Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions
Multi-energy microgrids (MEMG) play an important role in promoting carbon neutrality and achieving sustainable development. This study investigates an effective energy management strategy (EMS) for MEMG. First, an energy management system model that allows for intra-microgrid energy conversion is de...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2023-12-01
|
Series: | Global Energy Interconnection |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2096511723000944 |
_version_ | 1797376661617901568 |
---|---|
author | Yanhong Yang Tengfei Ma Haitao Li Yiran Liu Chenghong Tang Wei Pei |
author_facet | Yanhong Yang Tengfei Ma Haitao Li Yiran Liu Chenghong Tang Wei Pei |
author_sort | Yanhong Yang |
collection | DOAJ |
description | Multi-energy microgrids (MEMG) play an important role in promoting carbon neutrality and achieving sustainable development. This study investigates an effective energy management strategy (EMS) for MEMG. First, an energy management system model that allows for intra-microgrid energy conversion is developed, and the corresponding Markov decision process (MDP) problem is formulated. Subsequently, an improved double deep Q network (iDDQN) algorithm is proposed to enhance the exploration ability by modifying the calculation of the Q value, and a prioritized experience replay (PER) is introduced into the iDDQN to improve the training speed and effectiveness. Finally, taking advantage of the federated learning (FL) and iDDQN algorithms, a federated iDDQN is proposed to design an MEMG energy management strategy to enable each microgrid to share its experiences in the form of local neural network (NN) parameters with the federation layer, thus ensuring the privacy and security of data. The simulation results validate the superior performance of the proposed energy management strategy in minimizing the economic costs of the MEMG while reducing CO2 emissions and protecting data privacy. |
first_indexed | 2024-03-08T19:41:50Z |
format | Article |
id | doaj.art-c8b006b1428d48dfa676f4b77e9d7c81 |
institution | Directory Open Access Journal |
issn | 2096-5117 |
language | English |
last_indexed | 2024-03-08T19:41:50Z |
publishDate | 2023-12-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | Global Energy Interconnection |
spelling | doaj.art-c8b006b1428d48dfa676f4b77e9d7c812023-12-25T04:06:02ZengKeAi Communications Co., Ltd.Global Energy Interconnection2096-51172023-12-0166689699Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissionsYanhong Yang0Tengfei Ma1Haitao Li2Yiran Liu3Chenghong Tang4Wei Pei5Institute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, PR ChinaInstitute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, PR ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, PR ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, PR ChinaState Grid Electric Power Research Institute, Nanjing, 211100, PR ChinaInstitute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, PR ChinaMulti-energy microgrids (MEMG) play an important role in promoting carbon neutrality and achieving sustainable development. This study investigates an effective energy management strategy (EMS) for MEMG. First, an energy management system model that allows for intra-microgrid energy conversion is developed, and the corresponding Markov decision process (MDP) problem is formulated. Subsequently, an improved double deep Q network (iDDQN) algorithm is proposed to enhance the exploration ability by modifying the calculation of the Q value, and a prioritized experience replay (PER) is introduced into the iDDQN to improve the training speed and effectiveness. Finally, taking advantage of the federated learning (FL) and iDDQN algorithms, a federated iDDQN is proposed to design an MEMG energy management strategy to enable each microgrid to share its experiences in the form of local neural network (NN) parameters with the federation layer, thus ensuring the privacy and security of data. The simulation results validate the superior performance of the proposed energy management strategy in minimizing the economic costs of the MEMG while reducing CO2 emissions and protecting data privacy.http://www.sciencedirect.com/science/article/pii/S2096511723000944Multi-energy microgridFederated learningImproved double DQNEnergy conversion |
spellingShingle | Yanhong Yang Tengfei Ma Haitao Li Yiran Liu Chenghong Tang Wei Pei Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions Global Energy Interconnection Multi-energy microgrid Federated learning Improved double DQN Energy conversion |
title | Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions |
title_full | Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions |
title_fullStr | Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions |
title_full_unstemmed | Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions |
title_short | Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions |
title_sort | federated double dqn based multi energy microgrid energy management strategy considering carbon emissions |
topic | Multi-energy microgrid Federated learning Improved double DQN Energy conversion |
url | http://www.sciencedirect.com/science/article/pii/S2096511723000944 |
work_keys_str_mv | AT yanhongyang federateddoubledqnbasedmultienergymicrogridenergymanagementstrategyconsideringcarbonemissions AT tengfeima federateddoubledqnbasedmultienergymicrogridenergymanagementstrategyconsideringcarbonemissions AT haitaoli federateddoubledqnbasedmultienergymicrogridenergymanagementstrategyconsideringcarbonemissions AT yiranliu federateddoubledqnbasedmultienergymicrogridenergymanagementstrategyconsideringcarbonemissions AT chenghongtang federateddoubledqnbasedmultienergymicrogridenergymanagementstrategyconsideringcarbonemissions AT weipei federateddoubledqnbasedmultienergymicrogridenergymanagementstrategyconsideringcarbonemissions |