Fault Prediction and Reconfiguration Optimization in Smart Grids: AI-Driven Approach

David Carrascal, Paula Bartolomé, Elisa Rojas (), Diego Lopez-Pajares, Nicolas Manso and Javier Diaz-Fuentes
Additional contact information
David Carrascal: Universidad de Alcalá, Departamento de Automática, Escuela Politécnica Superior, 28805 Alcalá de Henares, Spain
Paula Bartolomé: Universidad de Alcalá, Departamento de Automática, Escuela Politécnica Superior, 28805 Alcalá de Henares, Spain
Elisa Rojas: Universidad de Alcalá, Departamento de Automática, Escuela Politécnica Superior, 28805 Alcalá de Henares, Spain
Diego Lopez-Pajares: Universidad de Alcalá, Departamento de Automática, Escuela Politécnica Superior, 28805 Alcalá de Henares, Spain
Nicolas Manso: Universidad de Alcalá, Departamento de Automática, Escuela Politécnica Superior, 28805 Alcalá de Henares, Spain
Javier Diaz-Fuentes: Universidad de Alcalá, Departamento de Automática, Escuela Politécnica Superior, 28805 Alcalá de Henares, Spain

Future Internet, 2024, vol. 16, issue 11, 1-26

Abstract: Smart grids (SGs) are essential for the efficient and distributed management of electrical distribution networks. A key task in SG management is fault detection and subsequently, network reconfiguration to minimize power losses and balance loads. This process should minimize power losses while optimizing distribution by balancing loads across the grid. However, the current literature yields a lack of methods for efficient fault prediction and fast reconfiguration. To achieve this goal, this paper builds on DEN2DE, an adaptable routing and reconfiguration solution potentially applicable to SGs, and investigates its potential extension with AI-based fault prediction using real-world datasets and randomly generated topologies based on the IEEE 123 Node Test Feeder. The study applies models based on Machine Learning (ML) and Deep Learning (DL) techniques, specifically evaluating Random Forest (RF) and Support Vector Machine (SVM) as ML methods, and Artificial Neural Network (ANN) as a DL method, evaluating each for accuracy, precision, and recall. Results indicate that the RF model with Recursive Feature Elimination (RFECV) achieves 94.28% precision and 81.05% recall, surpassing SVM (precision 89.32%, recall 6.95%) and ANN (precision 72.17%, recall 13.49%) in fault detection accuracy and reliability.

Keywords: smart grids; AI; fault prediction; machine learning; deep learning (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/16/11/428/pdf (application/pdf)
https://www.mdpi.com/1999-5903/16/11/428/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:16:y:2024:i:11:p:428-:d:1525189

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().