Energy Optimal Control of a Multivalent Building Energy System using Machine Learning

Chenzi Huang, Stephan Seidel, Xuehua Jia, Fabian Paschke, Jan Bräunig

2021

Abstract

In this contribution we develop and analyse intelligent control methods in order to optimise the energy efficiency of a modern residential building with multiple renewable energy sources. Because of alternative energy production options a non-convex mixed-integer optimisation problem arises. For the solution we first apply combined optimisation methods and integrate it into a model predictive controller (MPC). In comparison, a reinforcement learning (RL) based approach is developed and evaluated in detail. Both methods, in particular reinforcement learning approaches are able to decrease energy consumption and keep thermal comfort at the same time. However, in this paper RL can achieve better results with less computational resources than MPC approach.

Download


Paper Citation


in Harvard Style

Huang C., Seidel S., Jia X., Paschke F. and Bräunig J. (2021). Energy Optimal Control of a Multivalent Building Energy System using Machine Learning. In Proceedings of the 10th International Conference on Smart Cities and Green ICT Systems - Volume 1: SMARTGREENS, ISBN 978-989-758-512-8, pages 57-66. DOI: 10.5220/0010478500570066


in Bibtex Style

@conference{smartgreens21,
author={Chenzi Huang and Stephan Seidel and Xuehua Jia and Fabian Paschke and Jan Bräunig},
title={Energy Optimal Control of a Multivalent Building Energy System using Machine Learning},
booktitle={Proceedings of the 10th International Conference on Smart Cities and Green ICT Systems - Volume 1: SMARTGREENS,},
year={2021},
pages={57-66},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010478500570066},
isbn={978-989-758-512-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Smart Cities and Green ICT Systems - Volume 1: SMARTGREENS,
TI - Energy Optimal Control of a Multivalent Building Energy System using Machine Learning
SN - 978-989-758-512-8
AU - Huang C.
AU - Seidel S.
AU - Jia X.
AU - Paschke F.
AU - Bräunig J.
PY - 2021
SP - 57
EP - 66
DO - 10.5220/0010478500570066