Rapid quantification of demand response potential of building HAVC system via data-driven model

• Published in: Applied energy 2022-11, Vol.325, p.119796, Article 119796
• Main Authors: Zhu, Jie, Niu, Jide, Tian, Zhe, Zhou, Ruoyu, Ye, Chuang
• Format: Article
• Language: English
• Subjects: Building energy systems; Data-driven model; Demand response potential; Flexibility; Modelica
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2022.119796

•A data-driven model was developed to rapidly quantify the demand response potential of building HVAC systems.•Multiple factors affecting demand response potential were considered in the data-driven model.•A co-simulation platform based on EnergyPlus and Modelica was built for fully getting the demand response potential data.•Two commonly used DR strategies were evaluated using a series of indices. Buildings and heating, ventilation and air-conditioning systems are appropriate resources for demand response, but there is still a lack of rapid quantification methods to reveal buildings’ dynamic demand response potential under different meteorological conditions and control strategies. In order to achieve real-time power grid dispatch and to facilitate grid-building interaction, this paper proposes a framework for establishing models to rapidly quantify the demand response potential of resources. First, a detailed co-simulation model of the building and its energy system is constructed, followed by extensive stochastic simulations of two commonly used demand response strategies, after which the demand response potential is quantified using a set of indices. Then, feature selection is performed on factors that may affect demand response potential, and a data-driven model for quantifying demand response potential is proposed, whose results are compared with those from the simulation model. Also, the demand response effects of the two control strategies are compared in this paper. A case study was carried out in an industrial building in Shenzhen, China. The results showed that under different boundaries, the coefficient of determination (R2) of the quantification indices are all above 0.9, and that the data-driven model rapidly and accurately captured the demand response potential of the building and its heating, ventilation and air-conditioning system, and was easy to deploy in practice.