Real-Time AI-Based Power Demand Forecasting for Peak Shaving and Consumption Reduction Using Vehicle-to-Grid and Reused Energy Storage Systems: A Case Study at a Business Center on Jeju Island

The increasing demand for electricity and the environmental challenges associated with traditional fossil fuel-based power generation have accelerated the global transition to renewable energy sources. While renewable energy offers significant advantages, including low carbon emissions and sustainab...

Full description

Saved in:
Bibliographic Details
Main Authors: Kibaek Kim, Dongwoo Ko, Juwon Jung, Jeng-Ok Ryu, Kyung-Ja Hur, Young-Joo Kim
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/6/3050
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392560822288384
author Kibaek Kim
Dongwoo Ko
Juwon Jung
Jeng-Ok Ryu
Kyung-Ja Hur
Young-Joo Kim
author_facet Kibaek Kim
Dongwoo Ko
Juwon Jung
Jeng-Ok Ryu
Kyung-Ja Hur
Young-Joo Kim
author_sort Kibaek Kim
collection DOAJ
description The increasing demand for electricity and the environmental challenges associated with traditional fossil fuel-based power generation have accelerated the global transition to renewable energy sources. While renewable energy offers significant advantages, including low carbon emissions and sustainability, its inherent variability and intermittency create challenges for grid stability and energy management. This study contributes to addressing these challenges by developing an AI-driven power consumption forecasting system. The core of the proposed system is a multi-cluster long short-term memory model (MC-LSTM), which combines k-means clustering with LSTM neural networks to enhance forecasting accuracy. The MC-LSTM model achieved an overall prediction accuracy of 97.93%, enabling dynamic, real-time demand-side energy management. Furthermore, to validate its effectiveness, the system integrates vehicle-to-grid technology and reused energy storage systems as external energy sources. A real-world demonstration was conducted in a commercial building on Jeju Island, where the AI-driven system successfully reduced total energy consumption by 21.3% through optimized peak shaving and load balancing. The proposed system provides a practical framework for enhancing grid stability, optimizing energy distribution, and reducing dependence on centralized power systems.
format Article
id doaj-art-bb950ef01b5141dea59f9e5c0b65e38c
institution Kabale University
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-bb950ef01b5141dea59f9e5c0b65e38c2025-08-20T03:40:44ZengMDPI AGApplied Sciences2076-34172025-03-01156305010.3390/app15063050Real-Time AI-Based Power Demand Forecasting for Peak Shaving and Consumption Reduction Using Vehicle-to-Grid and Reused Energy Storage Systems: A Case Study at a Business Center on Jeju IslandKibaek Kim0Dongwoo Ko1Juwon Jung2Jeng-Ok Ryu3Kyung-Ja Hur4Young-Joo Kim5Department of Mechanical Engineering, Yonsei University, Seoul 03722, Republic of KoreaDepartment of Mechanical Engineering, Yonsei University, Seoul 03722, Republic of KoreaDepartment of Mechanical Engineering, Yonsei University, Seoul 03722, Republic of KoreaSmart Grid Business Division/R&D Center, Daekyung Engineering Co., Ltd., Jeju 63309, Republic of KoreaSmart Grid Business Division/R&D Center, Daekyung Engineering Co., Ltd., Jeju 63309, Republic of KoreaDepartment of Mechanical Engineering, Yonsei University, Seoul 03722, Republic of KoreaThe increasing demand for electricity and the environmental challenges associated with traditional fossil fuel-based power generation have accelerated the global transition to renewable energy sources. While renewable energy offers significant advantages, including low carbon emissions and sustainability, its inherent variability and intermittency create challenges for grid stability and energy management. This study contributes to addressing these challenges by developing an