Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities

Jan Zenisek; Florian Bachinger; Erik Pitzer; Stefan Wagner; Michael Affenzeller

doi:10.46354/i3m.2022.emss.042

Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities

Jan Zenisek^*
, Florian Bachinger
, Erik Pitzer
, Stefan Wagner
, Michael Affenzeller

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

With the growing use of machine learning models in many critical domains, research regarding making these models, as well as their predictions, more explainable has intensified in the last few years. In this paper, we present extensions to the machine learning based data mining technique Variable Interaction Networks (VIN), to integrate existing domain knowledge and thus, enable more meaningful analysis. Several tests on data from a case study concerned with long-term monitored photovoltaic systems, verify the feasibility of our approach to provide valuable, human-interpretable insights. In particular, we show the successful application of root-cause detection in scenarios with changing system conditions.

Original language	English
Title of host publication	34th European Modeling and Simulation Symposium, EMSS 2022
Editors	Michael Affenzeller, Agostino G. Bruzzone, Emilio Jimenez, Francesco Longo, Antonella Petrillo
Publisher	DIME UNIVERSITY OF GENOA
ISBN (Electronic)	9788885741737
DOIs	https://doi.org/10.46354/i3m.2022.emss.042
Publication status	Published - 2022
Event	34th European Modeling and Simulation Symposium, EMSS 2022 - Rome, Italy Duration: 19 Sept 2022 → 21 Sept 2022

Publication series

Name	34th European Modeling and Simulation Symposium, EMSS 2022

Conference

Conference	34th European Modeling and Simulation Symposium, EMSS 2022
Country/Territory	Italy
City	Rome
Period	19.09.2022 → 21.09.2022

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Data Stream Analysis
Energy Communities
Interpretable Machine Learning
Photovoltaic Systems
Root-Cause Analysis

Access to Document

10.46354/i3m.2022.emss.042

Cite this

Zenisek, J., Bachinger, F., Pitzer, E., Wagner, S., & Affenzeller, M. (2022). Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities. In M. Affenzeller, A. G. Bruzzone, E. Jimenez, F. Longo, & A. Petrillo (Eds.), 34th European Modeling and Simulation Symposium, EMSS 2022 Article 042 (34th European Modeling and Simulation Symposium, EMSS 2022). DIME UNIVERSITY OF GENOA. https://doi.org/10.46354/i3m.2022.emss.042

Zenisek, Jan ; Bachinger, Florian ; Pitzer, Erik et al. / Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities. 34th European Modeling and Simulation Symposium, EMSS 2022. editor / Michael Affenzeller ; Agostino G. Bruzzone ; Emilio Jimenez ; Francesco Longo ; Antonella Petrillo. DIME UNIVERSITY OF GENOA, 2022. (34th European Modeling and Simulation Symposium, EMSS 2022).

@inproceedings{ef8e0f8a599643288d33fd37b991812d,

title = "Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities",

abstract = "With the growing use of machine learning models in many critical domains, research regarding making these models, as well as their predictions, more explainable has intensified in the last few years. In this paper, we present extensions to the machine learning based data mining technique Variable Interaction Networks (VIN), to integrate existing domain knowledge and thus, enable more meaningful analysis. Several tests on data from a case study concerned with long-term monitored photovoltaic systems, verify the feasibility of our approach to provide valuable, human-interpretable insights. In particular, we show the successful application of root-cause detection in scenarios with changing system conditions.",

keywords = "Data Stream Analysis, Energy Communities, Interpretable Machine Learning, Photovoltaic Systems, Root-Cause Analysis",

author = "Jan Zenisek and Florian Bachinger and Erik Pitzer and Stefan Wagner and Michael Affenzeller",

note = "Funding Information: The presented work was done within the project {\textquotedblleft}Secure Prescriptive Analytics{\textquotedblright}, which is funded by the state of Upper Austria as part of the program {"}\#upperVISION2030{"}. Publisher Copyright: {\textcopyright} 2022 The Authors.; 34th European Modeling and Simulation Symposium, EMSS 2022 ; Conference date: 19-09-2022 Through 21-09-2022",

