Adaptive Machine Learning Techniques for Enhancing Smart Grid Data Integrity

Ensuring data integrity in smart power grids is crucial for their optimized operation and planning. However, the increasing penetration of renewable energy sources and the emergence of flexible loads like electric vehicles create significant uncertainties and complexities in data patterns. Tradition...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Anderson, Ibar Federico
Formato: Articulo
Lenguaje:Inglés
Publicado: 2024
Materias:
Informática
Smart grid
Machine Learning
Load Forecasting
Smart City
Energy
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/176829
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-176829
record_format dspace
spelling I19-R120-10915-1768292025-02-24T20:08:47Z http://sedici.unlp.edu.ar/handle/10915/176829 Adaptive Machine Learning Techniques for Enhancing Smart Grid Data Integrity Anderson, Ibar Federico 2024-06-22 2025-02-24T14:12:38Z en Informática Smart grid Machine Learning Load Forecasting Smart City Energy Ensuring data integrity in smart power grids is crucial for their optimized operation and planning. However, the increasing penetration of renewable energy sources and the emergence of flexible loads like electric vehicles create significant uncertainties and complexities in data patterns. Traditional centralized models struggle with data privacy concerns, communication overheads, and lack of model adaptiveness. This paper proposes adaptive machine-learning techniques for enhancing data integrity in smart grids. Local machine learning models are trained on distributed private datasets across different stations of the grid, and only the model parameters are communicated to a central server to create an aggregated global model, without exchanging any raw private data. The proposed approach harnesses edge resources efficiently through decentralized on-device training while providing enhanced accuracy and personalization over centralized models. Several experiments conducted on electricity consumption data validate the effectiveness of our approach in handling complex spatiotemporal changes and generating station-specific adaptive forecasts. By adopting a decentralized approach, our methodology seeks to enhance grid resilience by preserving data privacy, mitigating security risks, and optimizing the efficiency of smart microgrid operations. The proposed solution can enable optimized capacity planning and retail pricing for sustainable grids of the future. Facultad de Artes Articulo Articulo http://creativecommons.org/licenses/by/4.0/ Creative Commons Attribution 4.0 International (CC BY 4.0) application/pdf
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Informática
Smart grid
Machine Learning
Load Forecasting
Smart City
Energy
spellingShingle Informática
Smart grid
Machine Learning
Load Forecasting
Smart City
Energy
Anderson, Ibar Federico
Adaptive Machine Learning Techniques for Enhancing Smart Grid Data Integrity
topic_facet Informática
Smart grid
Machine Learning
Load Forecasting
Smart City
Energy
description Ensuring data integrity in smart power grids is crucial for their optimized operation and planning. However, the increasing penetration of renewable energy sources and the emergence of flexible loads like electric vehicles create significant uncertainties and complexities in data patterns. Traditional centralized models struggle with data privacy concerns, communication overheads, and lack of model adaptiveness. This paper proposes adaptive machine-learning techniques for enhancing data integrity in smart grids. Local machine learning models are trained on distributed private datasets across different stations of the grid, and only the model parameters are communicated to a central server to create an aggregated global model, without exchanging any raw private data. The proposed approach harnesses edge resources efficiently through decentralized on-device training while providing enhanced accuracy and personalization over centralized models. Several experiments conducted on electricity consumption data validate the effectiveness of our approach in handling complex spatiotemporal changes and generating station-specific adaptive forecasts. By adopting a decentralized approach, our methodology seeks to enhance grid resilience by preserving data privacy, mitigating security risks, and optimizing the efficiency of smart microgrid operations. The proposed solution can enable optimized capacity planning and retail pricing for sustainable grids of the future.
format Articulo
Articulo
author Anderson, Ibar Federico
author_facet Anderson, Ibar Federico
author_sort Anderson, Ibar Federico
title Adaptive Machine Learning Techniques for Enhancing Smart Grid Data Integrity
title_short Adaptive Machine Learning Techniques for Enhancing Smart Grid Data Integrity
title_full Adaptive Machine Learning Techniques for Enhancing Smart Grid Data Integrity
title_fullStr Adaptive Machine Learning Techniques for Enhancing Smart Grid Data Integrity
title_full_unstemmed Adaptive Machine Learning Techniques for Enhancing Smart Grid Data Integrity
title_sort adaptive machine learning techniques for enhancing smart grid data integrity
publishDate 2024
url http://sedici.unlp.edu.ar/handle/10915/176829
work_keys_str_mv AT andersonibarfederico adaptivemachinelearningtechniquesforenhancingsmartgriddataintegrity
_version_ 1847925288117207040

Ejemplares similares