Data-driven modelling for HVAC energy flexibility optimization

This paper investigates data-driven modelling of HVAC (Heating Ventilation and Air Conditioning) systems for the evaluation of the energy flexibility potentials in a Demand Response (DR) scheme. We focus on the load shifting strategy that consists in preheating/precooling the building to allow a loa...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe) pp. 1 - 5
Main Authors David, Ana, Alamir, Mazen, Pape-Gardeux, Claude Le
Format Conference Proceeding
LanguageEnglish
Published IEEE 10.10.2022
Subjects
Atmospheric modeling
Biological system modeling
Data models
Demand Response
Flexibility optimization
HVAC
HVAC optimal control
Machine Learning
Predictive modelling
Predictive models
Sensor systems
Windows
Online AccessGet full text

Cover

More Information
Summary:This paper investigates data-driven modelling of HVAC (Heating Ventilation and Air Conditioning) systems for the evaluation of the energy flexibility potentials in a Demand Response (DR) scheme. We focus on the load shifting strategy that consists in preheating/precooling the building to allow a load reduction during a DR event. A data-driven model is used to estimate the balance between the preheating and the shedded energy. Optimization in terms of setpoint changes is then performed in order to maximize an economic objective function based on a market reward model. Potential yearly outcomes are evaluated by using an advanced dynamic multi-zone building simulation tool. The modelling approach is easily scalable as it is purely data-driven and does not require information about the HVAC sub-systems, relies on data from commonly available sensors and can be easily implemented in an existing Building Management System (BMS).
DOI:10.1109/ISGT-Europe54678.2022.9960426