Reinforcement Neural Network-Based Grid-Integrated PV Control and Battery Management System

dc.contributor.authorThajeel, Salah Mahdi
dc.contributor.authorAtilla, Doğu Çağdaş
dc.date.accessioned2025-05-05T06:04:21Z
dc.date.available2025-05-05T06:04:21Z
dc.date.issued2025
dc.departmentEnstitüler, Lisansüstü Eğitim Enstitüsü, Elektrik ve Bilgisayar Mühendisliği Ana Bilim Dalı
dc.description.abstractA reinforcement neural network-based grid-integrated photovoltaic (PV) system with a battery management system (BMS) was developed to enhance the efficiency and reliability of renewable energy systems. In such a setup, the PV system generates electricity, which can be used immediately, stored in batteries, or fed into the grid. The challenge lies in dynamically optimizing the power flow between these components to minimize energy costs, maximize the use of renewable energy, and maintain grid stability. Reinforcement learning (RL) combined with NNs offers a powerful solution by enabling the system to learn and adapt its energy management strategy in real time. By using the proposed techniques, the convergence time was decreased with lower complexity compared with existing approaches. The RL agent interacts with the environment (i.e., the grid, PV system, and battery), continuously improving its decisions regarding when to store energy, draw from the battery, and supply power to the grid. This intelligent control approach ensures optimal performance, contributing to a more sustainable and resilient energy system.
dc.identifier.citationThajeel, S. M., & Atilla, D. Ç. (2025). Reinforcement Neural Network-Based Grid-Integrated PV Control and Battery Management System. Energies, 18(3), 637.
dc.identifier.doi10.3390/en18030637
dc.identifier.issn1996-1073
dc.identifier.issue3
dc.identifier.scopus2-s2.0-85217543546
dc.identifier.urihttps://hdl.handle.net/20.500.12939/5738
dc.identifier.volume18
dc.identifier.wosWOS:001418538600001
dc.identifier.wosqualityQ3
dc.indekslendigikaynakScopus
dc.institutionauthorThajeel, Salah Mahdi
dc.institutionauthorAtilla, Doğu Çağdaş
dc.institutionauthorid0000-0002-4249-6951
dc.language.isoen
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)
dc.relation.ispartofEnergies
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Öğrenci
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectfuzzy logic controllers (FLCs)
dc.subjectmaximum power point tracking (MPPT)
dc.subjectphotovoltaic (PV) systems
dc.titleReinforcement Neural Network-Based Grid-Integrated PV Control and Battery Management System
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
Tam Metin / Full Text
Boyut:
5.78 MB
Biçim:
Adobe Portable Document Format
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: