Physically Consistent Multiple-Step Data-Driven Predictions Using Physics-based Filters

Yingzhao LianJicheng ShiColin N. Jones

Mar 2023

摘要

Data-driven control can facilitate the rapid development of controllers,offering an alternative to conventional approaches. In order to maintainconsistency between any known underlying physical laws and a data-drivendecision-making process, preprocessing of raw data is necessary to account formeasurement noise and any inconsistencies it may introduce. In this paper, wepresent a physics-based filter to achieve this and demonstrate itseffectiveness through practical applications, using real-world datasetscollected in a building on the Ecole Polytechnique Federale de Lausanne (EPFL)campus. Two distinct use cases are explored: indoor temperature control anddemand response bidding.

展开全部

图表提取

论文十问

参考文献

被引用

提问与回答

暂无人提供速读十问回答

被引用

笔记

问答

领域