Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/106144
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Electrical and Electronic Engineering | en_US |
dc.creator | Amin, MA | en_US |
dc.creator | Suleman, A | en_US |
dc.creator | Waseem, M | en_US |
dc.creator | Iqbal, T | en_US |
dc.creator | Aziz, S | en_US |
dc.creator | Faiz, MT | en_US |
dc.creator | Zulfiqar, L | en_US |
dc.creator | Saleh, AM | en_US |
dc.date.accessioned | 2024-05-03T00:45:27Z | - |
dc.date.available | 2024-05-03T00:45:27Z | - |
dc.identifier.uri | http://hdl.handle.net/10397/106144 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ | en_US |
dc.rights | The following publication M. A. Amin et al., "Renewable Energy Maximization for Pelagic Islands Network of Microgrids Through Battery Swapping Using Deep Reinforcement Learning," in IEEE Access, vol. 11, pp. 86196-86213, 2023 is available at https://dx.doi.org/10.1109/ACCESS.2023.3302895. | en_US |
dc.subject | Deep reinforcement learning | en_US |
dc.subject | Pelagic island | en_US |
dc.subject | Microgrids | en_US |
dc.subject | EMS | en_US |
dc.subject | Renewable energy | en_US |
dc.title | Renewable energy maximization for pelagic islands network of microgrids through battery swapping using deep reinforcement learning | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 86196 | en_US |
dc.identifier.epage | 86213 | en_US |
dc.identifier.volume | 11 | en_US |
dc.identifier.doi | 10.1109/ACCESS.2023.3302895 | en_US |
dcterms.abstract | The study proposes an energy management system of pelagic islands network microgrids (PINMGs) based on reinforcement learning (RL) under the effect of environmental factors. Furthermore, the day-ahead standard scheduling proposes an energy-sharing framework across islands by presenting a novel method to optimize the use of renewable energy (RE). Energy sharing across islands is critical for powering isolated islands that need electricity owing to a lack of renewable energy supplies to fulfill local demand. A two-stage cooperative multi-agent deep RL solution based on deep Q-learning (DQN) with central RL and island agents (IA) spread over several islands has been presented to tackle this difficulty. Because of its in-depth learning potential, deep RL-based systems effectively train and optimize their behaviors across several epochs compared to other machine learning or traditional methods. As a result, the centralized RL-based problem of scheduling charge battery sharing from resource-rich islands (SI) to load island networks (LIN) was addressed utilizing dueling DQN. Furthermore, due to its precise tracking, the case study compared the accuracy of various DQN approaches and further scheduling based on the dueling DQN. The need for LIN is also stochastic because of variable demand and charging patterns. Hence, the simulation results, including energy scheduling through the ship, are confirmed by optimizing RE consumption via sharing across several islands, and the effectiveness of the proposed method is validated by state and action perturbation to guarantee robustness. | en_US |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | IEEE access, 2023, v. 11, p. 86196-86213 | en_US |
dcterms.isPartOf | IEEE access | en_US |
dcterms.issued | 2023 | - |
dc.identifier.isi | WOS:001051666000001 | - |
dc.identifier.eissn | 2169-3536 | en_US |
dc.description.validate | 202405 bcrc | en_US |
dc.description.oa | Version of Record | en_US |
dc.identifier.FolderNumber | OA_Scopus/WOS | - |
dc.description.pubStatus | Published | en_US |
dc.description.oaCategory | CC | en_US |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Amin_Renewable_Energy_Maximization.pdf | 2.42 MB | Adobe PDF | View/Open |
Page views
7
Citations as of Jun 30, 2024
Downloads
1
Citations as of Jun 30, 2024
SCOPUSTM
Citations
9
Citations as of Jun 21, 2024
WEB OF SCIENCETM
Citations
4
Citations as of Jul 4, 2024
![](/image/google_scholar.jpg)
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.