Direct and Inverse Neural Modelling of Buildings HVAC Systems
- Resource Type
- Conference
- Authors
- Belloni, Elisa; Fulginei, Francesco Riganti; Lozito, Gabriele Maria; Poli, Davide
- Source
- IEEE EUROCON 2023 - 20th International Conference on Smart Technologies Smart Technologies, IEEE EUROCON 2023 - 20th International Conference on. :269-274 Jul, 2023
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Geoscience
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Heating systems
Temperature distribution
HVAC
Databases
Computational modeling
Buildings
Urban areas
Artificial Neural Network
Building
HVAC management
Thermal-Electric Energy Consumptions
Database
- Language
The present paper describes an approach to develop a neural network model approach to characterize the thermal and electrical relationship in a climatized building. The approach is fundamental for the inclusion of such building in an grid with demand-response strategy, such as a micro-grid or a renewable energy community. The approach is based on the simulation of different buildings with variable boundary conditions in the EnergyPlus environment. This simulation is used to create a database of electrical and thermal profiles, which is then used to create direct (electrical to thermal) and inverse (thermal to electrical) models of the building. Both models were validated against test data to assess the accuracy of their predictions.