返回
Blockchain-enabled EV–renewable interaction using transformer forecasting and multi-agent learning
DOI:10.1016/j.epsr.2026.113421.png)
摘要
En 中文
• 提出了一种集成Transformer预测和多智能体强化学习(MARL)的混合框架,用于协调电动汽车–可再生能源管理。
• Transformer编码器提供了电动汽车充电需求和可再生能源发电的准确预测。
• MARL使电动汽车、可再生能源和电网参与者之间能够实现去中心化和自适应协调。
• 融入区块链技术,以确保生产者之间安全、透明和可信赖的能量交易。
• 实现了96.9%的预测可靠性、32.7%的负荷平衡改进、26.4%的效率提升以及24毫秒的延迟。
Keyword:
EV integration
Renewables optimization
Transformers MARL
Blockchain transactions
IoT load balancing and security
期刊
IF:
4.2
论文数:
1.2W
被引数:
2.2W
机构
引用论文
EV Charging System Considering Power Dispatching Based on Multi-Agent LLMs and CGAN基于多Agent LLMs和CGAN的考虑电力调度的电动汽车充电系统
Knowledge-guided self-learning control strategy for mixed vehicle platoons with delays基于知识引导的自学习控制策略,用于存在时延的混合车辆编队
Nature Communications
IF15.7
Enhancing Resilience of Electric Vehicle Charging Management in Hydrogen–Electric Coupled Distribution Networks: A Risk-Characterization Multi-Agent Reinforcement Learning Approach氢-电耦合配电网中电动汽车充电管理的韧性提升:一种基于风险表征的多智能体强化学习方法
A Novel Image Classification Approach via MobileNet Model for Security Assessment of Power System一种基于MobileNet模型的新型图像分类方法用于电力系统安全评估
A Blockchain-Powered Secure Architecture for Cyber Marketplaces of Electric Vehicles基于区块链的电动汽车网络市场安全架构
Network-Constrained P2P Trading: A Safety-Aware Decentralized Multi-Agent Reinforcement Learning Approach网络约束的P2P交易: 一种安全感知的分散式多Agent强化学习方法
Fast dynamic identification algorithm for key nodes in distribution networks with large-scale DG and EV integration含大规模DG和EV集成的配电网关键节点快速动态识别算法
APPLIED ENERGY
IF11
Detection of cyber attacks in electric vehicle charging systems using a remaining useful life generative adversarial network使用剩余使用寿命生成对抗网络检测电动汽车充电系统中的网络攻击
SCIENTIFIC REPORTS
IF3.9


