project will 1) collect design and operational data from actual hydro plants and 2) use a physics-informed machine learning approach for real-time emulation of hydropower plants, including hydro turbine and hydrodynamics. The data-driven models will be interfaced with digital real-time simulation at NREL{\textquoteright}s Flatirons campus for hardware-in-the-loop (HIL) testing of the governor hardware device or controller-HIL (CHIL). The proposed approach will also establish the connectivity based remote CHIL testing capability using real-time data streams from an actual hydro plant. This integrated hydro-plant emulation with CHIL will be used to prototype hydro-governor controls and eventually provide an opportunity to test hydropower integrated with various technologies (e.g. conventional and renewable generation, energy conversion, etc.) as HIL.",
keywords = "controls prototyping, data-driven, hardware in the loop, hydropower, machine learning, neural network",
author = "Mayank Panwar",
year = "2022",
language = "American English",
series = "Presented at the U.S. Department of Energy Water Power Technologies Office (WPTO) 2022 Project Peer Review, 25-29 July 2022",
type = "Other",
}