A data-driven rolling optimization control approach for building energy systems that integrate virtual energy storage systems

Abstract

The virtual energy storage system (VESS) is an innovative and cost-effective technique for coupling building envelope thermal storage and release abilities with the electric and heat power conversion characteristics of an air conditioner; this system provides building energy systems (BESs) with adjustable potentials similar to those of conventional battery energy storage systems (BESSs). However, the VESS is a dynamic system, and uncertainties in the outdoor temperature and solar irradiance are difficult to accurately predict, which impacts the quantification accuracy of VESSs; these characteristics challenge the BES control scheme economy and the thermal comfort of occupants. To solve this crucial issue, a data-driven rolling optimization (RO) control approach for a BES that integrates a VESS is proposed. First, a BES state space model integrating the VESS is created to reflect the VESS adjustable potential and dynamic characteristics. Based on the above model, while aiming at a small BES data sample size, a support vector machine (SVM) is combined with RO to correct the day-ahead quantification errors of the VESS adjustable potential and enhance the economical operation and thermal comfort of the BES that integrates the VESS in uncertain environments. Comparative simulations validate the effectiveness of this VESS modelling and data-driven RO control approach.