year = "2022",

doi = "10.46354/i3m.2022.emss.042",

language = "English",

series = "34th European Modeling and Simulation Symposium, EMSS 2022",

publisher = "DIME UNIVERSITY OF GENOA",

editor = "Michael Affenzeller and Bruzzone, \{Agostino G.\} and Emilio Jimenez and Francesco Longo and Antonella Petrillo",

booktitle = "34th European Modeling and Simulation Symposium, EMSS 2022",

}

Zenisek, J, Bachinger, F, Pitzer, E , Wagner, S & Affenzeller, M 2022, Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities. in M Affenzeller, AG Bruzzone, E Jimenez, F Longo & A Petrillo (eds), 34th European Modeling and Simulation Symposium, EMSS 2022., 042, 34th European Modeling and Simulation Symposium, EMSS 2022, DIME UNIVERSITY OF GENOA, 34th European Modeling and Simulation Symposium, EMSS 2022, Rome, Italy, 19.09.2022. https://doi.org/10.46354/i3m.2022.emss.042

Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities. / Zenisek, Jan; Bachinger, Florian; Pitzer, Erik et al.
34th European Modeling and Simulation Symposium, EMSS 2022. ed. / Michael Affenzeller; Agostino G. Bruzzone; Emilio Jimenez; Francesco Longo; Antonella Petrillo. DIME UNIVERSITY OF GENOA, 2022. 042 (34th European Modeling and Simulation Symposium, EMSS 2022).

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution › peer-review

TY - GEN

T1 - Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities

AU - Zenisek, Jan

AU - Bachinger, Florian

AU - Pitzer, Erik

AU - Wagner, Stefan

AU - Affenzeller, Michael

N1 - Funding Information: The presented work was done within the project “Secure Prescriptive Analytics”, which is funded by the state of Upper Austria as part of the program "#upperVISION2030". Publisher Copyright: © 2022 The Authors.

PY - 2022

Y1 - 2022

N2 - With the growing use of machine learning models in many critical domains, research regarding making these models, as well as their predictions, more explainable has intensified in the last few years. In this paper, we present extensions to the machine learning based data mining technique Variable Interaction Networks (VIN), to integrate existing domain knowledge and thus, enable more meaningful analysis. Several tests on data from a case study concerned with long-term monitored photovoltaic systems, verify the feasibility of our approach to provide valuable, human-interpretable insights. In particular, we show the successful application of root-cause detection in scenarios with changing system conditions.

AB - With the growing use of machine learning models in many critical domains, research regarding making these models, as well as their predictions, more explainable has intensified in the last few years. In this paper, we present extensions to the machine learning based data mining technique Variable Interaction Networks (VIN), to integrate existing domain knowledge and thus, enable more meaningful analysis. Several tests on data from a case study concerned with long-term monitored photovoltaic systems, verify the feasibility of our approach to provide valuable, human-interpretable insights. In particular, we show the successful application of root-cause detection in scenarios with changing system conditions.

KW - Data Stream Analysis

KW - Energy Communities

KW - Interpretable Machine Learning

KW - Photovoltaic Systems

KW - Root-Cause Analysis

UR - https://www.scopus.com/pages/publications/85142881053

U2 - 10.46354/i3m.2022.emss.042

DO - 10.46354/i3m.2022.emss.042

M3 - Conference contribution

AN - SCOPUS:85142881053

T3 - 34th European Modeling and Simulation Symposium, EMSS 2022

BT - 34th European Modeling and Simulation Symposium, EMSS 2022

A2 - Affenzeller, Michael

A2 - Bruzzone, Agostino G.

A2 - Jimenez, Emilio

A2 - Longo, Francesco

A2 - Petrillo, Antonella

PB - DIME UNIVERSITY OF GENOA

T2 - 34th European Modeling and Simulation Symposium, EMSS 2022

Y2 - 19 September 2022 through 21 September 2022

ER -

Zenisek J, Bachinger F, Pitzer E , Wagner S , Affenzeller M. Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities. In Affenzeller M, Bruzzone AG, Jimenez E, Longo F, Petrillo A, editors, 34th European Modeling and Simulation Symposium, EMSS 2022. DIME UNIVERSITY OF GENOA. 2022. 042. (34th European Modeling and Simulation Symposium, EMSS 2022). doi: 10.46354/i3m.2022.emss.042

Utilizing Interpretable Machine Learning to detect Dynamics in Energy Communities

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this