Publication | Other papers |
Towards a Taxonomy for Application of Machine Learning and Artificial Intelligence in Building and District Energy Management Systems
Published 2025
Citation: Lichtenegger K, Ahammer F, Schopper F, Muschick D, Gölles M. Towards a Taxonomy for Application of Machine Learning and Artificial Intelligence in Building and District Energy Management Systems. In: Martinac, I., Jørgensen, B.N., Ma, Z.G., Unnþórsson, R., Bordin, C. (eds) Energy Informatics. EIA Nordic 2025. Lecture Notes in Computer Science, vol 16096. Springer, Cham. https://doi.org/10.1007/978-3-032-03098-6_7.
Abstract
Building and district energy management increasingly requires advanced control strategies. For several tasks that arise, Machine Learning (ML) and Artificial Intelligence (AI) have found widespread application, but often the interaction with existing elements and the integration into the productive system are done in a rather unsystematic way. Thus, one faces problems concerning interface design, data requirements and reliability/trustworthiness. In order to improve this situation, we outline the general control structure of such systems, review key concepts from ML/AI and discuss approaches for conventional high-level control. This is followed by a literature review on ML/AI applications for energy management. Based on the systematics and the literature findings, we establish a taxonomy for the integration of ML/AI methods for energy management, which leads as a main result to a comprehensive guide for such applications, taking into account both characteristics of the method and the affected elements of the system. This is supplemented by a quick guideline for choice of an appropriate method and for subsequent evaluation. The target readership are control engineers who would like to get a systematic overview of ways to integrate ML/AI methods in their work, and data scientists who want to get a better understanding for main tasks and challenges for applying their tools for control tasks.