Master's Thesis Martin Rätz

 

Automated Data Driven Modeling of Building Energy Systems via Machine Learning Algorithms

Flowchart of the developed concept Copyright: EBC Flowchart of the developed concept for efficient data driven modeling. It explains the workflow how to obtain a trained model from input data (monitoring data

The present work investigates data driven modeling for building energy systems. The main focus is to develop an efficient methodology for data driven modeling. For this purpose, a comprehensive literature review for detecting optimization methods is conducted. Furthermore, the methodology is implemented in python, automated and used to model different energy systems based on monitoring data. These models can be used for forecasting, potential analysis, the implementation of various controlling strategies or as a replacement for missing information within the field of grey box modeling.