Multi-Timescale Voltage Control Method Using Limited Measurable Information with Explainable Deep Reinforcement Learning

The integration of photovoltaic (PV) power generation systems has significantly increased the complexity of voltage distribution in power grids, making it challenging for conventional Load Ratio Control Transformers (LRTs) to manage voltage fluctuations caused by weather-dependent PV output variatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Fumiya Matsushima, Mutsumi Aoki, Yuta Nakamura, Suresh Chand Verma, Katsuhisa Ueda, Yusuke Imanishi
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/3/653
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717711934849024
author Fumiya Matsushima
Mutsumi Aoki
Yuta Nakamura
Suresh Chand Verma
Katsuhisa Ueda
Yusuke Imanishi
author_facet Fumiya Matsushima
Mutsumi Aoki
Yuta Nakamura
Suresh Chand Verma
Katsuhisa Ueda
Yusuke Imanishi
author_sort Fumiya Matsushima
collection DOAJ
description The integration of photovoltaic (PV) power generation systems has significantly increased the complexity of voltage distribution in power grids, making it challenging for conventional Load Ratio Control Transformers (LRTs) to manage voltage fluctuations caused by weather-dependent PV output variations. Power Conditioning Systems (PCSs) interconnected with PV installations are increasingly considered for voltage control to address these challenges. This study proposes a Machine Learning (ML)-based control method for sub-transmission grids, integrating long-term LRT tap-changing with short-term reactive power control of PCSs. The approach estimates the voltage at each grid node using a Deep Neural Network (DNN) that processes measurable substation data. Based on these estimated voltages, the method determines optimal LRT tap positions and PCS reactive power outputs using Deep Reinforcement Learning (DRL). This enables real-time voltage monitoring and control using only substation measurements, even in grids without extensive sensor installations, ensuring all node voltages remain within specified limits. To improve the model’s transparency, Shapley Additive Explanation (SHAP), an Explainable AI (XAI) technique, is applied to the DRL model. SHAP enhances interpretability and confirms the effectiveness of the proposed method. Numerical simulations further validate its performance, demonstrating its potential for effective voltage management in modern power grids.
format Article
id doaj-art-3f57cbb417d6447f91577a31cb4b29b1
institution DOAJ
issn 1996-1073
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-3f57cbb417d6447f91577a31cb4b29b12025-08-20T03:12:35ZengMDPI AGEnergies1996-10732025-01-0118365310.3390/en18030653Multi-Timescale Voltage Control Method Using Limited Measurable Information with Explainable Deep Reinforcement LearningFumiya Matsushima0Mutsumi Aoki1Yuta Nakamura2Suresh Chand Verma3Katsuhisa Ueda4Yusuke Imanishi5Department of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya 466-8555, JapanDepartment of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya 466-8555, JapanDepartment of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya 466-8555, JapanDepartment of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya 466-8555, JapanDepartment of Electric Power Research and Development Center, Chubu Electric Power Co., Inc., Nagoya 459-8522, JapanDepartment of Electric Power Research and Development Center, Chubu Electric Power Co., Inc., Nagoya 459-8522, JapanThe integration of photovoltaic (PV) power generation systems has significantly increased the complexity of voltage distribution in power grids, making it challenging for conventional Load Ratio Control Transformers (LRTs) to manage voltage fluctuations caused by weather-dependent PV output variations. Power Conditioning Systems (PCSs) interconnected with PV installations are increasingly considered for voltage control to address these challenges. This study proposes a Machine Learning (ML)-based control method for sub-transmission grids, integrating long-term LRT tap-changing with short-term reactive power control of PCSs. The approach estimates the voltage at each grid node using a Deep Neural Network (DNN) that processes measurable substation data. Based on these estimated voltages, the method determines optimal LRT tap positions and PCS reactive power outputs using Deep Reinforcement Learning (DRL). This enables real-time voltage monitoring and control using only substation measurements, even in grids without extensive sensor installations, ensuring all node voltages remain within specified limits. To improve the model’s transparency, Shapley Additive Explanation (SHAP), an Explainable AI (XAI) technique, is applied to the DRL model. SHAP enhances interpretability and confirms the effectiveness of the proposed method. Numerical simulations further validate its performance, demonstrating its potential for effective voltage management in modern power grids.https://www.mdpi.com/1996-1073/18/3/653distributed energy resourcesmulti-timescale voltage controldeep reinforcement learningShapley additive explanationvoltage estimationdeep neural network
spellingShingle Fumiya Matsushima
Mutsumi Aoki
Yuta Nakamura
Suresh Chand Verma
Katsuhisa Ueda
Yusuke Imanishi
Multi-Timescale Voltage Control Method Using Limited Measurable Information with Explainable Deep Reinforcement Learning
Energies
distributed energy resources
multi-timescale voltage control
deep reinforcement learning
Shapley additive explanation
voltage estimation
deep neural network
title Multi-Timescale Voltage Control Method Using Limited Measurable Information with Explainable Deep Reinforcement Learning
title_full Multi-Timescale Voltage Control Method Using Limited Measurable Information with Explainable Deep Reinforcement Learning
title_fullStr Multi-Timescale Voltage Control Method Using Limited Measurable Information with Explainable Deep Reinforcement Learning
title_full_unstemmed Multi-Timescale Voltage Control Method Using Limited Measurable Information with Explainable Deep Reinforcement Learning
title_short Multi-Timescale Voltage Control Method Using Limited Measurable Information with Explainable Deep Reinforcement Learning
title_sort multi timescale voltage control method using limited measurable information with explainable deep reinforcement learning
topic distributed energy resources
multi-timescale voltage control
deep reinforcement learning
Shapley additive explanation
voltage estimation
deep neural network
url https://www.mdpi.com/1996-1073/18/3/653
work_keys_str_mv AT fumiyamatsushima multitimescalevoltagecontrolmethodusinglimitedmeasurableinformationwithexplainabledeepreinforcementlearning
AT mutsumiaoki multitimescalevoltagecontrolmethodusinglimitedmeasurableinformationwithexplainabledeepreinforcementlearning
AT yutanakamura multitimescalevoltagecontrolmethodusinglimitedmeasurableinformationwithexplainabledeepreinforcementlearning
AT sureshchandverma multitimescalevoltagecontrolmethodusinglimitedmeasurableinformationwithexplainabledeepreinforcementlearning
AT katsuhisaueda multitimescalevoltagecontrolmethodusinglimitedmeasurableinformationwithexplainabledeepreinforcementlearning
AT yusukeimanishi multitimescalevoltagecontrolmethodusinglimitedmeasurableinformationwithexplainabledeepreinforcementlearning