Nonlinear Moving Horizon Estimation and Model Predictive Control for Buildings with Unknown HVAC Dynamics

• Published in: IFAC-PapersOnLine Vol. 55; no. 41; pp. 71 - 76
• Main Authors: Mostafavi, Saman, Doddi, Harish, Kalyanam, Krishna, Schwartz, David
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2022
• Subjects: Comfort control in homes; energy optimization; model predictive building control; moving horizon estimation; energy optimization; moving horizon estimation; model predictive building control; Comfort control in homes
• ISSN: 2405-8963; 2405-8963
• DOI: 10.1016/j.ifacol.2023.01.105

We present a solution for modeling and online identification for heating, ventilation, and air conditioning (HVAC) control in buildings. Our approach comprises: (a) a resistance-capacitance (RC) model based on first order energy balance for deriving the zone temperature dynamics, and (b) a neural network for modeling HVAC dynamics. State estimation and model identification are simultaneously performed using nonlinear moving horizon estimation (MHE) with physical constraints for system states. We leverage the identified model in model predictive control (MPC) for occupant comfort satisfaction and HVAC energy savings and verify the approach using simulations. Our system relies only on building management system data, does not require extensive data storage, and does not require a detailed building model. This can significantly aid the large scale adoption of MPC for future occupant-centric control of grid-interactive buildings.