AI-Assisted Decision Support for District Heating Demand Response

Joonas Tuutijärvi, Satu Tamminen, Minna Kuittinen, Mikko Ojala, Jaakko Suutala

Abstract: Digital twins as decision support platforms construct a comprehensive digital representation of large-scale systems. This depiction can be utilised with machine learning to promote value from system data. Research conducted for this paper uses district heating data as basis for decision support digital twin that helps predict demand response situations in a district heating network by using a multi-modal model pipeline. Findings of the study include that computationally generated models can represent the data accurately enough to fit a well-defined purpose, even if model degradation increases variation from the actualised values. Additionally, the study illustrates the capability to observe and manipulate the digital twin environment through an interface, enhancing its value proposition.