.png){kind=icon}
Return
Blockchain-enabled EV–renewable interaction using transformer forecasting and multi-agent learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.epsr.2026.113421.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposes a hybrid framework integrating Transformer forecasting and Multi-Agent Reinforcement Learning (MARL) for coordinated EV–renewable energy management. • Transformer encoder provides accurate forecasting of EV charging demand and renewable energy generation. • MARL enables decentralized and adaptive coordination among EVs, renewable sources, and grid participants. • Incorporates blockchain technology to ensure secure, transparent, and trustworthy energy transactions among prosumers. • Achieves 96.9% predictive reliability, 32.7% load balancing improvement, 26.4% efficiency enhancement, and 24 ms latency.
Keywords:
EV integration
Renewables optimization
Transformers MARL
Blockchain transactions
IoT load balancing and security
Journal
IF:
4.2
Papers:
1.2W
Citations:
2.2W
Organization
View more organizations
Cited Papers
ShareSaveKnowledge-guided self-learning control strategy for mixed vehicle platoons with delays.png)
Nature Communications
OAAI
Nature CommunicationsIF15.7
OAAIShareSaveA Novel Image Classification Approach via MobileNet Model for Security Assessment of Power System
PREAI
ShareSaveShareSaveFast dynamic identification algorithm for key nodes in distribution networks with large-scale DG and EV integrationAPPLIED ENERGY
APPLIED ENERGYIF11
PREAI
ShareSaveDetection of cyber attacks in electric vehicle charging systems using a remaining useful life generative adversarial networkSCIENTIFIC REPORTSOAAI
SCIENTIFIC REPORTSIF3.9
OAAIShareSave View more