AI-driven power consumption forecasting system. The core of the proposed system is a multi-cluster long short-term memory model (MC-LSTM), which combines k-means clustering with LSTM neural networks to enhance forecasting accuracy. The MC-LSTM model achieved an overall prediction accuracy of 97.93%, enabling dynamic, real-time demand-side energy management. Furthermore, to validate its effectiveness, the system integrates vehicle-to-grid technology and reused energy storage systems as external energy sources. A real-world demonstration was conducted in a commercial building on Jeju Island, where the AI-driven system successfully reduced total energy consumption by 21.3% through optimized peak shaving and load balancing. The proposed system provides a practical framework for enhancing grid stability, optimizing energy distribution, and reducing dependence on centralized power systems.https://www.mdpi.com/2076-3417/15/6/3050demand forecastingartificial intelligencevehicle-to-gridreused energy storage systempeak shavingenergy management
spellingShingle Kibaek Kim
Dongwoo Ko
Juwon Jung
Jeng-Ok Ryu
Kyung-Ja Hur
Young-Joo Kim
Real-Time AI-Based Power Demand Forecasting for Peak Shaving and Consumption Reduction Using Vehicle-to-Grid and Reused Energy Storage Systems: A Case Study at a Business Center on Jeju Island
Applied Sciences
demand forecasting
artificial intelligence
vehicle-to-grid
reused energy storage system
peak shaving
energy management
title Real-Time AI-Based Power Demand Forecasting for Peak Shaving and Consumption Reduction Using Vehicle-to-Grid and Reused Energy Storage Systems: A Case Study at a Business Center on Jeju Island
title_full Real-Time AI-Based Power Demand Forecasting for Peak Shaving and Consumption Reduction Using Vehicle-to-Grid and Reused Energy Storage Systems: A Case Study at a Business Center on Jeju Island
title_fullStr Real-Time AI-Based Power Demand Forecasting for Peak Shaving and Consumption Reduction Using Vehicle-to-Grid and Reused Energy Storage Systems: A Case Study at a Business Center on Jeju Island
title_full_unstemmed Real-Time AI-Based Power Demand Forecasting for Peak Shaving and Consumption Reduction Using Vehicle-to-Grid and Reused Energy Storage Systems: A Case Study at a Business Center on Jeju Island
title_short Real-Time AI-Based Power Demand Forecasting for Peak Shaving and Consumption Reduction Using Vehicle-to-Grid and Reused Energy Storage Systems: A Case Study at a Business Center on Jeju Island
title_sort real time ai based power demand forecasting for peak shaving and consumption reduction using vehicle to grid and reused energy storage systems a case study at a business center on jeju island
topic demand forecasting
artificial intelligence
vehicle-to-grid
reused energy storage system
peak shaving
energy management
url https://www.mdpi.com/2076-3417/15/6/3050
work_keys_str_mv AT kibaekkim realtimeaibasedpowerdemandforecastingforpeakshavingandconsumptionreductionusingvehicletogridandreusedenergystoragesystemsacasestudyatabusinesscenteronjejuisland
AT dongwooko realtimeaibasedpowerdemandforecastingforpeakshavingandconsumptionreductionusingvehicletogridandreusedenergystoragesystemsacasestudyatabusinesscenteronjejuisland
AT juwonjung realtimeaibasedpowerdemandforecastingforpeakshavingandconsumptionreductionusingvehicletogridandreusedenergystoragesystemsacasestudyatabusinesscenteronjejuisland
AT jengokryu realtimeaibasedpowerdemandforecastingforpeakshavingandconsumptionreductionusingvehicletogridandreusedenergystoragesystemsacasestudyatabusinesscenteronjejuisland
AT kyungjahur realtimeaibasedpowerdemandforecastingforpeakshavingandconsumptionreductionusingvehicletogridandreusedenergystoragesystemsacasestudyatabusinesscenteronjejuisland
AT youngjookim realtimeaibasedpowerdemandforecastingforpeakshavingandconsumptionreductionusingvehicletogridandreusedenergystoragesystemsacasestudyatabusinesscenteronjejuisland