A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital Twins

Digital-twin platforms are increasingly adopted in energy infrastructure management for smart grids. Novel opportunities arise from emerging artificial intelligence technologies to increase user trust by enhancing predictive and prescriptive analytics capabilities and by improving user interaction p...

Full description

Saved in:
Bibliographic Details
Main Authors: Saverio Ieva, Davide Loconte, Giuseppe Loseto, Michele Ruta, Floriano Scioscia, Davide Marche, Marianna Notarnicola
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Smart Cities
Subjects:
Online Access:https://www.mdpi.com/2624-6511/7/6/121
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850239181508313088
author Saverio Ieva
Davide Loconte
Giuseppe Loseto
Michele Ruta
Floriano Scioscia
Davide Marche
Marianna Notarnicola
author_facet Saverio Ieva
Davide Loconte
Giuseppe Loseto
Michele Ruta
Floriano Scioscia
Davide Marche
Marianna Notarnicola
author_sort Saverio Ieva
collection DOAJ
description Digital-twin platforms are increasingly adopted in energy infrastructure management for smart grids. Novel opportunities arise from emerging artificial intelligence technologies to increase user trust by enhancing predictive and prescriptive analytics capabilities and by improving user interaction paradigms. This paper presents a novel data-driven and knowledge-based energy digital-twin framework and architecture. Data integration and mining based on machine learning are integrated into a knowledge graph annotating asset status data, prediction outcomes, and background domain knowledge in order to support a retrieval-augmented generation approach, which enhances a conversational virtual assistant based on a large language model to provide user decision support in asset management and maintenance. Components of the proposed architecture have been mapped to commercial-off-the-shelf tools to implement a prototype framework, exploited in a case study on the management of a section of the high-voltage energy infrastructure in central Italy.
format Article
id doaj-art-9f7055dcb5f7472baf8d55ed9ea3de70
institution OA Journals
issn 2624-6511
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Smart Cities
spelling doaj-art-9f7055dcb5f7472baf8d55ed9ea3de702025-08-20T02:01:14ZengMDPI AGSmart Cities2624-65112024-10-01763095312010.3390/smartcities7060121A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital TwinsSaverio Ieva0Davide Loconte1Giuseppe Loseto2Michele Ruta3Floriano Scioscia4Davide Marche5Marianna Notarnicola6Department of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, ItalyDepartment of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, ItalydonkeyPower S.r.l., Via E. Orabona 4, I-70125 Bari, ItalyDepartment of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, ItalyDepartment of Electrical and Information Engineering, Polytechnic University of Bari, Via E. Orabona 4, I-70125 Bari, ItalyLutech S.p.A., Via M. Gorki 30/32C, I-20092 Cinisello Balsamo, ItalyLutech S.p.A., Via M. Gorki 30/32C, I-20092 Cinisello Balsamo, ItalyDigital-twin platforms are increasingly adopted in energy infrastructure management for smart grids. Novel opportunities arise from emerging artificial intelligence technologies to increase user trust by enhancing predictive and prescriptive analytics capabilities and by improving user interaction paradigms. This paper presents a novel data-driven and knowledge-based energy digital-twin framework and architecture. Data integration and mining based on machine learning are integrated into a knowledge graph annotating asset status data, prediction outcomes, and background domain knowledge in order to support a retrieval-augmented generation approach, which enhances a conversational virtual assistant based on a large language model to provide user decision support in asset management and maintenance. Components of the proposed architecture have been mapped to commercial-off-the-shelf tools to implement a prototype framework, exploited in a case study on the management of a section of the high-voltage energy infrastructure in central Italy.https://www.mdpi.com/2624-6511/7/6/121digital twinenergy infrastructuresenergy managementretrieval-augmented generationnatural user interface
spellingShingle Saverio Ieva
Davide Loconte
Giuseppe Loseto
Michele Ruta
Floriano Scioscia
Davide Marche
Marianna Notarnicola
A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital Twins
Smart Cities
digital twin
energy infrastructures
energy management
retrieval-augmented generation
natural user interface
title A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital Twins
title_full A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital Twins
title_fullStr A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital Twins
title_full_unstemmed A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital Twins
title_short A Retrieval-Augmented Generation Approach for Data-Driven Energy Infrastructure Digital Twins
title_sort retrieval augmented generation approach for data driven energy infrastructure digital twins
topic digital twin
energy infrastructures
energy management
retrieval-augmented generation
natural user interface
url https://www.mdpi.com/2624-6511/7/6/121
work_keys_str_mv AT saverioieva aretrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT davideloconte aretrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT giuseppeloseto aretrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT micheleruta aretrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT florianoscioscia aretrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT davidemarche aretrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT mariannanotarnicola aretrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT saverioieva retrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT davideloconte retrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT giuseppeloseto retrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT micheleruta retrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT florianoscioscia retrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT davidemarche retrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins
AT mariannanotarnicola retrievalaugmentedgenerationapproachfordatadrivenenergyinfrastructuredigitaltwins