Optimal demand response scheduling of an industrial air separation unit using data-driven dynamic models

Abstract

Managing electricity demand has become a key consideration in power grid operations. Industrial demand response (DR) is an important component of demand-side management, and electricity-intensive chemical processes can both support power grid operations and derive economic benefits from electricity price fluctuations. For air separation units (ASUs), DR participation calls for frequent production rate changes, over time scales that overlap with the dominant dynamics of the plant. Production scheduling calculations must therefore explicitly consider process dynamics. We introduce a data-driven approach for learning the DR scheduling-relevant dynamics of an industrial ASU from its operational history, and present a dynamic optimization-based DR scheduling framework. We show that a class of low-order Hammerstein-Wiener models can accurately represent the dynamics of the industrial ASU and its model predictive control system. We evaluate the economic benefits of the proposed scheduling framework, and analyze their sensitivity to electricity price uncertainty.