A reinforcement learning based real-time energy management method for mobile microgrid considering photovoltaic uncertainty

With the ever-increasing awareness of worldwide greenhouse gas emissions, traditional diesel-driven ships are gradually being replaced by renewable energy ships. Zero-carbon power sources, such as photovoltaic (PV) power generation, are progressively integrated into electric ships. However, the unce...

Full description

Saved in:
Bibliographic Details
Main Authors: Huasong Fang, Huayue Zhang, Shuli Wen, Zhong Li, Zhilin Zeng, Miao Zhu, Pengfeng Lin
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:International Journal of Electrical Power & Energy Systems
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0142061525003928
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849390698996957184
author Huasong Fang
Huayue Zhang
Shuli Wen
Zhong Li
Zhilin Zeng
Miao Zhu
Pengfeng Lin
author_facet Huasong Fang
Huayue Zhang
Shuli Wen
Zhong Li
Zhilin Zeng
Miao Zhu
Pengfeng Lin
author_sort Huasong Fang
collection DOAJ
description With the ever-increasing awareness of worldwide greenhouse gas emissions, traditional diesel-driven ships are gradually being replaced by renewable energy ships. Zero-carbon power sources, such as photovoltaic (PV) power generation, are progressively integrated into electric ships. However, the uncertainty associated with onboard PV generation has become a critical factor limiting effective energy management on alternative energy ships. To address this issue, this paper proposes a real-time energy management optimization method based on reinforcement learning, specifically tailored to handle PV uncertainty and dynamic load variations during navigation. The proposed algorithm optimizes the energy flow between the onboard diesel generator and the energy storage system in real-time, aiming to minimize fuel consumption and enhance operational stability. Real-world shipboard microgrid data is utilized to perform case studies. Simulation results indicate that fuel consumption under the proposed approach is only 90.32% and 94.57% of that in scenarios without PV systems and traditional robust optimization methods, respectively. Moreover, the method effectively stabilizes the state of charge within a safe operational range of [0.2, 0.8], which is helpful for energy storage lifespan.
format Article
id doaj-art-f2bbf88cb66a41a596bc86f53113e5ce
institution Kabale University
issn 0142-0615
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series International Journal of Electrical Power & Energy Systems
spelling doaj-art-f2bbf88cb66a41a596bc86f53113e5ce2025-08-20T03:41:22ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-09-0117011084410.1016/j.ijepes.2025.110844A reinforcement learning based real-time energy management method for mobile microgrid considering photovoltaic uncertaintyHuasong Fang0Huayue Zhang1Shuli Wen2Zhong Li3Zhilin Zeng4Miao Zhu5Pengfeng Lin6School of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; Wuhan Ship Electric Propulsion Equipment Research Institute, Wuhan 430200, ChinaCollege of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China; Corresponding authors.School of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; Corresponding authors.Shanghai Marine Equipment Research Institute, Shanghai 200031, ChinaShanghai Marine Equipment Research Institute, Shanghai 200031, ChinaSchool of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaWith the ever-increasing awareness of worldwide greenhouse gas emissions, traditional diesel-driven ships are gradually being replaced by renewable energy ships. Zero-carbon power sources, such as photovoltaic (PV) power generation, are progressively integrated into electric ships. However, the uncertainty associated with onboard PV generation has become a critical factor limiting effective energy management on alternative energy ships. To address this issue, this paper proposes a real-time energy management optimization method based on reinforcement learning, specifically tailored to handle PV uncertainty and dynamic load variations during navigation. The proposed algorithm optimizes the energy flow between the onboard diesel generator and the energy storage system in real-time, aiming to minimize fuel consumption and enhance operational stability. Real-world shipboard microgrid data is utilized to perform case studies. Simulation results indicate that fuel consumption under the proposed approach is only 90.32% and 94.57% of that in scenarios without PV systems and traditional robust optimization methods, respectively. Moreover, the method effectively stabilizes the state of charge within a safe operational range of [0.2, 0.8], which is helpful for energy storage lifespan.http://www.sciencedirect.com/science/article/pii/S0142061525003928Reinforcement learningEnergy managementAll-electric shipPV uncertainty
spellingShingle Huasong Fang
Huayue Zhang
Shuli Wen
Zhong Li
Zhilin Zeng
Miao Zhu
Pengfeng Lin
A reinforcement learning based real-time energy management method for mobile microgrid considering photovoltaic uncertainty
International Journal of Electrical Power & Energy Systems
Reinforcement learning
Energy management
All-electric ship
PV uncertainty
title A reinforcement learning based real-time energy management method for mobile microgrid considering photovoltaic uncertainty
title_full A reinforcement learning based real-time energy management method for mobile microgrid considering photovoltaic uncertainty
title_fullStr A reinforcement learning based real-time energy management method for mobile microgrid considering photovoltaic uncertainty
title_full_unstemmed A reinforcement learning based real-time energy management method for mobile microgrid considering photovoltaic uncertainty
title_short A reinforcement learning based real-time energy management method for mobile microgrid considering photovoltaic uncertainty
title_sort reinforcement learning based real time energy management method for mobile microgrid considering photovoltaic uncertainty
topic Reinforcement learning
Energy management
All-electric ship
PV uncertainty
url http://www.sciencedirect.com/science/article/pii/S0142061525003928
work_keys_str_mv AT huasongfang areinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT huayuezhang areinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT shuliwen areinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT zhongli areinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT zhilinzeng areinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT miaozhu areinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT pengfenglin areinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT huasongfang reinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT huayuezhang reinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT shuliwen reinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT zhongli reinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT zhilinzeng reinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT miaozhu reinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty
AT pengfenglin reinforcementlearningbasedrealtimeenergymanagementmethodformobilemicrogridconsideringphotovoltaicuncertainty