Evaluating Machine Learning and Heuristic Optimization Based Surrogates as a Replacement for a Complex Building Simulation Model

Kathrin Kefer, Samuel Haijes, Michael Mörth, Richard Heimrath, Thomas Mach, Valentin Kaisermayer, Christopher Zemann, Daniel Muschick, Bogdan Burlacu, Stephan Winkler, Michael Affenzeller

Publikation: Beitrag in Buch/Bericht/TagungsbandKonferenzbeitragBegutachtung

Abstract

Intelligent energy management systems can play a vital role in supporting the much needed energy transition. However, in order to train machine learning models for this task, often very complex and detailed simulation models are needed. This can make the overall training process very slow or even impossible, which is why using resource efficient surrogates of the original simulation model during the training can be a possible solution. This work therefore focuses on the training of surrogates of a very detailed building simulation model using three different algorithms (k-Nearest Neighbour, Random Forest and Genetic Algorithm) and evaluates and compares them for their prediction capabilities, learned behaviours as well as execution time. Results show that the Random Forest algorithm achieves the best overall performance for 28 of the 35 surrogates, can learn the expected behavior and improves the execution speed by a factor of up to 664 compared to the original IDA ICE simulation model.

OriginalspracheEnglisch
Titel11th International Workshop on Simulation for Energy, Sustainable Development and Environment, SESDE 2023
Redakteure/-innenAgostino G. Bruzzone, Janos Sebestyen Janosy, Letizia Nicoletti, Gregory Zacharewicz
Herausgeber (Verlag)Cal-Tek srl
ISBN (elektronisch)9788885741980
DOIs
PublikationsstatusVeröffentlicht - 2023
Veranstaltung11th International Workshop on Simulation for Energy, Sustainable Development and Environment, SESDE 2023 - Athens, Griechenland
Dauer: 18 Sep. 202320 Sep. 2023

Publikationsreihe

NameProceedings of the International Workshop on Simulation for Energy, Sustainable Development and Environment, SESDE
Band2023-September
ISSN (Print)2724-0061

Konferenz

Konferenz11th International Workshop on Simulation for Energy, Sustainable Development and Environment, SESDE 2023
Land/GebietGriechenland
OrtAthens
Zeitraum18.09.202320.09.2023

Fingerprint

Untersuchen Sie die Forschungsthemen von „Evaluating Machine Learning and Heuristic Optimization Based Surrogates as a Replacement for a Complex Building Simulation Model“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren