Smart Management of Energy Losses in Distribution Networks Using Deep Neural Networks

This research presents an advanced methodology for smart management of energy losses in electrical distribution networks by leveraging deep neural network architectures. The primary objective is to enhance the accuracy of short-term forecasting for nodal loads and corresponding energy losses, enabli...

Full description

Saved in:
Bibliographic Details
Main Authors: Ihor Blinov, Virginijus Radziukynas, Pavlo Shymaniuk, Artur Dyczko, Kinga Stecuła, Viktoriia Sychova, Volodymyr Miroshnyk, Roman Dychkovskyi
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/12/3156
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849472264425177088
author Ihor Blinov
Virginijus Radziukynas
Pavlo Shymaniuk
Artur Dyczko
Kinga Stecuła
Viktoriia Sychova
Volodymyr Miroshnyk
Roman Dychkovskyi
author_facet Ihor Blinov
Virginijus Radziukynas
Pavlo Shymaniuk
Artur Dyczko
Kinga Stecuła
Viktoriia Sychova
Volodymyr Miroshnyk
Roman Dychkovskyi
author_sort Ihor Blinov
collection DOAJ
description This research presents an advanced methodology for smart management of energy losses in electrical distribution networks by leveraging deep neural network architectures. The primary objective is to enhance the accuracy of short-term forecasting for nodal loads and corresponding energy losses, enabling more efficient and intelligent grid operation. Two predictive approaches were explored: the first involves separate forecasting of nodal loads followed by loss calculations, while the second directly estimates network-wide energy losses. For model implementation, Long Short-Term Memory (LSTM) networks and the enhanced Residual Network (eResNet) architecture, developed at the Institute of Electrodynamics of the National Academy of Sciences of Ukraine, were utilized. The models were validated using retrospective data from a Ukrainian Distribution System Operator (DSO) covering the period from 2017 to 2019 with 30 min sampling intervals. An adapted CIGRE benchmark medium-voltage network was employed to simulate real-world conditions. Given the presence of anomalies and missing values in the operational data, a two-stage preprocessing algorithm incorporating DBSCAN clustering was applied for data cleansing and imputation. The results indicate a Mean Absolute Percentage Error (MAPE) of just 3.29% for nodal load forecasts, which significantly outperforms conventional methods. These findings affirm the feasibility of integrating such models into Smart Grid infrastructures to improve decision-making, minimize operational losses, and reduce the costs associated with energy loss compensation. This study provides a practical framework for data-driven energy loss management, emphasizing the growing role of artificial intelligence in modern power systems.
format Article
id doaj-art-c371d7feccf047d8b0f70fd48405dbbf
institution Kabale University
issn 1996-1073
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-c371d7feccf047d8b0f70fd48405dbbf2025-08-20T03:24:35ZengMDPI AGEnergies1996-10732025-06-011812315610.3390/en18123156Smart Management of Energy Losses in Distribution Networks Using Deep Neural NetworksIhor Blinov0Virginijus Radziukynas1Pavlo Shymaniuk2Artur Dyczko3Kinga Stecuła4Viktoriia Sychova5Volodymyr Miroshnyk6Roman Dychkovskyi7Institute of Electrodynamics NASU, Department of Modelling of Electrical Power Objects and Systems, 03057 Kyiv, UkraineSmart Grids and Renewable Energy Laboratory, Lithuanian Energy Institute, 44403 Kaunas, LithuaniaInstitute of Electrodynamics NASU, Department of Modelling of Electrical Power Objects and Systems, 03057 Kyiv, UkraineMineral and Energy Economy Research Institute, Polish Academy of Sciences, 7A Wybickiego St., 31-261 Krakow, PolandFaculty of Organization and Management, Silesian University of Technology, 44-100 Gliwice, PolandInstitute of Electrodynamics NASU, Department of Modelling of Electrical Power Objects and Systems, 03057 Kyiv, UkraineInstitute of Electrodynamics NASU, Department of Modelling of Electrical Power Objects and Systems, 03057 Kyiv, UkraineDepartment of Mining Engineering and Education, Dnipro University of Technology, 19 Yavornytskoho Ave., 49005 Dnipro, UkraineThis research presents an advanced methodology for smart management of energy losses in electrical distribution networks by leveraging deep neural network architectures. The primary objective is to enhance the accuracy of short-term forecasting for nodal loads and corresponding energy losses, enabling more efficient and intelligent grid operation. Two predictive approaches were explored: the first involves separate forecasting of nodal loads followed by loss calculations, while the second directly estimates network-wide energy losses. For model implementation, Long Short-Term Memory (LSTM) networks and the enhanced Residual Network (eResNet) architecture, developed at the Institute of Electrodynamics of the National Academy of Sciences of Ukraine, were utilized. The models were validated using retrospective data from a Ukrainian Distribution System Operator (DSO) covering the period from 2017 to 2019 with 30 min sampling intervals. An adapted CIGRE benchmark medium-voltage network was employed to simulate real-world conditions. Given the presence of anomalies and missing values in the operational data, a two-stage preprocessing algorithm incorporating DBSCAN clustering was applied for data cleansing and imputation. The results indicate a Mean Absolute Percentage Error (MAPE) of just 3.29% for nodal load forecasts, which significantly outperforms conventional methods. These findings affirm the feasibility of integrating such models into Smart Grid infrastructures to improve decision-making, minimize operational losses, and reduce the costs associated with energy loss compensation. This study provides a practical framework for data-driven energy loss management, emphasizing the growing role of artificial intelligence in modern power systems.https://www.mdpi.com/1996-1073/18/12/3156energy loss forecastingdeep neural networksdata preprocessingpower system efficiencyartificial intelligence in energyelectrical grid optimization
spellingShingle Ihor Blinov
Virginijus Radziukynas
Pavlo Shymaniuk
Artur Dyczko
Kinga Stecuła
Viktoriia Sychova
Volodymyr Miroshnyk
Roman Dychkovskyi
Smart Management of Energy Losses in Distribution Networks Using Deep Neural Networks
Energies
energy loss forecasting
deep neural networks
data preprocessing
power system efficiency
artificial intelligence in energy
electrical grid optimization
title Smart Management of Energy Losses in Distribution Networks Using Deep Neural Networks
title_full Smart Management of Energy Losses in Distribution Networks Using Deep Neural Networks
title_fullStr Smart Management of Energy Losses in Distribution Networks Using Deep Neural Networks
title_full_unstemmed Smart Management of Energy Losses in Distribution Networks Using Deep Neural Networks
title_short Smart Management of Energy Losses in Distribution Networks Using Deep Neural Networks
title_sort smart management of energy losses in distribution networks using deep neural networks
topic energy loss forecasting
deep neural networks
data preprocessing
power system efficiency
artificial intelligence in energy
electrical grid optimization
url https://www.mdpi.com/1996-1073/18/12/3156
work_keys_str_mv AT ihorblinov smartmanagementofenergylossesindistributionnetworksusingdeepneuralnetworks
AT virginijusradziukynas smartmanagementofenergylossesindistributionnetworksusingdeepneuralnetworks
AT pavloshymaniuk smartmanagementofenergylossesindistributionnetworksusingdeepneuralnetworks
AT arturdyczko smartmanagementofenergylossesindistributionnetworksusingdeepneuralnetworks
AT kingastecuła smartmanagementofenergylossesindistributionnetworksusingdeepneuralnetworks
AT viktoriiasychova smartmanagementofenergylossesindistributionnetworksusingdeepneuralnetworks
AT volodymyrmiroshnyk smartmanagementofenergylossesindistributionnetworksusingdeepneuralnetworks
AT romandychkovskyi smartmanagementofenergylossesindistributionnetworksusingdeepneuralnetworks